langchain/14-Chat-Rest-API/openapi.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "id": "85fb2c03-ab88-4c8c-97e3-a7f2954555ab",
      "metadata": {
        "id": "85fb2c03-ab88-4c8c-97e3-a7f2954555ab"
      },
      "source": [
        "# OpenAPI Toolkit\n",
        "\n",
        "We can construct agents to consume arbitrary APIs, here APIs conformant to the `OpenAPI`/`Swagger` specification."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 32,
      "id": "798a442b",
      "metadata": {
        "id": "798a442b"
      },
      "outputs": [],
      "source": [
        "# NOTE: In this example. We must set `allow_dangerous_request=True` to enable the OpenAPI Agent to automatically use the Request Tool.\n",
        "# This can be dangerous for calling unwanted requests. Please make sure your custom OpenAPI spec (yaml) is safe.\n",
        "ALLOW_DANGEROUS_REQUEST = True"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "a389367b",
      "metadata": {
        "id": "a389367b"
      },
      "source": [
        "## 1st example: hierarchical planning agent\n",
        "\n",
        "In this example, we'll consider an approach called hierarchical planning, common in robotics and appearing in recent works for LLMs X robotics. We'll see it's a viable approach to start working with a massive API spec AND to assist with user queries that require multiple steps against the API.\n",
        "\n",
        "The idea is simple: to get coherent agent behavior over long sequences behavior & to save on tokens, we'll separate concerns: a \"planner\" will be responsible for what endpoints to call and a \"controller\" will be responsible for how to call them.\n",
        "\n",
        "In the initial implementation, the planner is an LLM chain that has the name and a short description for each endpoint in context. The controller is an LLM agent that is instantiated with documentation for only the endpoints for a particular plan. There's a lot left to get this working very robustly :)\n",
        "\n",
        "---"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "4b6ecf6e",
      "metadata": {
        "id": "4b6ecf6e"
      },
      "source": [
        "### To start, let's collect some OpenAPI specs."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 15,
      "id": "0adf3537",
      "metadata": {
        "id": "0adf3537"
      },
      "outputs": [],
      "source": [
        "import os\n",
        "\n",
        "import yaml"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "816011d8",
      "metadata": {
        "id": "816011d8"
      },
      "source": [
        "You will be able to get OpenAPI specs from here: [APIs-guru/openapi-directory](https://github.com/APIs-guru/openapi-directory)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 16,
      "id": "eb15cea0",
      "metadata": {
        "id": "eb15cea0",
        "outputId": "2a2d47d2-e5cf-4571-d83b-0868d3ef58ee"
      },
      "outputs": [],
      "source": [
        "# Run these steps only if we do not have Swagger yaml files of these APIs\n",
        "#!wget https://raw.githubusercontent.com/openai/openai-openapi/master/openapi.yaml -O openai_openapi.yaml\n",
        "#!wget https://raw.githubusercontent.com/APIs-guru/openapi-directory/main/APIs/spotify.com/1.0.0/openapi.yaml -O spotify_openapi.yaml"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 17,
      "id": "690a35bf",
      "metadata": {
        "id": "690a35bf"
      },
      "outputs": [],
      "source": [
        "from langchain_community.agent_toolkits.openapi.spec import reduce_openapi_spec"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 18,
      "id": "69a8e1b9",
      "metadata": {
        "id": "69a8e1b9"
      },
      "outputs": [],
      "source": [
        "with open(\"openai_openapi.yaml\") as f:\n",
        "    raw_openai_api_spec = yaml.load(f, Loader=yaml.Loader)\n",
        "openai_api_spec = reduce_openapi_spec(raw_openai_api_spec)\n",
        "\n",
        "with open(\"spotify_openapi.yaml\") as f:\n",
        "    raw_spotify_api_spec = yaml.load(f, Loader=yaml.Loader)\n",
        "spotify_api_spec = reduce_openapi_spec(raw_spotify_api_spec)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "ba833d49",
      "metadata": {
        "id": "ba833d49"
      },
      "source": [
        "---\n",
        "\n",
        "We'll work with the Spotify API as one of the examples of a somewhat complex API. There's a bit of auth-related setup to do if you want to replicate this.\n",
        "\n",
        "- You'll have to set up an application in the Spotify developer console, documented [here](https://developer.spotify.com/documentation/general/guides/authorization/), to get credentials: `CLIENT_ID`, `CLIENT_SECRET`, and `REDIRECT_URI`.\n",
        "- To get an access tokens (and keep them fresh), you can implement the oauth flows, or you can use `spotipy`. If you've set your Spotify creedentials as environment variables `SPOTIPY_CLIENT_ID`, `SPOTIPY_CLIENT_SECRET`, and `SPOTIPY_REDIRECT_URI`, you can use the helper functions below:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 19,
      "id": "c82b7c6e",
      "metadata": {},
      "outputs": [],
      "source": [
        "from dotenv import load_dotenv\n",
        "load_dotenv()\n",
        "\n",
        "os.environ['OPENAI_API_KEY']=os.getenv(\"OPENAI_API_KEY\")\n",
        "os.environ['SPOTIPY_CLIENT_ID']=os.getenv(\"SPOTIPY_CLIENT_ID\")\n",
        "os.environ['SPOTIPY_CLIENT_SECRET']=os.getenv(\"SPOTIPY_CLIENT_SECRET\")\n",
        "os.environ['SPOTIPY_REDIRECT_URI']=os.getenv(\"SPOTIPY_REDIRECT_URI\")\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 21,
      "id": "a82c2cfa",
      "metadata": {
        "id": "a82c2cfa"
      },
      "outputs": [],
      "source": [
        "import spotipy.util as util\n",
        "from langchain_community.utilities.requests import RequestsWrapper\n",
        "\n",
        "\n",
        "def construct_spotify_auth_headers(raw_spec: dict):\n",
        "    scopes = list(\n",
        "        raw_spec[\"components\"][\"securitySchemes\"][\"oauth_2_0\"][\"flows\"][\n",
        "            \"authorizationCode\"\n",
        "        ][\"scopes\"].keys()\n",
        "    )\n",
        "    access_token = util.prompt_for_user_token(scope=\",\".join(scopes))\n",
        "    return {\"Authorization\": f\"Bearer {access_token}\"}\n",
        "\n",
        "\n",
        "# Get API credentials.\n",
        "headers = construct_spotify_auth_headers(raw_spotify_api_spec)\n",
        "requests_wrapper = RequestsWrapper(headers=headers)\n",
        "\n",
        "# Notes: Make sure to enter the redirected link, such as: https://thangtrandev.net/?code=AQAyQl1aPpQs99k4MMqXeZBAzINpugn8Acb-E12BsZaNym0ztFJbe6ozNWCapD4Zcfv3NbDVo0_hoDnThKWH7yZl4qzU3gJ52jKA6RVmByqhDQyNa8iA35SY6r_AazJ1G24l0Yn2Y5lsp3wHmhTiygcs65TRMh_a9jyzZ0twu74uZB93Q4xkcVQe_QLFKQOuRChJw4G_FblvCy8wPqockd3FYqnAOo0uPApNwul6sJN8urRGH4nYgDl72t0E_QVSvD_vr5VadZ65Ejbb8jGS0gnLzzeEvJnRyL8lzlyCtGY3roJq1nUMp94xs9n3LJjdnW9mw_kBACVUmUpmvEI5Oh1RNtZOnd05BATNKfDo8ITsOQ2pC_9oDeQyQZpSSf9e4Y-r4-6TVCQ7HjIv1CrgZlvrv-NFLhXLsaHAEu_Q0YxQGyqpJgdjwGlJTet9lamNK4XCwAT3dWC1Trl_tiA8uliATOvusBUAp5gkkilg6WnMwXGTz035qevBGEY0WgkBWwQHa4MZGELjibI4gu5VgKXyiJJV6RpQCefNM2W5HdERfzsw-Mzx293Dn3AK2hndZyHlWB0nDgTPAxoQU1OQ2HLFDS7M0rg_tfIKw-Zj-iLePgKa552i54T-h_G0wTc2MNvA0q6MmvdlJBLl4XyJSbb2XcFV0gg3Fdih4PyABUKPwYXw6t2Can9UBXy3OVl7PY1v2AyyQ-EdCURprfM"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "76349780",
      "metadata": {
        "id": "76349780"
      },
      "source": [
        "### How big is this spec?"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 22,
      "id": "2a93271e",
      "metadata": {
        "id": "2a93271e",
        "outputId": "acb8012f-ea9b-41d2-a312-de208195f7e1"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "63"
            ]
          },
          "execution_count": 22,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "endpoints = [\n",
        "    (route, operation)\n",
        "    for route, operations in raw_spotify_api_spec[\"paths\"].items()\n",
        "    for operation in operations\n",
        "    if operation in [\"get\", \"post\"]\n",
        "]\n",
        "len(endpoints)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 23,
      "id": "eb829190",
      "metadata": {
        "id": "eb829190",
        "outputId": "d66d3eff-a390-42f7-9dae-0a8a71876d73"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "68910"
            ]
          },
          "execution_count": 23,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "import tiktoken\n",
        "\n",
        "enc = tiktoken.encoding_for_model(\"gpt-4\")\n",
        "\n",
        "\n",
        "def count_tokens(s):\n",
        "    return len(enc.encode(s))\n",
        "\n",
        "\n",
        "count_tokens(yaml.dump(raw_spotify_api_spec))"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "cbc4964e",
      "metadata": {
        "id": "cbc4964e"
      },
      "source": [
        "### Let's see some examples!\n",
        "\n",
        "Starting with GPT-4. (Some robustness iterations under way for GPT-3 family.)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 33,
      "id": "7f42ee84",
      "metadata": {
        "id": "7f42ee84",
        "outputId": "aed7a22a-7ec3-4657-c512-624293b06752"
      },
      "outputs": [],
      "source": [
        "from langchain_community.agent_toolkits.openapi import planner\n",
        "from langchain_openai import ChatOpenAI\n",
        "\n",
        "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0.0)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 34,
      "id": "38762cc0",
      "metadata": {
        "id": "38762cc0",
        "outputId": "b34a9550-dad0-49b5-e895-4480a7bd3b06"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3mAction: api_planner\n",
            "Action Input: I need to find the right API calls to create a playlist with the first song from the album \"Kind of Blue\" and name it \"Machine Blues\"\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m1. GET /albums with a query param to search for \"Kind of Blue\" to get the album's Spotify ID.\n",
            "2. GET /albums/{id}/tracks to get the tracks from the album \"Kind of Blue\". Take the Spotify ID of the first track.\n",
            "3. GET /me to get the current user's Spotify ID.\n",
            "4. POST /users/{user_id}/playlists to create a new playlist named \"Machine Blues\".\n",
            "5. POST /playlists/{playlist_id}/tracks to add the first song from the album \"Kind of Blue\" to the newly created playlist.\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3mI'm ready to execute the API calls.\n",
            "Action: api_controller\n",
            "Action Input: 1. GET /albums with a query param to search for \"Kind of Blue\" to get the album's Spotify ID.\n",
            "2. GET /albums/{id}/tracks to get the tracks from the album \"Kind of Blue\". Take the Spotify ID of the first track.\n",
            "3. GET /me to get the current user's Spotify ID.\n",
            "4. POST /users/{user_id}/playlists to create a new playlist named \"Machine Blues\".\n",
            "5. POST /playlists/{playlist_id}/tracks to add the first song from the album \"Kind of Blue\" to the newly created playlist.\u001b[0m\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n"
          ]
        },
        {
          "ename": "RateLimitError",
          "evalue": "Error code: 429 - {'error': {'message': 'Request too large for gpt-4 in organization org-CKrg0v0PHxuOodrFd2y0RurI on tokens per min (TPM): Limit 10000, Requested 26403. The input or output tokens must be reduced in order to run successfully. Visit https://platform.openai.com/account/rate-limits to learn more.', 'type': 'tokens', 'param': None, 'code': 'rate_limit_exceeded'}}",
          "output_type": "error",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mRateLimitError\u001b[0m                            Traceback (most recent call last)",
            "Cell \u001b[0;32mIn[34], line 11\u001b[0m\n\u001b[1;32m      2\u001b[0m spotify_agent \u001b[38;5;241m=\u001b[39m planner\u001b[38;5;241m.\u001b[39mcreate_openapi_agent(\n\u001b[1;32m      3\u001b[0m     spotify_api_spec,\n\u001b[1;32m      4\u001b[0m     requests_wrapper,\n\u001b[1;32m      5\u001b[0m     llm,\n\u001b[1;32m      6\u001b[0m     allow_dangerous_requests\u001b[38;5;241m=\u001b[39mALLOW_DANGEROUS_REQUEST,\n\u001b[1;32m      7\u001b[0m )\n\u001b[1;32m      8\u001b[0m user_query \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m      9\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmake me a playlist with the first song from kind of blue. call it machine blues.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     10\u001b[0m )\n\u001b[0;32m---> 11\u001b[0m \u001b[43mspotify_agent\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\u001b[43muser_query\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:170\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    168\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    169\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n\u001b[0;32m--> 170\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    171\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_end(outputs)\n\u001b[1;32m    173\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m include_run_info:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:160\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    157\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    158\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_inputs(inputs)\n\u001b[1;32m    159\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 160\u001b[0m         \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    161\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m    162\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call(inputs)\n\u001b[1;32m    163\u001b[0m     )\n\u001b[1;32m    165\u001b[0m     final_outputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprep_outputs(\n\u001b[1;32m    166\u001b[0m         inputs, outputs, return_only_outputs\n\u001b[1;32m    167\u001b[0m     )\n\u001b[1;32m    168\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/agents/agent.py:1624\u001b[0m, in \u001b[0;36mAgentExecutor._call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m   1622\u001b[0m \u001b[38;5;66;03m# We now enter the agent loop (until it returns something).\u001b[39;00m\n\u001b[1;32m   1623\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_continue(iterations, time_elapsed):\n\u001b[0;32m-> 1624\u001b[0m     next_step_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_take_next_step\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1625\u001b[0m \u001b[43m        \u001b[49m\u001b[43mname_to_tool_map\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1626\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcolor_mapping\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1627\u001b[0m \u001b[43m        \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1628\u001b[0m \u001b[43m        \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1629\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1630\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1631\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(next_step_output, AgentFinish):\n\u001b[1;32m   1632\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_return(\n\u001b[1;32m   1633\u001b[0m             next_step_output, intermediate_steps, run_manager\u001b[38;5;241m=\u001b[39mrun_manager\n\u001b[1;32m   1634\u001b[0m         )\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/agents/agent.py:1332\u001b[0m, in \u001b[0;36mAgentExecutor._take_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m   1321\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_take_next_step\u001b[39m(\n\u001b[1;32m   1322\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   1323\u001b[0m     name_to_tool_map: Dict[\u001b[38;5;28mstr\u001b[39m, BaseTool],\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1327\u001b[0m     run_manager: Optional[CallbackManagerForChainRun] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   1328\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Union[AgentFinish, List[Tuple[AgentAction, \u001b[38;5;28mstr\u001b[39m]]]:\n\u001b[1;32m   1329\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_consume_next_step(\n\u001b[1;32m   1330\u001b[0m         [\n\u001b[1;32m   1331\u001b[0m             a\n\u001b[0;32m-> 1332\u001b[0m             \u001b[38;5;28;01mfor\u001b[39;00m a \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_iter_next_step(\n\u001b[1;32m   1333\u001b[0m                 name_to_tool_map,\n\u001b[1;32m   1334\u001b[0m                 color_mapping,\n\u001b[1;32m   1335\u001b[0m                 inputs,\n\u001b[1;32m   1336\u001b[0m                 intermediate_steps,\n\u001b[1;32m   1337\u001b[0m                 run_manager,\n\u001b[1;32m   1338\u001b[0m             )\n\u001b[1;32m   1339\u001b[0m         ]\n\u001b[1;32m   1340\u001b[0m     )\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/agents/agent.py:1415\u001b[0m, in \u001b[0;36mAgentExecutor._iter_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m   1413\u001b[0m     \u001b[38;5;28;01myield\u001b[39;00m agent_action\n\u001b[1;32m   1414\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m agent_action \u001b[38;5;129;01min\u001b[39;00m actions:\n\u001b[0;32m-> 1415\u001b[0m     \u001b[38;5;28;01myield\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_perform_agent_action\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1416\u001b[0m \u001b[43m        \u001b[49m\u001b[43mname_to_tool_map\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcolor_mapping\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43magent_action\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\n\u001b[1;32m   1417\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/agents/agent.py:1437\u001b[0m, in \u001b[0;36mAgentExecutor._perform_agent_action\u001b[0;34m(self, name_to_tool_map, color_mapping, agent_action, run_manager)\u001b[0m\n\u001b[1;32m   1435\u001b[0m         tool_run_kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mllm_prefix\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   1436\u001b[0m     \u001b[38;5;66;03m# We then call the tool on the tool input to get an observation\u001b[39;00m\n\u001b[0;32m-> 1437\u001b[0m     observation \u001b[38;5;241m=\u001b[39m \u001b[43mtool\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1438\u001b[0m \u001b[43m        \u001b[49m\u001b[43magent_action\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtool_input\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1439\u001b[0m \u001b[43m        \u001b[49m\u001b[43mverbose\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mverbose\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1440\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcolor\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcolor\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1441\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_child\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m   1442\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mtool_run_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1443\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1444\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m   1445\u001b[0m     tool_run_kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_action_agent\u001b[38;5;241m.\u001b[39mtool_run_logging_kwargs()\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/tools/base.py:725\u001b[0m, in \u001b[0;36mBaseTool.run\u001b[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, config, tool_call_id, **kwargs)\u001b[0m\n\u001b[1;32m    723\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m error_to_raise:\n\u001b[1;32m    724\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_tool_error(error_to_raise)\n\u001b[0;32m--> 725\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m error_to_raise\n\u001b[1;32m    726\u001b[0m output \u001b[38;5;241m=\u001b[39m _format_output(content, artifact, tool_call_id, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mname, status)\n\u001b[1;32m    727\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_tool_end(output, color\u001b[38;5;241m=\u001b[39mcolor, name\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mname, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/tools/base.py:693\u001b[0m, in \u001b[0;36mBaseTool.run\u001b[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, config, tool_call_id, **kwargs)\u001b[0m\n\u001b[1;32m    691\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m config_param \u001b[38;5;241m:=\u001b[39m _get_runnable_config_param(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_run):\n\u001b[1;32m    692\u001b[0m     tool_kwargs \u001b[38;5;241m=\u001b[39m tool_kwargs \u001b[38;5;241m|\u001b[39m {config_param: config}\n\u001b[0;32m--> 693\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[43mcontext\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_run\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mtool_args\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mtool_kwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    694\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mresponse_format \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcontent_and_artifact\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m    695\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(response, \u001b[38;5;28mtuple\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(response) \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m2\u001b[39m:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/tools/simple.py:94\u001b[0m, in \u001b[0;36mTool._run\u001b[0;34m(self, config, run_manager, *args, **kwargs)\u001b[0m\n\u001b[1;32m     92\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m config_param \u001b[38;5;241m:=\u001b[39m _get_runnable_config_param(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfunc):\n\u001b[1;32m     93\u001b[0m         kwargs[config_param] \u001b[38;5;241m=\u001b[39m config\n\u001b[0;32m---> 94\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     95\u001b[0m msg \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mTool does not support sync invocation.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     96\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mNotImplementedError\u001b[39;00m(msg)\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_community/agent_toolkits/openapi/planner.py:374\u001b[0m, in \u001b[0;36m_create_api_controller_tool.<locals>._create_and_run_api_controller_agent\u001b[0;34m(plan_str)\u001b[0m\n\u001b[1;32m    364\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mendpoint_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m endpoint does not exist.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m    366\u001b[0m agent \u001b[38;5;241m=\u001b[39m _create_api_controller_agent(\n\u001b[1;32m    367\u001b[0m     base_url,\n\u001b[1;32m    368\u001b[0m     docs_str,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    372\u001b[0m     allowed_operations,\n\u001b[1;32m    373\u001b[0m )\n\u001b[0;32m--> 374\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43magent\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\u001b[43mplan_str\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/_api/deprecation.py:182\u001b[0m, in \u001b[0;36mdeprecated.<locals>.deprecate.<locals>.warning_emitting_wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    180\u001b[0m     warned \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m    181\u001b[0m     emit_warning()\n\u001b[0;32m--> 182\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapped\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:606\u001b[0m, in \u001b[0;36mChain.run\u001b[0;34m(self, callbacks, tags, metadata, *args, **kwargs)\u001b[0m\n\u001b[1;32m    604\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(args) \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m    605\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m`run` supports only one positional argument.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 606\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43margs\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtags\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtags\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmetadata\u001b[49m\u001b[43m)\u001b[49m[\n\u001b[1;32m    607\u001b[0m         _output_key\n\u001b[1;32m    608\u001b[0m     ]\n\u001b[1;32m    610\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m kwargs \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m args:\n\u001b[1;32m    611\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m(kwargs, callbacks\u001b[38;5;241m=\u001b[39mcallbacks, tags\u001b[38;5;241m=\u001b[39mtags, metadata\u001b[38;5;241m=\u001b[39mmetadata)[\n\u001b[1;32m    612\u001b[0m         _output_key\n\u001b[1;32m    613\u001b[0m     ]\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/_api/deprecation.py:182\u001b[0m, in \u001b[0;36mdeprecated.<locals>.deprecate.<locals>.warning_emitting_wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    180\u001b[0m     warned \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m    181\u001b[0m     emit_warning()\n\u001b[0;32m--> 182\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapped\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:389\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks, tags, metadata, run_name, include_run_info)\u001b[0m\n\u001b[1;32m    357\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Execute the chain.\u001b[39;00m\n\u001b[1;32m    358\u001b[0m \n\u001b[1;32m    359\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    380\u001b[0m \u001b[38;5;124;03m        `Chain.output_keys`.\u001b[39;00m\n\u001b[1;32m    381\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    382\u001b[0m config \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m    383\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcallbacks\u001b[39m\u001b[38;5;124m\"\u001b[39m: callbacks,\n\u001b[1;32m    384\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtags\u001b[39m\u001b[38;5;124m\"\u001b[39m: tags,\n\u001b[1;32m    385\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmetadata\u001b[39m\u001b[38;5;124m\"\u001b[39m: metadata,\n\u001b[1;32m    386\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_name\u001b[39m\u001b[38;5;124m\"\u001b[39m: run_name,\n\u001b[1;32m    387\u001b[0m }\n\u001b[0;32m--> 389\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    390\u001b[0m \u001b[43m    \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    391\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast\u001b[49m\u001b[43m(\u001b[49m\u001b[43mRunnableConfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m{\u001b[49m\u001b[43mk\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mitems\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mis\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m}\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    392\u001b[0m \u001b[43m    \u001b[49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    393\u001b[0m \u001b[43m    \u001b[49m\u001b[43minclude_run_info\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minclude_run_info\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    394\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:170\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    168\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    169\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n\u001b[0;32m--> 170\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    171\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_end(outputs)\n\u001b[1;32m    173\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m include_run_info:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:160\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    157\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    158\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_inputs(inputs)\n\u001b[1;32m    159\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 160\u001b[0m         \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    161\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m    162\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call(inputs)\n\u001b[1;32m    163\u001b[0m     )\n\u001b[1;32m    165\u001b[0m     final_outputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprep_outputs(\n\u001b[1;32m    166\u001b[0m         inputs, outputs, return_only_outputs\n\u001b[1;32m    167\u001b[0m     )\n\u001b[1;32m    168\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/agents/agent.py:1624\u001b[0m, in \u001b[0;36mAgentExecutor._call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m   1622\u001b[0m \u001b[38;5;66;03m# We now enter the agent loop (until it returns something).\u001b[39;00m\n\u001b[1;32m   1623\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_continue(iterations, time_elapsed):\n\u001b[0;32m-> 1624\u001b[0m     next_step_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_take_next_step\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1625\u001b[0m \u001b[43m        \u001b[49m\u001b[43mname_to_tool_map\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1626\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcolor_mapping\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1627\u001b[0m \u001b[43m        \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1628\u001b[0m \u001b[43m        \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1629\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1630\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1631\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(next_step_output, AgentFinish):\n\u001b[1;32m   1632\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_return(\n\u001b[1;32m   1633\u001b[0m             next_step_output, intermediate_steps, run_manager\u001b[38;5;241m=\u001b[39mrun_manager\n\u001b[1;32m   1634\u001b[0m         )\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/agents/agent.py:1332\u001b[0m, in \u001b[0;36mAgentExecutor._take_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m   1321\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_take_next_step\u001b[39m(\n\u001b[1;32m   1322\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   1323\u001b[0m     name_to_tool_map: Dict[\u001b[38;5;28mstr\u001b[39m, BaseTool],\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1327\u001b[0m     run_manager: Optional[CallbackManagerForChainRun] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   1328\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Union[AgentFinish, List[Tuple[AgentAction, \u001b[38;5;28mstr\u001b[39m]]]:\n\u001b[1;32m   1329\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_consume_next_step(\n\u001b[1;32m   1330\u001b[0m         [\n\u001b[1;32m   1331\u001b[0m             a\n\u001b[0;32m-> 1332\u001b[0m             \u001b[38;5;28;01mfor\u001b[39;00m a \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_iter_next_step(\n\u001b[1;32m   1333\u001b[0m                 name_to_tool_map,\n\u001b[1;32m   1334\u001b[0m                 color_mapping,\n\u001b[1;32m   1335\u001b[0m                 inputs,\n\u001b[1;32m   1336\u001b[0m                 intermediate_steps,\n\u001b[1;32m   1337\u001b[0m                 run_manager,\n\u001b[1;32m   1338\u001b[0m             )\n\u001b[1;32m   1339\u001b[0m         ]\n\u001b[1;32m   1340\u001b[0m     )\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/agents/agent.py:1358\u001b[0m, in \u001b[0;36mAgentExecutor._iter_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m   1355\u001b[0m     intermediate_steps \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_prepare_intermediate_steps(intermediate_steps)\n\u001b[1;32m   1357\u001b[0m     \u001b[38;5;66;03m# Call the LLM to see what to do.\u001b[39;00m\n\u001b[0;32m-> 1358\u001b[0m     output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_action_agent\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mplan\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1359\u001b[0m \u001b[43m        \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1360\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_child\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m   1361\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1362\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1363\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m OutputParserException \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m   1364\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_parsing_errors, \u001b[38;5;28mbool\u001b[39m):\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/agents/agent.py:804\u001b[0m, in \u001b[0;36mAgent.plan\u001b[0;34m(self, intermediate_steps, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m    792\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Given input, decided what to do.\u001b[39;00m\n\u001b[1;32m    793\u001b[0m \n\u001b[1;32m    794\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    801\u001b[0m \u001b[38;5;124;03m    Action specifying what tool to use.\u001b[39;00m\n\u001b[1;32m    802\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    803\u001b[0m full_inputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mget_full_inputs(intermediate_steps, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m--> 804\u001b[0m full_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mllm_chain\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpredict\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mfull_inputs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    805\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_parser\u001b[38;5;241m.\u001b[39mparse(full_output)\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/llm.py:318\u001b[0m, in \u001b[0;36mLLMChain.predict\u001b[0;34m(self, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m    303\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpredict\u001b[39m(\u001b[38;5;28mself\u001b[39m, callbacks: Callbacks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28mstr\u001b[39m:\n\u001b[1;32m    304\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Format prompt with kwargs and pass to LLM.\u001b[39;00m\n\u001b[1;32m    305\u001b[0m \n\u001b[1;32m    306\u001b[0m \u001b[38;5;124;03m    Args:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    316\u001b[0m \u001b[38;5;124;03m            completion = llm.predict(adjective=\"funny\")\u001b[39;00m\n\u001b[1;32m    317\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[0;32m--> 318\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m)\u001b[49m[\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_key]\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/_api/deprecation.py:182\u001b[0m, in \u001b[0;36mdeprecated.<locals>.deprecate.<locals>.warning_emitting_wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    180\u001b[0m     warned \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m    181\u001b[0m     emit_warning()\n\u001b[0;32m--> 182\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapped\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:389\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks, tags, metadata, run_name, include_run_info)\u001b[0m\n\u001b[1;32m    357\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Execute the chain.\u001b[39;00m\n\u001b[1;32m    358\u001b[0m \n\u001b[1;32m    359\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    380\u001b[0m \u001b[38;5;124;03m        `Chain.output_keys`.\u001b[39;00m\n\u001b[1;32m    381\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    382\u001b[0m config \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m    383\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcallbacks\u001b[39m\u001b[38;5;124m\"\u001b[39m: callbacks,\n\u001b[1;32m    384\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtags\u001b[39m\u001b[38;5;124m\"\u001b[39m: tags,\n\u001b[1;32m    385\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmetadata\u001b[39m\u001b[38;5;124m\"\u001b[39m: metadata,\n\u001b[1;32m    386\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_name\u001b[39m\u001b[38;5;124m\"\u001b[39m: run_name,\n\u001b[1;32m    387\u001b[0m }\n\u001b[0;32m--> 389\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    390\u001b[0m \u001b[43m    \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    391\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast\u001b[49m\u001b[43m(\u001b[49m\u001b[43mRunnableConfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m{\u001b[49m\u001b[43mk\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mitems\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mis\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m}\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    392\u001b[0m \u001b[43m    \u001b[49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    393\u001b[0m \u001b[43m    \u001b[49m\u001b[43minclude_run_info\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minclude_run_info\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    394\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:170\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    168\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    169\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n\u001b[0;32m--> 170\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    171\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_end(outputs)\n\u001b[1;32m    173\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m include_run_info:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:160\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    157\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    158\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_inputs(inputs)\n\u001b[1;32m    159\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 160\u001b[0m         \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    161\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m    162\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call(inputs)\n\u001b[1;32m    163\u001b[0m     )\n\u001b[1;32m    165\u001b[0m     final_outputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprep_outputs(\n\u001b[1;32m    166\u001b[0m         inputs, outputs, return_only_outputs\n\u001b[1;32m    167\u001b[0m     )\n\u001b[1;32m    168\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/llm.py:126\u001b[0m, in \u001b[0;36mLLMChain._call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m    121\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_call\u001b[39m(\n\u001b[1;32m    122\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    123\u001b[0m     inputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any],\n\u001b[1;32m    124\u001b[0m     run_manager: Optional[CallbackManagerForChainRun] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m    125\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Dict[\u001b[38;5;28mstr\u001b[39m, \u001b[38;5;28mstr\u001b[39m]:\n\u001b[0;32m--> 126\u001b[0m     response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[43m[\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    127\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcreate_outputs(response)[\u001b[38;5;241m0\u001b[39m]\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/llm.py:138\u001b[0m, in \u001b[0;36mLLMChain.generate\u001b[0;34m(self, input_list, run_manager)\u001b[0m\n\u001b[1;32m    136\u001b[0m callbacks \u001b[38;5;241m=\u001b[39m run_manager\u001b[38;5;241m.\u001b[39mget_child() \u001b[38;5;28;01mif\u001b[39;00m run_manager \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    137\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm, BaseLanguageModel):\n\u001b[0;32m--> 138\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mllm\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate_prompt\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    139\u001b[0m \u001b[43m        \u001b[49m\u001b[43mprompts\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    140\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    141\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    142\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mllm_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    143\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    144\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    145\u001b[0m     results \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm\u001b[38;5;241m.\u001b[39mbind(stop\u001b[38;5;241m=\u001b[39mstop, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm_kwargs)\u001b[38;5;241m.\u001b[39mbatch(\n\u001b[1;32m    146\u001b[0m         cast(List, prompts), {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcallbacks\u001b[39m\u001b[38;5;124m\"\u001b[39m: callbacks}\n\u001b[1;32m    147\u001b[0m     )\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py:786\u001b[0m, in \u001b[0;36mBaseChatModel.generate_prompt\u001b[0;34m(self, prompts, stop, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m    778\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mgenerate_prompt\u001b[39m(\n\u001b[1;32m    779\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    780\u001b[0m     prompts: \u001b[38;5;28mlist\u001b[39m[PromptValue],\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    783\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m    784\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m LLMResult:\n\u001b[1;32m    785\u001b[0m     prompt_messages \u001b[38;5;241m=\u001b[39m [p\u001b[38;5;241m.\u001b[39mto_messages() \u001b[38;5;28;01mfor\u001b[39;00m p \u001b[38;5;129;01min\u001b[39;00m prompts]\n\u001b[0;32m--> 786\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[43mprompt_messages\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py:643\u001b[0m, in \u001b[0;36mBaseChatModel.generate\u001b[0;34m(self, messages, stop, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001b[0m\n\u001b[1;32m    641\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m run_managers:\n\u001b[1;32m    642\u001b[0m             run_managers[i]\u001b[38;5;241m.\u001b[39mon_llm_error(e, response\u001b[38;5;241m=\u001b[39mLLMResult(generations\u001b[38;5;241m=\u001b[39m[]))\n\u001b[0;32m--> 643\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    644\u001b[0m flattened_outputs \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m    645\u001b[0m     LLMResult(generations\u001b[38;5;241m=\u001b[39m[res\u001b[38;5;241m.\u001b[39mgenerations], llm_output\u001b[38;5;241m=\u001b[39mres\u001b[38;5;241m.\u001b[39mllm_output)  \u001b[38;5;66;03m# type: ignore[list-item]\u001b[39;00m\n\u001b[1;32m    646\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m res \u001b[38;5;129;01min\u001b[39;00m results\n\u001b[1;32m    647\u001b[0m ]\n\u001b[1;32m    648\u001b[0m llm_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_combine_llm_outputs([res\u001b[38;5;241m.\u001b[39mllm_output \u001b[38;5;28;01mfor\u001b[39;00m res \u001b[38;5;129;01min\u001b[39;00m results])\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py:633\u001b[0m, in \u001b[0;36mBaseChatModel.generate\u001b[0;34m(self, messages, stop, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001b[0m\n\u001b[1;32m    630\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i, m \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(messages):\n\u001b[1;32m    631\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    632\u001b[0m         results\u001b[38;5;241m.\u001b[39mappend(\n\u001b[0;32m--> 633\u001b[0m             \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_generate_with_cache\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    634\u001b[0m \u001b[43m                \u001b[49m\u001b[43mm\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    635\u001b[0m \u001b[43m                \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    636\u001b[0m \u001b[43m                \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_managers\u001b[49m\u001b[43m[\u001b[49m\u001b[43mi\u001b[49m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mrun_managers\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m    637\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    638\u001b[0m \u001b[43m            \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    639\u001b[0m         )\n\u001b[1;32m    640\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    641\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m run_managers:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py:851\u001b[0m, in \u001b[0;36mBaseChatModel._generate_with_cache\u001b[0;34m(self, messages, stop, run_manager, **kwargs)\u001b[0m\n\u001b[1;32m    849\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    850\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m inspect\u001b[38;5;241m.\u001b[39msignature(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_generate)\u001b[38;5;241m.\u001b[39mparameters\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_manager\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[0;32m--> 851\u001b[0m         result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_generate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    852\u001b[0m \u001b[43m            \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\n\u001b[1;32m    853\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    854\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    855\u001b[0m         result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_generate(messages, stop\u001b[38;5;241m=\u001b[39mstop, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_openai/chat_models/base.py:717\u001b[0m, in \u001b[0;36mBaseChatOpenAI._generate\u001b[0;34m(self, messages, stop, run_manager, **kwargs)\u001b[0m\n\u001b[1;32m    715\u001b[0m     generation_info \u001b[38;5;241m=\u001b[39m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mheaders\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28mdict\u001b[39m(raw_response\u001b[38;5;241m.\u001b[39mheaders)}\n\u001b[1;32m    716\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 717\u001b[0m     response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mclient\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mpayload\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    718\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_create_chat_result(response, generation_info)\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/_utils/_utils.py:275\u001b[0m, in \u001b[0;36mrequired_args.<locals>.inner.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    273\u001b[0m             msg \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMissing required argument: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mquote(missing[\u001b[38;5;241m0\u001b[39m])\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    274\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(msg)\n\u001b[0;32m--> 275\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/resources/chat/completions.py:859\u001b[0m, in \u001b[0;36mCompletions.create\u001b[0;34m(self, messages, model, audio, frequency_penalty, function_call, functions, logit_bias, logprobs, max_completion_tokens, max_tokens, metadata, modalities, n, parallel_tool_calls, prediction, presence_penalty, reasoning_effort, response_format, seed, service_tier, stop, store, stream, stream_options, temperature, tool_choice, tools, top_logprobs, top_p, user, extra_headers, extra_query, extra_body, timeout)\u001b[0m\n\u001b[1;32m    817\u001b[0m \u001b[38;5;129m@required_args\u001b[39m([\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmessages\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel\u001b[39m\u001b[38;5;124m\"\u001b[39m], [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmessages\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstream\u001b[39m\u001b[38;5;124m\"\u001b[39m])\n\u001b[1;32m    818\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcreate\u001b[39m(\n\u001b[1;32m    819\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    856\u001b[0m     timeout: \u001b[38;5;28mfloat\u001b[39m \u001b[38;5;241m|\u001b[39m httpx\u001b[38;5;241m.\u001b[39mTimeout \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m|\u001b[39m NotGiven \u001b[38;5;241m=\u001b[39m NOT_GIVEN,\n\u001b[1;32m    857\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ChatCompletion \u001b[38;5;241m|\u001b[39m Stream[ChatCompletionChunk]:\n\u001b[1;32m    858\u001b[0m     validate_response_format(response_format)\n\u001b[0;32m--> 859\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_post\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    860\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/chat/completions\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m    861\u001b[0m \u001b[43m        \u001b[49m\u001b[43mbody\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmaybe_transform\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    862\u001b[0m \u001b[43m            \u001b[49m\u001b[43m{\u001b[49m\n\u001b[1;32m    863\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmessages\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    864\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmodel\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    865\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43maudio\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43maudio\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    866\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfrequency_penalty\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfrequency_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    867\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfunction_call\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunction_call\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    868\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfunctions\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunctions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    869\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mlogit_bias\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogit_bias\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    870\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mlogprobs\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    871\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmax_completion_tokens\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_completion_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    872\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmax_tokens\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    873\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmetadata\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    874\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmodalities\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodalities\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    875\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mn\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mn\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    876\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mparallel_tool_calls\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mparallel_tool_calls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    877\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mprediction\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mprediction\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    878\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mpresence_penalty\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mpresence_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    879\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mreasoning_effort\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mreasoning_effort\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    880\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mresponse_format\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mresponse_format\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    881\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mseed\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mseed\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    882\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mservice_tier\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mservice_tier\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    883\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstop\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    884\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstore\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstore\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    885\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstream\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    886\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstream_options\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    887\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtemperature\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtemperature\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    888\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtool_choice\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtool_choice\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    889\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtools\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtools\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    890\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtop_logprobs\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_logprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    891\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtop_p\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_p\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    892\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43muser\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43muser\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    893\u001b[0m \u001b[43m            \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    894\u001b[0m \u001b[43m            \u001b[49m\u001b[43mcompletion_create_params\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mCompletionCreateParams\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    895\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    896\u001b[0m \u001b[43m        \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmake_request_options\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    897\u001b[0m \u001b[43m            \u001b[49m\u001b[43mextra_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_headers\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_query\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_query\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_body\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_body\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\n\u001b[1;32m    898\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    899\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mChatCompletion\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    900\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m    901\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mStream\u001b[49m\u001b[43m[\u001b[49m\u001b[43mChatCompletionChunk\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    902\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/_base_client.py:1280\u001b[0m, in \u001b[0;36mSyncAPIClient.post\u001b[0;34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1266\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpost\u001b[39m(\n\u001b[1;32m   1267\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   1268\u001b[0m     path: \u001b[38;5;28mstr\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1275\u001b[0m     stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   1276\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ResponseT \u001b[38;5;241m|\u001b[39m _StreamT:\n\u001b[1;32m   1277\u001b[0m     opts \u001b[38;5;241m=\u001b[39m FinalRequestOptions\u001b[38;5;241m.\u001b[39mconstruct(\n\u001b[1;32m   1278\u001b[0m         method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpost\u001b[39m\u001b[38;5;124m\"\u001b[39m, url\u001b[38;5;241m=\u001b[39mpath, json_data\u001b[38;5;241m=\u001b[39mbody, files\u001b[38;5;241m=\u001b[39mto_httpx_files(files), \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39moptions\n\u001b[1;32m   1279\u001b[0m     )\n\u001b[0;32m-> 1280\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m cast(ResponseT, \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mopts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m)\u001b[49m)\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/_base_client.py:957\u001b[0m, in \u001b[0;36mSyncAPIClient.request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m    954\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    955\u001b[0m     retries_taken \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0\u001b[39m\n\u001b[0;32m--> 957\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    958\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    959\u001b[0m \u001b[43m    \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    960\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    961\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    962\u001b[0m \u001b[43m    \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    963\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/_base_client.py:1046\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1044\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m remaining_retries \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_retry(err\u001b[38;5;241m.\u001b[39mresponse):\n\u001b[1;32m   1045\u001b[0m     err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m-> 1046\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_retry_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1047\u001b[0m \u001b[43m        \u001b[49m\u001b[43minput_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1048\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1049\u001b[0m \u001b[43m        \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1050\u001b[0m \u001b[43m        \u001b[49m\u001b[43mresponse_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1051\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1052\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1053\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1055\u001b[0m \u001b[38;5;66;03m# If the response is streamed then we need to explicitly read the response\u001b[39;00m\n\u001b[1;32m   1056\u001b[0m \u001b[38;5;66;03m# to completion before attempting to access the response text.\u001b[39;00m\n\u001b[1;32m   1057\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mis_closed:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/_base_client.py:1095\u001b[0m, in \u001b[0;36mSyncAPIClient._retry_request\u001b[0;34m(self, options, cast_to, retries_taken, response_headers, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1091\u001b[0m \u001b[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001b[39;00m\n\u001b[1;32m   1092\u001b[0m \u001b[38;5;66;03m# different thread if necessary.\u001b[39;00m\n\u001b[1;32m   1093\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(timeout)\n\u001b[0;32m-> 1095\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1096\u001b[0m \u001b[43m    \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1097\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1098\u001b[0m \u001b[43m    \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1099\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1100\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1101\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/_base_client.py:1046\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1044\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m remaining_retries \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_retry(err\u001b[38;5;241m.\u001b[39mresponse):\n\u001b[1;32m   1045\u001b[0m     err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m-> 1046\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_retry_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1047\u001b[0m \u001b[43m        \u001b[49m\u001b[43minput_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1048\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1049\u001b[0m \u001b[43m        \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1050\u001b[0m \u001b[43m        \u001b[49m\u001b[43mresponse_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1051\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1052\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1053\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1055\u001b[0m \u001b[38;5;66;03m# If the response is streamed then we need to explicitly read the response\u001b[39;00m\n\u001b[1;32m   1056\u001b[0m \u001b[38;5;66;03m# to completion before attempting to access the response text.\u001b[39;00m\n\u001b[1;32m   1057\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mis_closed:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/_base_client.py:1095\u001b[0m, in \u001b[0;36mSyncAPIClient._retry_request\u001b[0;34m(self, options, cast_to, retries_taken, response_headers, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1091\u001b[0m \u001b[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001b[39;00m\n\u001b[1;32m   1092\u001b[0m \u001b[38;5;66;03m# different thread if necessary.\u001b[39;00m\n\u001b[1;32m   1093\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(timeout)\n\u001b[0;32m-> 1095\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1096\u001b[0m \u001b[43m    \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1097\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1098\u001b[0m \u001b[43m    \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1099\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1100\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1101\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/_base_client.py:1061\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1058\u001b[0m         err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mread()\n\u001b[1;32m   1060\u001b[0m     log\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRe-raising status error\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m-> 1061\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_make_status_error_from_response(err\u001b[38;5;241m.\u001b[39mresponse) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   1063\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_process_response(\n\u001b[1;32m   1064\u001b[0m     cast_to\u001b[38;5;241m=\u001b[39mcast_to,\n\u001b[1;32m   1065\u001b[0m     options\u001b[38;5;241m=\u001b[39moptions,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1069\u001b[0m     retries_taken\u001b[38;5;241m=\u001b[39mretries_taken,\n\u001b[1;32m   1070\u001b[0m )\n",
            "\u001b[0;31mRateLimitError\u001b[0m: Error code: 429 - {'error': {'message': 'Request too large for gpt-4 in organization org-CKrg0v0PHxuOodrFd2y0RurI on tokens per min (TPM): Limit 10000, Requested 26403. The input or output tokens must be reduced in order to run successfully. Visit https://platform.openai.com/account/rate-limits to learn more.', 'type': 'tokens', 'param': None, 'code': 'rate_limit_exceeded'}}"
          ]
        }
      ],
      "source": [
        "# NOTE: set allow_dangerous_requests manually for security concern https://python.langchain.com/docs/security\n",
        "spotify_agent = planner.create_openapi_agent(\n",
        "    spotify_api_spec,\n",
        "    requests_wrapper,\n",
        "    llm,\n",
        "    allow_dangerous_requests=ALLOW_DANGEROUS_REQUEST,\n",
        ")\n",
        "user_query = (\n",
        "    \"make me a playlist with the first song from kind of blue. call it machine blues.\"\n",
        ")\n",
        "spotify_agent.invoke(user_query)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 35,
      "id": "96184181",
      "metadata": {
        "id": "96184181",
        "outputId": "5af9d10f-5528-4e3d-ea4d-3f7eb9f6a313"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3mAction: api_planner\n",
            "Action Input: I need to find the right API calls to get a blues song recommendation for the user\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m1. GET /me to get the current user's profile information.\n",
            "2. GET /recommendations/available-genre-seeds to get a list of available genres.\n",
            "3. GET /recommendations with a query param to get a blues song recommendation for the user.\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3mI'm ready to execute the API calls.\n",
            "Action: api_controller\n",
            "Action Input: 1. GET /me to get the current user's profile information.\n",
            "2. GET /recommendations/available-genre-seeds to get a list of available genres.\n",
            "3. GET /recommendations with a query param to get a blues song recommendation for the user.\u001b[0m\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n"
          ]
        },
        {
          "ename": "RateLimitError",
          "evalue": "Error code: 429 - {'error': {'message': 'Request too large for gpt-4 in organization org-CKrg0v0PHxuOodrFd2y0RurI on tokens per min (TPM): Limit 10000, Requested 16804. The input or output tokens must be reduced in order to run successfully. Visit https://platform.openai.com/account/rate-limits to learn more.', 'type': 'tokens', 'param': None, 'code': 'rate_limit_exceeded'}}",
          "output_type": "error",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mRateLimitError\u001b[0m                            Traceback (most recent call last)",
            "Cell \u001b[0;32mIn[35], line 2\u001b[0m\n\u001b[1;32m      1\u001b[0m user_query \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mgive me a song I\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124md like, make it blues-ey\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m----> 2\u001b[0m \u001b[43mspotify_agent\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\u001b[43muser_query\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:170\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    168\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    169\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n\u001b[0;32m--> 170\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    171\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_end(outputs)\n\u001b[1;32m    173\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m include_run_info:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:160\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    157\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    158\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_inputs(inputs)\n\u001b[1;32m    159\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 160\u001b[0m         \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    161\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m    162\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call(inputs)\n\u001b[1;32m    163\u001b[0m     )\n\u001b[1;32m    165\u001b[0m     final_outputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprep_outputs(\n\u001b[1;32m    166\u001b[0m         inputs, outputs, return_only_outputs\n\u001b[1;32m    167\u001b[0m     )\n\u001b[1;32m    168\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/agents/agent.py:1624\u001b[0m, in \u001b[0;36mAgentExecutor._call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m   1622\u001b[0m \u001b[38;5;66;03m# We now enter the agent loop (until it returns something).\u001b[39;00m\n\u001b[1;32m   1623\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_continue(iterations, time_elapsed):\n\u001b[0;32m-> 1624\u001b[0m     next_step_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_take_next_step\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1625\u001b[0m \u001b[43m        \u001b[49m\u001b[43mname_to_tool_map\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1626\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcolor_mapping\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1627\u001b[0m \u001b[43m        \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1628\u001b[0m \u001b[43m        \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1629\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1630\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1631\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(next_step_output, AgentFinish):\n\u001b[1;32m   1632\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_return(\n\u001b[1;32m   1633\u001b[0m             next_step_output, intermediate_steps, run_manager\u001b[38;5;241m=\u001b[39mrun_manager\n\u001b[1;32m   1634\u001b[0m         )\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/agents/agent.py:1332\u001b[0m, in \u001b[0;36mAgentExecutor._take_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m   1321\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_take_next_step\u001b[39m(\n\u001b[1;32m   1322\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   1323\u001b[0m     name_to_tool_map: Dict[\u001b[38;5;28mstr\u001b[39m, BaseTool],\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1327\u001b[0m     run_manager: Optional[CallbackManagerForChainRun] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   1328\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Union[AgentFinish, List[Tuple[AgentAction, \u001b[38;5;28mstr\u001b[39m]]]:\n\u001b[1;32m   1329\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_consume_next_step(\n\u001b[1;32m   1330\u001b[0m         [\n\u001b[1;32m   1331\u001b[0m             a\n\u001b[0;32m-> 1332\u001b[0m             \u001b[38;5;28;01mfor\u001b[39;00m a \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_iter_next_step(\n\u001b[1;32m   1333\u001b[0m                 name_to_tool_map,\n\u001b[1;32m   1334\u001b[0m                 color_mapping,\n\u001b[1;32m   1335\u001b[0m                 inputs,\n\u001b[1;32m   1336\u001b[0m                 intermediate_steps,\n\u001b[1;32m   1337\u001b[0m                 run_manager,\n\u001b[1;32m   1338\u001b[0m             )\n\u001b[1;32m   1339\u001b[0m         ]\n\u001b[1;32m   1340\u001b[0m     )\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/agents/agent.py:1415\u001b[0m, in \u001b[0;36mAgentExecutor._iter_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m   1413\u001b[0m     \u001b[38;5;28;01myield\u001b[39;00m agent_action\n\u001b[1;32m   1414\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m agent_action \u001b[38;5;129;01min\u001b[39;00m actions:\n\u001b[0;32m-> 1415\u001b[0m     \u001b[38;5;28;01myield\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_perform_agent_action\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1416\u001b[0m \u001b[43m        \u001b[49m\u001b[43mname_to_tool_map\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcolor_mapping\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43magent_action\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\n\u001b[1;32m   1417\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/agents/agent.py:1437\u001b[0m, in \u001b[0;36mAgentExecutor._perform_agent_action\u001b[0;34m(self, name_to_tool_map, color_mapping, agent_action, run_manager)\u001b[0m\n\u001b[1;32m   1435\u001b[0m         tool_run_kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mllm_prefix\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   1436\u001b[0m     \u001b[38;5;66;03m# We then call the tool on the tool input to get an observation\u001b[39;00m\n\u001b[0;32m-> 1437\u001b[0m     observation \u001b[38;5;241m=\u001b[39m \u001b[43mtool\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1438\u001b[0m \u001b[43m        \u001b[49m\u001b[43magent_action\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtool_input\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1439\u001b[0m \u001b[43m        \u001b[49m\u001b[43mverbose\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mverbose\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1440\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcolor\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcolor\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1441\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_child\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m   1442\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mtool_run_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1443\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1444\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m   1445\u001b[0m     tool_run_kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_action_agent\u001b[38;5;241m.\u001b[39mtool_run_logging_kwargs()\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/tools/base.py:725\u001b[0m, in \u001b[0;36mBaseTool.run\u001b[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, config, tool_call_id, **kwargs)\u001b[0m\n\u001b[1;32m    723\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m error_to_raise:\n\u001b[1;32m    724\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_tool_error(error_to_raise)\n\u001b[0;32m--> 725\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m error_to_raise\n\u001b[1;32m    726\u001b[0m output \u001b[38;5;241m=\u001b[39m _format_output(content, artifact, tool_call_id, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mname, status)\n\u001b[1;32m    727\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_tool_end(output, color\u001b[38;5;241m=\u001b[39mcolor, name\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mname, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/tools/base.py:693\u001b[0m, in \u001b[0;36mBaseTool.run\u001b[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, config, tool_call_id, **kwargs)\u001b[0m\n\u001b[1;32m    691\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m config_param \u001b[38;5;241m:=\u001b[39m _get_runnable_config_param(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_run):\n\u001b[1;32m    692\u001b[0m     tool_kwargs \u001b[38;5;241m=\u001b[39m tool_kwargs \u001b[38;5;241m|\u001b[39m {config_param: config}\n\u001b[0;32m--> 693\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[43mcontext\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_run\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mtool_args\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mtool_kwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    694\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mresponse_format \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcontent_and_artifact\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m    695\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(response, \u001b[38;5;28mtuple\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(response) \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m2\u001b[39m:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/tools/simple.py:94\u001b[0m, in \u001b[0;36mTool._run\u001b[0;34m(self, config, run_manager, *args, **kwargs)\u001b[0m\n\u001b[1;32m     92\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m config_param \u001b[38;5;241m:=\u001b[39m _get_runnable_config_param(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfunc):\n\u001b[1;32m     93\u001b[0m         kwargs[config_param] \u001b[38;5;241m=\u001b[39m config\n\u001b[0;32m---> 94\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     95\u001b[0m msg \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mTool does not support sync invocation.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     96\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mNotImplementedError\u001b[39;00m(msg)\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_community/agent_toolkits/openapi/planner.py:374\u001b[0m, in \u001b[0;36m_create_api_controller_tool.<locals>._create_and_run_api_controller_agent\u001b[0;34m(plan_str)\u001b[0m\n\u001b[1;32m    364\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mendpoint_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m endpoint does not exist.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m    366\u001b[0m agent \u001b[38;5;241m=\u001b[39m _create_api_controller_agent(\n\u001b[1;32m    367\u001b[0m     base_url,\n\u001b[1;32m    368\u001b[0m     docs_str,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    372\u001b[0m     allowed_operations,\n\u001b[1;32m    373\u001b[0m )\n\u001b[0;32m--> 374\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43magent\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\u001b[43mplan_str\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/_api/deprecation.py:182\u001b[0m, in \u001b[0;36mdeprecated.<locals>.deprecate.<locals>.warning_emitting_wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    180\u001b[0m     warned \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m    181\u001b[0m     emit_warning()\n\u001b[0;32m--> 182\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapped\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:606\u001b[0m, in \u001b[0;36mChain.run\u001b[0;34m(self, callbacks, tags, metadata, *args, **kwargs)\u001b[0m\n\u001b[1;32m    604\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(args) \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m    605\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m`run` supports only one positional argument.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 606\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43margs\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtags\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtags\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmetadata\u001b[49m\u001b[43m)\u001b[49m[\n\u001b[1;32m    607\u001b[0m         _output_key\n\u001b[1;32m    608\u001b[0m     ]\n\u001b[1;32m    610\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m kwargs \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m args:\n\u001b[1;32m    611\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m(kwargs, callbacks\u001b[38;5;241m=\u001b[39mcallbacks, tags\u001b[38;5;241m=\u001b[39mtags, metadata\u001b[38;5;241m=\u001b[39mmetadata)[\n\u001b[1;32m    612\u001b[0m         _output_key\n\u001b[1;32m    613\u001b[0m     ]\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/_api/deprecation.py:182\u001b[0m, in \u001b[0;36mdeprecated.<locals>.deprecate.<locals>.warning_emitting_wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    180\u001b[0m     warned \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m    181\u001b[0m     emit_warning()\n\u001b[0;32m--> 182\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapped\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:389\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks, tags, metadata, run_name, include_run_info)\u001b[0m\n\u001b[1;32m    357\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Execute the chain.\u001b[39;00m\n\u001b[1;32m    358\u001b[0m \n\u001b[1;32m    359\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    380\u001b[0m \u001b[38;5;124;03m        `Chain.output_keys`.\u001b[39;00m\n\u001b[1;32m    381\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    382\u001b[0m config \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m    383\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcallbacks\u001b[39m\u001b[38;5;124m\"\u001b[39m: callbacks,\n\u001b[1;32m    384\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtags\u001b[39m\u001b[38;5;124m\"\u001b[39m: tags,\n\u001b[1;32m    385\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmetadata\u001b[39m\u001b[38;5;124m\"\u001b[39m: metadata,\n\u001b[1;32m    386\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_name\u001b[39m\u001b[38;5;124m\"\u001b[39m: run_name,\n\u001b[1;32m    387\u001b[0m }\n\u001b[0;32m--> 389\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    390\u001b[0m \u001b[43m    \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    391\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast\u001b[49m\u001b[43m(\u001b[49m\u001b[43mRunnableConfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m{\u001b[49m\u001b[43mk\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mitems\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mis\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m}\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    392\u001b[0m \u001b[43m    \u001b[49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    393\u001b[0m \u001b[43m    \u001b[49m\u001b[43minclude_run_info\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minclude_run_info\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    394\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:170\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    168\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    169\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n\u001b[0;32m--> 170\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    171\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_end(outputs)\n\u001b[1;32m    173\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m include_run_info:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:160\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    157\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    158\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_inputs(inputs)\n\u001b[1;32m    159\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 160\u001b[0m         \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    161\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m    162\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call(inputs)\n\u001b[1;32m    163\u001b[0m     )\n\u001b[1;32m    165\u001b[0m     final_outputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprep_outputs(\n\u001b[1;32m    166\u001b[0m         inputs, outputs, return_only_outputs\n\u001b[1;32m    167\u001b[0m     )\n\u001b[1;32m    168\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/agents/agent.py:1624\u001b[0m, in \u001b[0;36mAgentExecutor._call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m   1622\u001b[0m \u001b[38;5;66;03m# We now enter the agent loop (until it returns something).\u001b[39;00m\n\u001b[1;32m   1623\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_continue(iterations, time_elapsed):\n\u001b[0;32m-> 1624\u001b[0m     next_step_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_take_next_step\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1625\u001b[0m \u001b[43m        \u001b[49m\u001b[43mname_to_tool_map\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1626\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcolor_mapping\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1627\u001b[0m \u001b[43m        \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1628\u001b[0m \u001b[43m        \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1629\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1630\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1631\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(next_step_output, AgentFinish):\n\u001b[1;32m   1632\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_return(\n\u001b[1;32m   1633\u001b[0m             next_step_output, intermediate_steps, run_manager\u001b[38;5;241m=\u001b[39mrun_manager\n\u001b[1;32m   1634\u001b[0m         )\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/agents/agent.py:1332\u001b[0m, in \u001b[0;36mAgentExecutor._take_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m   1321\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_take_next_step\u001b[39m(\n\u001b[1;32m   1322\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   1323\u001b[0m     name_to_tool_map: Dict[\u001b[38;5;28mstr\u001b[39m, BaseTool],\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1327\u001b[0m     run_manager: Optional[CallbackManagerForChainRun] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   1328\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Union[AgentFinish, List[Tuple[AgentAction, \u001b[38;5;28mstr\u001b[39m]]]:\n\u001b[1;32m   1329\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_consume_next_step(\n\u001b[1;32m   1330\u001b[0m         [\n\u001b[1;32m   1331\u001b[0m             a\n\u001b[0;32m-> 1332\u001b[0m             \u001b[38;5;28;01mfor\u001b[39;00m a \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_iter_next_step(\n\u001b[1;32m   1333\u001b[0m                 name_to_tool_map,\n\u001b[1;32m   1334\u001b[0m                 color_mapping,\n\u001b[1;32m   1335\u001b[0m                 inputs,\n\u001b[1;32m   1336\u001b[0m                 intermediate_steps,\n\u001b[1;32m   1337\u001b[0m                 run_manager,\n\u001b[1;32m   1338\u001b[0m             )\n\u001b[1;32m   1339\u001b[0m         ]\n\u001b[1;32m   1340\u001b[0m     )\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/agents/agent.py:1358\u001b[0m, in \u001b[0;36mAgentExecutor._iter_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m   1355\u001b[0m     intermediate_steps \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_prepare_intermediate_steps(intermediate_steps)\n\u001b[1;32m   1357\u001b[0m     \u001b[38;5;66;03m# Call the LLM to see what to do.\u001b[39;00m\n\u001b[0;32m-> 1358\u001b[0m     output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_action_agent\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mplan\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1359\u001b[0m \u001b[43m        \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1360\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_child\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m   1361\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1362\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1363\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m OutputParserException \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m   1364\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_parsing_errors, \u001b[38;5;28mbool\u001b[39m):\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/agents/agent.py:804\u001b[0m, in \u001b[0;36mAgent.plan\u001b[0;34m(self, intermediate_steps, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m    792\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Given input, decided what to do.\u001b[39;00m\n\u001b[1;32m    793\u001b[0m \n\u001b[1;32m    794\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    801\u001b[0m \u001b[38;5;124;03m    Action specifying what tool to use.\u001b[39;00m\n\u001b[1;32m    802\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    803\u001b[0m full_inputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mget_full_inputs(intermediate_steps, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m--> 804\u001b[0m full_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mllm_chain\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpredict\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mfull_inputs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    805\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_parser\u001b[38;5;241m.\u001b[39mparse(full_output)\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/llm.py:318\u001b[0m, in \u001b[0;36mLLMChain.predict\u001b[0;34m(self, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m    303\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpredict\u001b[39m(\u001b[38;5;28mself\u001b[39m, callbacks: Callbacks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28mstr\u001b[39m:\n\u001b[1;32m    304\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Format prompt with kwargs and pass to LLM.\u001b[39;00m\n\u001b[1;32m    305\u001b[0m \n\u001b[1;32m    306\u001b[0m \u001b[38;5;124;03m    Args:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    316\u001b[0m \u001b[38;5;124;03m            completion = llm.predict(adjective=\"funny\")\u001b[39;00m\n\u001b[1;32m    317\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[0;32m--> 318\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m)\u001b[49m[\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_key]\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/_api/deprecation.py:182\u001b[0m, in \u001b[0;36mdeprecated.<locals>.deprecate.<locals>.warning_emitting_wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    180\u001b[0m     warned \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m    181\u001b[0m     emit_warning()\n\u001b[0;32m--> 182\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mwrapped\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:389\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks, tags, metadata, run_name, include_run_info)\u001b[0m\n\u001b[1;32m    357\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Execute the chain.\u001b[39;00m\n\u001b[1;32m    358\u001b[0m \n\u001b[1;32m    359\u001b[0m \u001b[38;5;124;03mArgs:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    380\u001b[0m \u001b[38;5;124;03m        `Chain.output_keys`.\u001b[39;00m\n\u001b[1;32m    381\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    382\u001b[0m config \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m    383\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcallbacks\u001b[39m\u001b[38;5;124m\"\u001b[39m: callbacks,\n\u001b[1;32m    384\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtags\u001b[39m\u001b[38;5;124m\"\u001b[39m: tags,\n\u001b[1;32m    385\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmetadata\u001b[39m\u001b[38;5;124m\"\u001b[39m: metadata,\n\u001b[1;32m    386\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_name\u001b[39m\u001b[38;5;124m\"\u001b[39m: run_name,\n\u001b[1;32m    387\u001b[0m }\n\u001b[0;32m--> 389\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minvoke\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    390\u001b[0m \u001b[43m    \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    391\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast\u001b[49m\u001b[43m(\u001b[49m\u001b[43mRunnableConfig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m{\u001b[49m\u001b[43mk\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mitems\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mv\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mis\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m}\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    392\u001b[0m \u001b[43m    \u001b[49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_only_outputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    393\u001b[0m \u001b[43m    \u001b[49m\u001b[43minclude_run_info\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minclude_run_info\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    394\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:170\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    168\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    169\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n\u001b[0;32m--> 170\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    171\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_end(outputs)\n\u001b[1;32m    173\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m include_run_info:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/base.py:160\u001b[0m, in \u001b[0;36mChain.invoke\u001b[0;34m(self, input, config, **kwargs)\u001b[0m\n\u001b[1;32m    157\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    158\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_inputs(inputs)\n\u001b[1;32m    159\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 160\u001b[0m         \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    161\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m    162\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call(inputs)\n\u001b[1;32m    163\u001b[0m     )\n\u001b[1;32m    165\u001b[0m     final_outputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprep_outputs(\n\u001b[1;32m    166\u001b[0m         inputs, outputs, return_only_outputs\n\u001b[1;32m    167\u001b[0m     )\n\u001b[1;32m    168\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/llm.py:126\u001b[0m, in \u001b[0;36mLLMChain._call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m    121\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_call\u001b[39m(\n\u001b[1;32m    122\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    123\u001b[0m     inputs: Dict[\u001b[38;5;28mstr\u001b[39m, Any],\n\u001b[1;32m    124\u001b[0m     run_manager: Optional[CallbackManagerForChainRun] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m    125\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Dict[\u001b[38;5;28mstr\u001b[39m, \u001b[38;5;28mstr\u001b[39m]:\n\u001b[0;32m--> 126\u001b[0m     response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[43m[\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    127\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcreate_outputs(response)[\u001b[38;5;241m0\u001b[39m]\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain/chains/llm.py:138\u001b[0m, in \u001b[0;36mLLMChain.generate\u001b[0;34m(self, input_list, run_manager)\u001b[0m\n\u001b[1;32m    136\u001b[0m callbacks \u001b[38;5;241m=\u001b[39m run_manager\u001b[38;5;241m.\u001b[39mget_child() \u001b[38;5;28;01mif\u001b[39;00m run_manager \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    137\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm, BaseLanguageModel):\n\u001b[0;32m--> 138\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mllm\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate_prompt\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    139\u001b[0m \u001b[43m        \u001b[49m\u001b[43mprompts\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    140\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    141\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    142\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mllm_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    143\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    144\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    145\u001b[0m     results \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm\u001b[38;5;241m.\u001b[39mbind(stop\u001b[38;5;241m=\u001b[39mstop, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm_kwargs)\u001b[38;5;241m.\u001b[39mbatch(\n\u001b[1;32m    146\u001b[0m         cast(List, prompts), {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcallbacks\u001b[39m\u001b[38;5;124m\"\u001b[39m: callbacks}\n\u001b[1;32m    147\u001b[0m     )\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py:786\u001b[0m, in \u001b[0;36mBaseChatModel.generate_prompt\u001b[0;34m(self, prompts, stop, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m    778\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mgenerate_prompt\u001b[39m(\n\u001b[1;32m    779\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    780\u001b[0m     prompts: \u001b[38;5;28mlist\u001b[39m[PromptValue],\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    783\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs: Any,\n\u001b[1;32m    784\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m LLMResult:\n\u001b[1;32m    785\u001b[0m     prompt_messages \u001b[38;5;241m=\u001b[39m [p\u001b[38;5;241m.\u001b[39mto_messages() \u001b[38;5;28;01mfor\u001b[39;00m p \u001b[38;5;129;01min\u001b[39;00m prompts]\n\u001b[0;32m--> 786\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[43mprompt_messages\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py:643\u001b[0m, in \u001b[0;36mBaseChatModel.generate\u001b[0;34m(self, messages, stop, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001b[0m\n\u001b[1;32m    641\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m run_managers:\n\u001b[1;32m    642\u001b[0m             run_managers[i]\u001b[38;5;241m.\u001b[39mon_llm_error(e, response\u001b[38;5;241m=\u001b[39mLLMResult(generations\u001b[38;5;241m=\u001b[39m[]))\n\u001b[0;32m--> 643\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    644\u001b[0m flattened_outputs \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m    645\u001b[0m     LLMResult(generations\u001b[38;5;241m=\u001b[39m[res\u001b[38;5;241m.\u001b[39mgenerations], llm_output\u001b[38;5;241m=\u001b[39mres\u001b[38;5;241m.\u001b[39mllm_output)  \u001b[38;5;66;03m# type: ignore[list-item]\u001b[39;00m\n\u001b[1;32m    646\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m res \u001b[38;5;129;01min\u001b[39;00m results\n\u001b[1;32m    647\u001b[0m ]\n\u001b[1;32m    648\u001b[0m llm_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_combine_llm_outputs([res\u001b[38;5;241m.\u001b[39mllm_output \u001b[38;5;28;01mfor\u001b[39;00m res \u001b[38;5;129;01min\u001b[39;00m results])\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py:633\u001b[0m, in \u001b[0;36mBaseChatModel.generate\u001b[0;34m(self, messages, stop, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001b[0m\n\u001b[1;32m    630\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i, m \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(messages):\n\u001b[1;32m    631\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    632\u001b[0m         results\u001b[38;5;241m.\u001b[39mappend(\n\u001b[0;32m--> 633\u001b[0m             \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_generate_with_cache\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    634\u001b[0m \u001b[43m                \u001b[49m\u001b[43mm\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    635\u001b[0m \u001b[43m                \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    636\u001b[0m \u001b[43m                \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_managers\u001b[49m\u001b[43m[\u001b[49m\u001b[43mi\u001b[49m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mrun_managers\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m    637\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    638\u001b[0m \u001b[43m            \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    639\u001b[0m         )\n\u001b[1;32m    640\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    641\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m run_managers:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py:851\u001b[0m, in \u001b[0;36mBaseChatModel._generate_with_cache\u001b[0;34m(self, messages, stop, run_manager, **kwargs)\u001b[0m\n\u001b[1;32m    849\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    850\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m inspect\u001b[38;5;241m.\u001b[39msignature(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_generate)\u001b[38;5;241m.\u001b[39mparameters\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrun_manager\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[0;32m--> 851\u001b[0m         result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_generate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    852\u001b[0m \u001b[43m            \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\n\u001b[1;32m    853\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    854\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    855\u001b[0m         result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_generate(messages, stop\u001b[38;5;241m=\u001b[39mstop, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_openai/chat_models/base.py:717\u001b[0m, in \u001b[0;36mBaseChatOpenAI._generate\u001b[0;34m(self, messages, stop, run_manager, **kwargs)\u001b[0m\n\u001b[1;32m    715\u001b[0m     generation_info \u001b[38;5;241m=\u001b[39m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mheaders\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28mdict\u001b[39m(raw_response\u001b[38;5;241m.\u001b[39mheaders)}\n\u001b[1;32m    716\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 717\u001b[0m     response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mclient\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mpayload\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    718\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_create_chat_result(response, generation_info)\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/_utils/_utils.py:275\u001b[0m, in \u001b[0;36mrequired_args.<locals>.inner.<locals>.wrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    273\u001b[0m             msg \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMissing required argument: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mquote(missing[\u001b[38;5;241m0\u001b[39m])\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    274\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(msg)\n\u001b[0;32m--> 275\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/resources/chat/completions.py:859\u001b[0m, in \u001b[0;36mCompletions.create\u001b[0;34m(self, messages, model, audio, frequency_penalty, function_call, functions, logit_bias, logprobs, max_completion_tokens, max_tokens, metadata, modalities, n, parallel_tool_calls, prediction, presence_penalty, reasoning_effort, response_format, seed, service_tier, stop, store, stream, stream_options, temperature, tool_choice, tools, top_logprobs, top_p, user, extra_headers, extra_query, extra_body, timeout)\u001b[0m\n\u001b[1;32m    817\u001b[0m \u001b[38;5;129m@required_args\u001b[39m([\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmessages\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel\u001b[39m\u001b[38;5;124m\"\u001b[39m], [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmessages\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodel\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstream\u001b[39m\u001b[38;5;124m\"\u001b[39m])\n\u001b[1;32m    818\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcreate\u001b[39m(\n\u001b[1;32m    819\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    856\u001b[0m     timeout: \u001b[38;5;28mfloat\u001b[39m \u001b[38;5;241m|\u001b[39m httpx\u001b[38;5;241m.\u001b[39mTimeout \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m|\u001b[39m NotGiven \u001b[38;5;241m=\u001b[39m NOT_GIVEN,\n\u001b[1;32m    857\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ChatCompletion \u001b[38;5;241m|\u001b[39m Stream[ChatCompletionChunk]:\n\u001b[1;32m    858\u001b[0m     validate_response_format(response_format)\n\u001b[0;32m--> 859\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_post\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    860\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/chat/completions\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m    861\u001b[0m \u001b[43m        \u001b[49m\u001b[43mbody\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmaybe_transform\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    862\u001b[0m \u001b[43m            \u001b[49m\u001b[43m{\u001b[49m\n\u001b[1;32m    863\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmessages\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmessages\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    864\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmodel\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    865\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43maudio\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43maudio\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    866\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfrequency_penalty\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfrequency_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    867\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfunction_call\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunction_call\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    868\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfunctions\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunctions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    869\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mlogit_bias\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogit_bias\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    870\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mlogprobs\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mlogprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    871\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmax_completion_tokens\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_completion_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    872\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmax_tokens\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    873\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmetadata\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmetadata\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    874\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmodalities\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodalities\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    875\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mn\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mn\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    876\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mparallel_tool_calls\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mparallel_tool_calls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    877\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mprediction\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mprediction\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    878\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mpresence_penalty\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mpresence_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    879\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mreasoning_effort\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mreasoning_effort\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    880\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mresponse_format\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mresponse_format\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    881\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mseed\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mseed\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    882\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mservice_tier\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mservice_tier\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    883\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstop\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstop\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    884\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstore\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstore\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    885\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstream\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    886\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mstream_options\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    887\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtemperature\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtemperature\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    888\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtool_choice\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtool_choice\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    889\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtools\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtools\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    890\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtop_logprobs\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_logprobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    891\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtop_p\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mtop_p\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    892\u001b[0m \u001b[43m                \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43muser\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43muser\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    893\u001b[0m \u001b[43m            \u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    894\u001b[0m \u001b[43m            \u001b[49m\u001b[43mcompletion_create_params\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mCompletionCreateParams\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    895\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    896\u001b[0m \u001b[43m        \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmake_request_options\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    897\u001b[0m \u001b[43m            \u001b[49m\u001b[43mextra_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_headers\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_query\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_query\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mextra_body\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_body\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\n\u001b[1;32m    898\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    899\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mChatCompletion\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    900\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m    901\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mStream\u001b[49m\u001b[43m[\u001b[49m\u001b[43mChatCompletionChunk\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    902\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/_base_client.py:1280\u001b[0m, in \u001b[0;36mSyncAPIClient.post\u001b[0;34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1266\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpost\u001b[39m(\n\u001b[1;32m   1267\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   1268\u001b[0m     path: \u001b[38;5;28mstr\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1275\u001b[0m     stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   1276\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ResponseT \u001b[38;5;241m|\u001b[39m _StreamT:\n\u001b[1;32m   1277\u001b[0m     opts \u001b[38;5;241m=\u001b[39m FinalRequestOptions\u001b[38;5;241m.\u001b[39mconstruct(\n\u001b[1;32m   1278\u001b[0m         method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpost\u001b[39m\u001b[38;5;124m\"\u001b[39m, url\u001b[38;5;241m=\u001b[39mpath, json_data\u001b[38;5;241m=\u001b[39mbody, files\u001b[38;5;241m=\u001b[39mto_httpx_files(files), \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39moptions\n\u001b[1;32m   1279\u001b[0m     )\n\u001b[0;32m-> 1280\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m cast(ResponseT, \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mopts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m)\u001b[49m)\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/_base_client.py:957\u001b[0m, in \u001b[0;36mSyncAPIClient.request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m    954\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    955\u001b[0m     retries_taken \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0\u001b[39m\n\u001b[0;32m--> 957\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    958\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    959\u001b[0m \u001b[43m    \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    960\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    961\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    962\u001b[0m \u001b[43m    \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    963\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/_base_client.py:1046\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1044\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m remaining_retries \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_retry(err\u001b[38;5;241m.\u001b[39mresponse):\n\u001b[1;32m   1045\u001b[0m     err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m-> 1046\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_retry_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1047\u001b[0m \u001b[43m        \u001b[49m\u001b[43minput_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1048\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1049\u001b[0m \u001b[43m        \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1050\u001b[0m \u001b[43m        \u001b[49m\u001b[43mresponse_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1051\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1052\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1053\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1055\u001b[0m \u001b[38;5;66;03m# If the response is streamed then we need to explicitly read the response\u001b[39;00m\n\u001b[1;32m   1056\u001b[0m \u001b[38;5;66;03m# to completion before attempting to access the response text.\u001b[39;00m\n\u001b[1;32m   1057\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mis_closed:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/_base_client.py:1095\u001b[0m, in \u001b[0;36mSyncAPIClient._retry_request\u001b[0;34m(self, options, cast_to, retries_taken, response_headers, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1091\u001b[0m \u001b[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001b[39;00m\n\u001b[1;32m   1092\u001b[0m \u001b[38;5;66;03m# different thread if necessary.\u001b[39;00m\n\u001b[1;32m   1093\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(timeout)\n\u001b[0;32m-> 1095\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1096\u001b[0m \u001b[43m    \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1097\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1098\u001b[0m \u001b[43m    \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1099\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1100\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1101\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/_base_client.py:1046\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1044\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m remaining_retries \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_retry(err\u001b[38;5;241m.\u001b[39mresponse):\n\u001b[1;32m   1045\u001b[0m     err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mclose()\n\u001b[0;32m-> 1046\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_retry_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1047\u001b[0m \u001b[43m        \u001b[49m\u001b[43minput_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1048\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1049\u001b[0m \u001b[43m        \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1050\u001b[0m \u001b[43m        \u001b[49m\u001b[43mresponse_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1051\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1052\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1053\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1055\u001b[0m \u001b[38;5;66;03m# If the response is streamed then we need to explicitly read the response\u001b[39;00m\n\u001b[1;32m   1056\u001b[0m \u001b[38;5;66;03m# to completion before attempting to access the response text.\u001b[39;00m\n\u001b[1;32m   1057\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mis_closed:\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/_base_client.py:1095\u001b[0m, in \u001b[0;36mSyncAPIClient._retry_request\u001b[0;34m(self, options, cast_to, retries_taken, response_headers, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1091\u001b[0m \u001b[38;5;66;03m# In a synchronous context we are blocking the entire thread. Up to the library user to run the client in a\u001b[39;00m\n\u001b[1;32m   1092\u001b[0m \u001b[38;5;66;03m# different thread if necessary.\u001b[39;00m\n\u001b[1;32m   1093\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(timeout)\n\u001b[0;32m-> 1095\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1096\u001b[0m \u001b[43m    \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1097\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1098\u001b[0m \u001b[43m    \u001b[49m\u001b[43mretries_taken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mretries_taken\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1099\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1100\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1101\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/openai/_base_client.py:1061\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, retries_taken, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1058\u001b[0m         err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mread()\n\u001b[1;32m   1060\u001b[0m     log\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRe-raising status error\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m-> 1061\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_make_status_error_from_response(err\u001b[38;5;241m.\u001b[39mresponse) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   1063\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_process_response(\n\u001b[1;32m   1064\u001b[0m     cast_to\u001b[38;5;241m=\u001b[39mcast_to,\n\u001b[1;32m   1065\u001b[0m     options\u001b[38;5;241m=\u001b[39moptions,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1069\u001b[0m     retries_taken\u001b[38;5;241m=\u001b[39mretries_taken,\n\u001b[1;32m   1070\u001b[0m )\n",
            "\u001b[0;31mRateLimitError\u001b[0m: Error code: 429 - {'error': {'message': 'Request too large for gpt-4 in organization org-CKrg0v0PHxuOodrFd2y0RurI on tokens per min (TPM): Limit 10000, Requested 16804. The input or output tokens must be reduced in order to run successfully. Visit https://platform.openai.com/account/rate-limits to learn more.', 'type': 'tokens', 'param': None, 'code': 'rate_limit_exceeded'}}"
          ]
        }
      ],
      "source": [
        "user_query = \"give me a song I'd like, make it blues-ey\"\n",
        "spotify_agent.invoke(user_query)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "d5317926",
      "metadata": {
        "id": "d5317926"
      },
      "source": [
        "#### Try another API.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 36,
      "id": "06c3d6a8",
      "metadata": {
        "id": "06c3d6a8"
      },
      "outputs": [],
      "source": [
        "headers = {\"Authorization\": f\"Bearer {os.getenv('OPENAI_API_KEY')}\"}\n",
        "openai_requests_wrapper = RequestsWrapper(headers=headers)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 37,
      "id": "3a9cc939",
      "metadata": {
        "id": "3a9cc939",
        "outputId": "eec13ae7-ce07-4c34-ed10-eb48f342d225"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3mAction: api_planner\n",
            "Action Input: generate a short piece of advice\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3mSorry, this API's domain is data management and machine learning, not generating advice.\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3mThe API doesn't support generating advice. I should inform the user.\n",
            "Final Answer: I'm sorry, but this API's domain is data management and machine learning, not generating advice.\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "data": {
            "text/plain": [
              "{'input': 'generate a short piece of advice',\n",
              " 'output': \"I'm sorry, but this API's domain is data management and machine learning, not generating advice.\"}"
            ]
          },
          "execution_count": 37,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "# Meta!\n",
        "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0.25)\n",
        "openai_agent = planner.create_openapi_agent(\n",
        "    openai_api_spec, openai_requests_wrapper, llm\n",
        ")\n",
        "user_query = \"generate a short piece of advice\"\n",
        "openai_agent.invoke(user_query)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "f32bc6ec",
      "metadata": {
        "id": "f32bc6ec"
      },
      "source": [
        "Takes awhile to get there!"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "461229e4",
      "metadata": {
        "id": "461229e4"
      },
      "source": [
        "## 2nd example: \"json explorer\" agent\n",
        "\n",
        "Here's an agent that's not particularly practical, but neat! The agent has access to 2 toolkits. One comprises tools to interact with json: one tool to list the keys of a json object and another tool to get the value for a given key. The other toolkit comprises `requests` wrappers to send GET and POST requests. This agent consumes a lot calls to the language model, but does a surprisingly decent job.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 30,
      "id": "f8dfa1d3",
      "metadata": {
        "id": "f8dfa1d3"
      },
      "outputs": [],
      "source": [
        "from langchain_community.agent_toolkits import OpenAPIToolkit, create_openapi_agent\n",
        "from langchain_community.tools.json.tool import JsonSpec\n",
        "from langchain_openai import OpenAI"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 31,
      "id": "9ecd1ba0-3937-4359-a41e-68605f0596a1",
      "metadata": {
        "id": "9ecd1ba0-3937-4359-a41e-68605f0596a1",
        "tags": []
      },
      "outputs": [
        {
          "ename": "ValueError",
          "evalue": "You must set allow_dangerous_requests to True to use this tool. Requests can be dangerous and can lead to security vulnerabilities. For example, users can ask a server to make a request to an internal server. It's recommended to use requests through a proxy server and avoid accepting inputs from untrusted sources without proper sandboxing.Please see: https://python.langchain.com/docs/security for further security information.",
          "output_type": "error",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
            "Cell \u001b[0;32mIn[31], line 9\u001b[0m\n\u001b[1;32m      3\u001b[0m json_spec \u001b[38;5;241m=\u001b[39m JsonSpec(dict_\u001b[38;5;241m=\u001b[39mdata, max_value_length\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m4000\u001b[39m)\n\u001b[1;32m      6\u001b[0m openapi_toolkit \u001b[38;5;241m=\u001b[39m OpenAPIToolkit\u001b[38;5;241m.\u001b[39mfrom_llm(\n\u001b[1;32m      7\u001b[0m     OpenAI(temperature\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0\u001b[39m), json_spec, openai_requests_wrapper, verbose\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m      8\u001b[0m )\n\u001b[0;32m----> 9\u001b[0m openapi_agent_executor \u001b[38;5;241m=\u001b[39m \u001b[43mcreate_openapi_agent\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m     10\u001b[0m \u001b[43m    \u001b[49m\u001b[43mllm\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mOpenAI\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtemperature\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     11\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtoolkit\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mopenapi_toolkit\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     12\u001b[0m \u001b[43m    \u001b[49m\u001b[43mallow_dangerous_requests\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mALLOW_DANGEROUS_REQUEST\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     13\u001b[0m \u001b[43m    \u001b[49m\u001b[43mverbose\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m     14\u001b[0m \u001b[43m)\u001b[49m\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_community/agent_toolkits/openapi/base.py:76\u001b[0m, in \u001b[0;36mcreate_openapi_agent\u001b[0;34m(llm, toolkit, callback_manager, prefix, suffix, format_instructions, input_variables, max_iterations, max_execution_time, early_stopping_method, verbose, return_intermediate_steps, agent_executor_kwargs, **kwargs)\u001b[0m\n\u001b[1;32m     73\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mlangchain\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01magents\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmrkl\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mbase\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m ZeroShotAgent\n\u001b[1;32m     74\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mlangchain\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mchains\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mllm\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m LLMChain\n\u001b[0;32m---> 76\u001b[0m tools \u001b[38;5;241m=\u001b[39m \u001b[43mtoolkit\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_tools\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     77\u001b[0m prompt_params \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m     78\u001b[0m     {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mformat_instructions\u001b[39m\u001b[38;5;124m\"\u001b[39m: format_instructions}\n\u001b[1;32m     79\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m format_instructions \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m     80\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m {}\n\u001b[1;32m     81\u001b[0m )\n\u001b[1;32m     82\u001b[0m prompt \u001b[38;5;241m=\u001b[39m ZeroShotAgent\u001b[38;5;241m.\u001b[39mcreate_prompt(\n\u001b[1;32m     83\u001b[0m     tools,\n\u001b[1;32m     84\u001b[0m     prefix\u001b[38;5;241m=\u001b[39mprefix,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     87\u001b[0m     \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mprompt_params,\n\u001b[1;32m     88\u001b[0m )\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_community/agent_toolkits/openapi/toolkit.py:221\u001b[0m, in \u001b[0;36mOpenAPIToolkit.get_tools\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    212\u001b[0m json_agent_tool \u001b[38;5;241m=\u001b[39m Tool(\n\u001b[1;32m    213\u001b[0m     name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mjson_explorer\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m    214\u001b[0m     func\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mjson_agent\u001b[38;5;241m.\u001b[39mrun,\n\u001b[1;32m    215\u001b[0m     description\u001b[38;5;241m=\u001b[39mDESCRIPTION,\n\u001b[1;32m    216\u001b[0m )\n\u001b[1;32m    217\u001b[0m request_toolkit \u001b[38;5;241m=\u001b[39m RequestsToolkit(\n\u001b[1;32m    218\u001b[0m     requests_wrapper\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrequests_wrapper,\n\u001b[1;32m    219\u001b[0m     allow_dangerous_requests\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mallow_dangerous_requests,\n\u001b[1;32m    220\u001b[0m )\n\u001b[0;32m--> 221\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m [\u001b[38;5;241m*\u001b[39m\u001b[43mrequest_toolkit\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_tools\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m, json_agent_tool]\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_community/agent_toolkits/openapi/toolkit.py:169\u001b[0m, in \u001b[0;36mRequestsToolkit.get_tools\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    166\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mget_tools\u001b[39m(\u001b[38;5;28mself\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m List[BaseTool]:\n\u001b[1;32m    167\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Return a list of tools.\"\"\"\u001b[39;00m\n\u001b[1;32m    168\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m [\n\u001b[0;32m--> 169\u001b[0m         \u001b[43mRequestsGetTool\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    170\u001b[0m \u001b[43m            \u001b[49m\u001b[43mrequests_wrapper\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequests_wrapper\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    171\u001b[0m \u001b[43m            \u001b[49m\u001b[43mallow_dangerous_requests\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mallow_dangerous_requests\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    172\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m,\n\u001b[1;32m    173\u001b[0m         RequestsPostTool(\n\u001b[1;32m    174\u001b[0m             requests_wrapper\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrequests_wrapper,\n\u001b[1;32m    175\u001b[0m             allow_dangerous_requests\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mallow_dangerous_requests,\n\u001b[1;32m    176\u001b[0m         ),\n\u001b[1;32m    177\u001b[0m         RequestsPatchTool(\n\u001b[1;32m    178\u001b[0m             requests_wrapper\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrequests_wrapper,\n\u001b[1;32m    179\u001b[0m             allow_dangerous_requests\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mallow_dangerous_requests,\n\u001b[1;32m    180\u001b[0m         ),\n\u001b[1;32m    181\u001b[0m         RequestsPutTool(\n\u001b[1;32m    182\u001b[0m             requests_wrapper\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrequests_wrapper,\n\u001b[1;32m    183\u001b[0m             allow_dangerous_requests\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mallow_dangerous_requests,\n\u001b[1;32m    184\u001b[0m         ),\n\u001b[1;32m    185\u001b[0m         RequestsDeleteTool(\n\u001b[1;32m    186\u001b[0m             requests_wrapper\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrequests_wrapper,\n\u001b[1;32m    187\u001b[0m             allow_dangerous_requests\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mallow_dangerous_requests,\n\u001b[1;32m    188\u001b[0m         ),\n\u001b[1;32m    189\u001b[0m     ]\n",
            "File \u001b[0;32m~/gen-ai/langchain/venv/lib/python3.12/site-packages/langchain_community/tools/requests/tool.py:37\u001b[0m, in \u001b[0;36mBaseRequestsTool.__init__\u001b[0;34m(self, **kwargs)\u001b[0m\n\u001b[1;32m     35\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Initialize the tool.\"\"\"\u001b[39;00m\n\u001b[1;32m     36\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m kwargs\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mallow_dangerous_requests\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mFalse\u001b[39;00m):\n\u001b[0;32m---> 37\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m     38\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mYou must set allow_dangerous_requests to True to use this tool. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     39\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRequests can be dangerous and can lead to security vulnerabilities. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     40\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFor example, users can ask a server to make a request to an internal \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     41\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mserver. It\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124ms recommended to use requests through a proxy server \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     42\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mand avoid accepting inputs from untrusted sources without proper \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     43\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msandboxing.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     44\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPlease see: https://python.langchain.com/docs/security for \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     45\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfurther security information.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m     46\u001b[0m     )\n\u001b[1;32m     47\u001b[0m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__init__\u001b[39m(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
            "\u001b[0;31mValueError\u001b[0m: You must set allow_dangerous_requests to True to use this tool. Requests can be dangerous and can lead to security vulnerabilities. For example, users can ask a server to make a request to an internal server. It's recommended to use requests through a proxy server and avoid accepting inputs from untrusted sources without proper sandboxing.Please see: https://python.langchain.com/docs/security for further security information."
          ]
        }
      ],
      "source": [
        "with open(\"openai_openapi.yaml\") as f:\n",
        "    data = yaml.load(f, Loader=yaml.FullLoader)\n",
        "json_spec = JsonSpec(dict_=data, max_value_length=4000)\n",
        "\n",
        "\n",
        "openapi_toolkit = OpenAPIToolkit.from_llm(\n",
        "    OpenAI(temperature=0), json_spec, openai_requests_wrapper, verbose=True\n",
        ")\n",
        "openapi_agent_executor = create_openapi_agent(\n",
        "    llm=OpenAI(temperature=0),\n",
        "    toolkit=openapi_toolkit,\n",
        "    allow_dangerous_requests=ALLOW_DANGEROUS_REQUEST,\n",
        "    verbose=True,\n",
        ")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "548db7f7-337b-4ba8-905c-e7fd58c01799",
      "metadata": {
        "id": "548db7f7-337b-4ba8-905c-e7fd58c01799",
        "outputId": "8d0fc2cb-3662-43b5-f9cd-6f66e99ee03a",
        "tags": []
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3mAction: json_explorer\n",
            "Action Input: What is the base url for the API?\u001b[0m\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
            "Action Input: data\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I should look at the servers key to see what the base url is\n",
            "Action: json_spec_list_keys\n",
            "Action Input: data[\"servers\"][0]\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3mValueError('Value at path `data[\"servers\"][0]` is not a dict, get the value directly.')\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I should get the value of the servers key\n",
            "Action: json_spec_get_value\n",
            "Action Input: data[\"servers\"][0]\u001b[0m\n",
            "Observation: \u001b[33;1m\u001b[1;3m{'url': 'https://api.openai.com/v1'}\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I now know the base url for the API\n",
            "Final Answer: The base url for the API is https://api.openai.com/v1\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n",
            "\n",
            "Observation: \u001b[33;1m\u001b[1;3mThe base url for the API is https://api.openai.com/v1\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I should find the path for the /completions endpoint.\n",
            "Action: json_explorer\n",
            "Action Input: What is the path for the /completions endpoint?\u001b[0m\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
            "Action Input: data\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I should look at the paths key to see what endpoints exist\n",
            "Action: json_spec_list_keys\n",
            "Action Input: data[\"paths\"]\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m['/engines', '/engines/{engine_id}', '/completions', '/chat/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/audio/transcriptions', '/audio/translations', '/engines/{engine_id}/search', '/files', '/files/{file_id}', '/files/{file_id}/content', '/answers', '/classifications', '/fine-tunes', '/fine-tunes/{fine_tune_id}', '/fine-tunes/{fine_tune_id}/cancel', '/fine-tunes/{fine_tune_id}/events', '/models', '/models/{model}', '/moderations']\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I now know the path for the /completions endpoint\n",
            "Final Answer: The path for the /completions endpoint is data[\"paths\"][2]\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n",
            "\n",
            "Observation: \u001b[33;1m\u001b[1;3mThe path for the /completions endpoint is data[\"paths\"][2]\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I should find the required parameters for the POST request.\n",
            "Action: json_explorer\n",
            "Action Input: What are the required parameters for a POST request to the /completions endpoint?\u001b[0m\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
            "Action Input: data\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I should look at the paths key to see what endpoints exist\n",
            "Action: json_spec_list_keys\n",
            "Action Input: data[\"paths\"]\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m['/engines', '/engines/{engine_id}', '/completions', '/chat/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/audio/transcriptions', '/audio/translations', '/engines/{engine_id}/search', '/files', '/files/{file_id}', '/files/{file_id}/content', '/answers', '/classifications', '/fine-tunes', '/fine-tunes/{fine_tune_id}', '/fine-tunes/{fine_tune_id}/cancel', '/fine-tunes/{fine_tune_id}/events', '/models', '/models/{model}', '/moderations']\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I should look at the /completions endpoint to see what parameters are required\n",
            "Action: json_spec_list_keys\n",
            "Action Input: data[\"paths\"][\"/completions\"]\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m['post']\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I should look at the post key to see what parameters are required\n",
            "Action: json_spec_list_keys\n",
            "Action Input: data[\"paths\"][\"/completions\"][\"post\"]\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m['operationId', 'tags', 'summary', 'requestBody', 'responses', 'x-oaiMeta']\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I should look at the requestBody key to see what parameters are required\n",
            "Action: json_spec_list_keys\n",
            "Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"]\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m['required', 'content']\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I should look at the content key to see what parameters are required\n",
            "Action: json_spec_list_keys\n",
            "Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"]\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m['application/json']\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I should look at the application/json key to see what parameters are required\n",
            "Action: json_spec_list_keys\n",
            "Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"]\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m['schema']\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I should look at the schema key to see what parameters are required\n",
            "Action: json_spec_list_keys\n",
            "Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"]\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m['$ref']\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I should look at the $ref key to see what parameters are required\n",
            "Action: json_spec_list_keys\n",
            "Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3mValueError('Value at path `data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]` is not a dict, get the value directly.')\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I should look at the $ref key to get the value directly\n",
            "Action: json_spec_get_value\n",
            "Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]\u001b[0m\n",
            "Observation: \u001b[33;1m\u001b[1;3m#/components/schemas/CreateCompletionRequest\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I should look at the CreateCompletionRequest schema to see what parameters are required\n",
            "Action: json_spec_list_keys\n",
            "Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"]\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m['type', 'properties', 'required']\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I should look at the required key to see what parameters are required\n",
            "Action: json_spec_get_value\n",
            "Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"][\"required\"]\u001b[0m\n",
            "Observation: \u001b[33;1m\u001b[1;3m['model']\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
            "Final Answer: The required parameters for a POST request to the /completions endpoint are 'model'.\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n",
            "\n",
            "Observation: \u001b[33;1m\u001b[1;3mThe required parameters for a POST request to the /completions endpoint are 'model'.\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I now know the parameters needed to make the request.\n",
            "Action: requests_post\n",
            "Action Input: { \"url\": \"https://api.openai.com/v1/completions\", \"data\": { \"model\": \"davinci\", \"prompt\": \"tell me a joke\" } }\u001b[0m\n",
            "Observation: \u001b[33;1m\u001b[1;3m{\"id\":\"cmpl-70Ivzip3dazrIXU8DSVJGzFJj2rdv\",\"object\":\"text_completion\",\"created\":1680307139,\"model\":\"davinci\",\"choices\":[{\"text\":\" with mummy not there”\\n\\nYou dig deep and come up with,\",\"index\":0,\"logprobs\":null,\"finish_reason\":\"length\"}],\"usage\":{\"prompt_tokens\":4,\"completion_tokens\":16,\"total_tokens\":20}}\n",
            "\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
            "Final Answer: The response of the POST request is {\"id\":\"cmpl-70Ivzip3dazrIXU8DSVJGzFJj2rdv\",\"object\":\"text_completion\",\"created\":1680307139,\"model\":\"davinci\",\"choices\":[{\"text\":\" with mummy not there”\\n\\nYou dig deep and come up with,\",\"index\":0,\"logprobs\":null,\"finish_reason\":\"length\"}],\"usage\":{\"prompt_tokens\":4,\"completion_tokens\":16,\"total_tokens\":20}}\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "data": {
            "text/plain": [
              "'The response of the POST request is {\"id\":\"cmpl-70Ivzip3dazrIXU8DSVJGzFJj2rdv\",\"object\":\"text_completion\",\"created\":1680307139,\"model\":\"davinci\",\"choices\":[{\"text\":\" with mummy not there”\\\\n\\\\nYou dig deep and come up with,\",\"index\":0,\"logprobs\":null,\"finish_reason\":\"length\"}],\"usage\":{\"prompt_tokens\":4,\"completion_tokens\":16,\"total_tokens\":20}}'"
            ]
          },
          "execution_count": 33,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "openapi_agent_executor.run(\n",
        "    \"Make a post request to openai /completions. The prompt should be 'tell me a joke.'\"\n",
        ")"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.12.3"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}