feat: added experimental support to tool function loading for agents …

…and refactored prompt loading accordingly
MoritzLaurer · Nov 27, 2024 · d9383a3 · d9383a3
1 parent 87a509e
commit d9383a3
Show file tree

Hide file tree

Showing 19 changed files with 1,718 additions and 724 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -20,6 +20,8 @@ repos:
     rev: v1.13.0
     hooks:
     -   id: mypy
-        additional_dependencies: [types-PyYAML==6.0.12.20240917]
+        additional_dependencies: 
+            - types-PyYAML==6.0.12.20240917
+            - types-setuptools
         args: ["--config-file=pyproject.toml"]
         exclude: ^tests/
diff --git a/docs/index.md b/docs/index.md
@@ -30,8 +30,8 @@ pip install hf-hub-prompts
 ['code_teacher.yaml', 'translate.yaml']
 
 >>> # 2. Download a prompt template:
->>> from hf_hub_prompts import download_prompt_template
->>> prompt_template = download_prompt_template(
+>>> from hf_hub_prompts import PromptTemplateLoader
+>>> prompt_template = PromptTemplateLoader.from_hub(
 ...     repo_id="MoritzLaurer/example_prompts",
 ...     filename="code_teacher.yaml"
 ... )

diff --git a/docs/reference/hub_api.md b/docs/reference/hub_api.md
@@ -1,6 +1,9 @@
-# Downloading prompts
+# Downloading prompts and tools
 
-This section documents the functions for downloading and listing prompt templates from the Hugging Face Hub.
+This section documents the classes and functions for downloading prompt templates and tools from the Hugging Face Hub.
+
+!!! note
+    Note that the ToolLoader class and related functionalities for working with tools is still highly experimental.
 
 ::: hf_hub_prompts.hub_api
     options:

diff --git a/docs/reference/tools.md b/docs/reference/tools.md
@@ -0,0 +1,10 @@
+# Tools
+
+This section documents the Tool class.
+
+!!! note
+    This class is still in an early experimental stage.
+
+::: hf_hub_prompts.tools
+    options:
+        show_if_no_docstring: false
diff --git a/docs/repo_types_examples.md b/docs/repo_types_examples.md
@@ -32,11 +32,12 @@ list_prompt_templates(repo_id="MoritzLaurer/closed_system_prompts")
 Here, we download the leaked prompt for Claude-3.5 Sonnet for creating Artifacts. 
 
 ```python
-from hf_hub_prompts import download_prompt_template
-prompt_template = download_prompt_template(
+from hf_hub_prompts import PromptTemplateLoader
+prompt_template = PromptTemplateLoader.from_hub(
     repo_id="MoritzLaurer/closed_system_prompts",
     filename="claude-3-5-artifacts-leak-210624.yaml"
 )
+
 print(prompt_template)
 # ChatPromptTemplate(messages=[{'role': 'system', 'content': '<artifacts_info> The assistant can create and reference artifacts during conversations. Artifacts are ... Claude is now being connected with a human.'}, {'role': 'user', 'content': '{user_message}'}], input_variables=['current_date', 'user_message'], metadata=[{'source': 'https://gist.github.com/dedlim/6bf6d81f77c19e20cd40594aa09e3ecd'}])
 ```
@@ -82,9 +83,12 @@ response = client_anthropic.messages.create(
 The paper "JudgeBench: A Benchmark for Evaluating LLM-Based Judges" (<a href="https://arxiv.org/pdf/2410.12784">paper</a>) collects several prompts for using LLMs to evaluate unstructured LLM outputs. After copying them into a <a href="https://huggingface.co/MoritzLaurer/judgebench-prompts">HF Hub model repo</a> in the standardized YAML format, they can be directly loaded and populated.
 
 ```python
-from hf_hub_prompts import download_prompt_template
+from hf_hub_prompts import PromptTemplateLoader
+prompt_template = PromptTemplateLoader.from_hub(
+  repo_id="MoritzLaurer/judgebench-prompts", 
+  filename="vanilla-prompt.yaml"
+)
 
-prompt_template = download_prompt_template(repo_id="MoritzLaurer/judgebench-prompts", filename="vanilla-prompt.yaml")
 ```
 </details>
 
@@ -95,11 +99,14 @@ The community has extracted system prompts from closed API providers like OpenAI
 
 
 ```python
-from hf_hub_prompts import list_prompt_templates, download_prompt_template
+from hf_hub_prompts import list_prompt_templates, PromptTemplateLoader
 list_prompt_templates(repo_id="MoritzLaurer/closed_system_prompts")
 # out: ['claude-3-5-artifacts-leak-210624.yaml', 'claude-3-5-sonnet-text-090924.yaml', 'claude-3-5-sonnet-text-image-090924.yaml', 'jokes-prompt.yaml', 'openai-metaprompt-audio.yaml', 'openai-metaprompt-text.yaml']
 
-prompt_template = download_prompt_template(repo_id="MoritzLaurer/closed_system_prompts", filename="openai-metaprompt-text.yaml")
+prompt_template = PromptTemplateLoader.from_hub(
+  repo_id="MoritzLaurer/closed_system_prompts", 
+  filename="openai-metaprompt-text.yaml"
+)
 ```
 </details>
 
@@ -118,10 +125,12 @@ These prompts are currently either mentioned unsystematically in model cards or
   <summary>1. Example: Sharing the <a href="https://huggingface.co/MoritzLaurer/open_models_special_prompts">InternVL2 special task prompts</a></summary>
 
 ```python
-from hf_hub_prompts import download_prompt_template
-
 # download image prompt template
-prompt_template = download_prompt_template(repo_id="MoritzLaurer/open_models_special_prompts", filename="internvl2-bbox-prompt.yaml")
+from hf_hub_prompts import PromptTemplateLoader
+prompt_template = PromptTemplateLoader.from_hub(
+  repo_id="MoritzLaurer/open_models_special_prompts", 
+  filename="internvl2-bbox-prompt.yaml"
+)
 
 # populate prompt
 image_url = "https://unsplash.com/photos/ZVw3HmHRhv0/download?ixid=M3wxMjA3fDB8MXxhbGx8NHx8fHx8fDJ8fDE3MjQ1NjAzNjl8&force=true&w=1920"
@@ -183,11 +192,15 @@ See this <a href="https://huggingface.co/datasets/MoritzLaurer/dataset_prompts">
 
 
 ```python
-from hf_hub_prompts import download_prompt_template
+from hf_hub_prompts import PromptTemplateLoader
 import torch
 from transformers import pipeline
 
-prompt_template = download_prompt_template(repo_id="MoritzLaurer/dataset_prompts", filename="fineweb-edu-prompt.yaml", repo_type="dataset")
+prompt_template = PromptTemplateLoader.from_hub(
+  repo_id="MoritzLaurer/dataset_prompts", 
+  filename="fineweb-edu-prompt.yaml", 
+  repo_type="dataset"
+)
 
 # populate the prompt
 text_to_score = "The quick brown fox jumps over the lazy dog"
@@ -229,7 +242,7 @@ The prompts could be directly added to the dataset repository in the standardize
 
 ## 4. Attaching prompts to HF Spaces
 
-See also the [Agents](agents.md) and [Tools](tools.md) page for using HF Spaces for hosting prompts and tools as part of agents.
+See also the [Agents](agents.md) and [Tools](standard_tool_format.md) page for using HF Spaces for hosting prompts and tools as part of agents.
 
 [TODO: create example]
 

diff --git a/docs/standard_prompt_format.md b/docs/standard_prompt_format.md
@@ -75,6 +75,6 @@ prompt_template_langchain = prompt_template.to_langchain_template()
 - [LangGraph Templates](https://blog.langchain.dev/launching-langgraph-templates/) (underlying data structure unclear, does not seem to have a collaborative way of sharing templates)
 - [LlamaHub](https://llamahub.ai/) (seems to use GitHub as backend)
 - [Deepset Prompt Hub](https://github.com/deepset-ai/prompthub) (seems not maintained anymore, used YAML with {...} for input variables)
-- distilabel [templates](https://github.com/argilla-io/distilabel/tree/main/src/distilabel/steps/tasks/templates) and [tasks](https://distilabel.argilla.io/latest/components-gallery/tasks/) (using pure jinja2 with {{ ... }} for input variables)
+- distilabel [templates](https://github.com/argilla-io/distilabel/tree/main/src/distilabel/steps/tasks/templates) and [tasks](https://distilabel.argilla.io/latest/components-gallery/tasks/) ([source](https://github.com/argilla-io/distilabel/tree/main/src/distilabel/steps/tasks)) (using pure jinja2 with {{ ... }} for input variables)
 - [Langfuse](https://langfuse.com/docs/prompts/get-started), see also [example here](https://langfuse.com/guides/cookbook/prompt_management_langchain) (no public prompt repo, using JSON internally with {{...}} for input variables)
 - [Promptify](https://github.com/promptslab/Promptify/tree/27a53fa8e8f2a4d90f887d06ece65a44466f873a/promptify/prompts) (not maintained anymore, used jinja1 and {{ ... }} for input variables)
diff --git a/docs/tools.md → docs/standard_tool_format.md b/docs/tools.md → docs/standard_tool_format.md
diff --git a/examples/example-usage.ipynb b/examples/example-usage.ipynb
@@ -5,7 +5,10 @@
    "id": "43c0e4d4-b25d-48a9-ba4c-7b412c641677",
    "metadata": {},
    "source": [
-    "# Testing approaches to prompt sharing/downloading on the HF Hub"
+    "# Testing approaches to prompt sharing/downloading on the HF Hub\n",
+    "\n",
+    "> [!WARNING]  \n",
+    "> This notebook is not maintained or tested and contains outdated code. I'm just using it for quick testing of code."
    ]
   },
   {
@@ -47,17 +50,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "id": "947ac23c",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<module 'hf_hub_prompts.prompt_templates' from '/Users/moritzlaurer/huggingface/projects/hf-hub-prompts/hf_hub_prompts/prompt_templates.py'>"
+       "<module 'hf_hub_prompts.tools' from '/Users/moritzlaurer/huggingface/projects/hf-hub-prompts/hf_hub_prompts/tools.py'>"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 1,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -69,7 +72,98 @@
     "\n",
     "# Reload the specific module\n",
     "importlib.reload(hf_hub_prompts.hub_api)\n",
-    "importlib.reload(hf_hub_prompts.prompt_templates)"
+    "importlib.reload(hf_hub_prompts.prompt_templates)\n",
+    "importlib.reload(hf_hub_prompts.tools)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "509335ed",
+   "metadata": {},
+   "source": [
+    "### Example tool use"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "37f739bd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "os.chdir(\"/Users/moritzlaurer/huggingface/projects/hf-hub-prompts\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "ab33eeae",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Tool class: {'func': <function get_stock_price at 0x108a09300>, 'name': 'get_stock_price', 'description': 'Retrieve stock price data for a given ticker symbol.', 'args_description': {'ticker': \"The stock ticker symbol (e.g., 'AAPL' for Apple Inc.)\", 'days': 'Number of days of historical data to fetch (default: 1d).'}, 'return_description': \"Dict[str, Union[float, str, list, datetime]]: Dictionary containing: - prices (list): List of closing prices for requested days - currency (str): The currency of the price (e.g., 'USD') - timestamps (list): List of timestamps for each price\", 'raises_description': {'ValueError': 'If days parameter is not one of the allowed values'}, 'metadata': {'version': '0.0.1', 'author': 'John Doe', 'requires_gpu': 'False', 'requires_api_key': 'False'}, 'dependencies': {'yfinance'}}\n",
+      "OpenAI function: {'name': 'get_stock_price', 'description': 'Retrieve stock price data for a given ticker symbol.', 'parameters': {'type': 'object', 'properties': {'ticker': {'type': 'string', 'description': \"The stock ticker symbol (e.g., 'AAPL' for Apple Inc.)\"}, 'days': {'type': 'string', 'description': 'Number of days of historical data to fetch (default: 1d).'}}, 'required': ['ticker']}}\n",
+      "Result: {'prices': [228.52000427246094, 229.8699951171875, 232.8699951171875, 235.05999755859375, 234.9499969482422], 'currency': 'USD', 'timestamps': [datetime.datetime(2024, 11, 21, 0, 0, tzinfo=<DstTzInfo 'America/New_York' EST-1 day, 19:00:00 STD>), datetime.datetime(2024, 11, 22, 0, 0, tzinfo=<DstTzInfo 'America/New_York' EST-1 day, 19:00:00 STD>), datetime.datetime(2024, 11, 25, 0, 0, tzinfo=<DstTzInfo 'America/New_York' EST-1 day, 19:00:00 STD>), datetime.datetime(2024, 11, 26, 0, 0, tzinfo=<DstTzInfo 'America/New_York' EST-1 day, 19:00:00 STD>), datetime.datetime(2024, 11, 27, 0, 0, tzinfo=<DstTzInfo 'America/New_York' EST-1 day, 19:00:00 STD>)]}\n",
+      "Tool class: {'func': <function get_stock_price at 0x10b9edda0>, 'name': 'get_stock_price', 'description': 'Retrieve stock price data for a given ticker symbol.', 'args_description': {'ticker': \"The stock ticker symbol (e.g., 'AAPL' for Apple Inc.)\", 'days': 'Number of days of historical data to fetch (default: 1d).'}, 'return_description': \"Dict[str, Union[float, str, list, datetime]]: Dictionary containing: - prices (list): List of closing prices for requested days - currency (str): The currency of the price (e.g., 'USD') - timestamps (list): List of timestamps for each price\", 'raises_description': {'ValueError': 'If days parameter is not one of the allowed values'}, 'metadata': {'version': '0.0.1', 'author': 'John Doe', 'requires_gpu': 'False', 'requires_api_key': 'False'}, 'dependencies': {'yfinance'}}\n",
+      "OpenAI function: {'name': 'get_stock_price', 'description': 'Retrieve stock price data for a given ticker symbol.', 'parameters': {'type': 'object', 'properties': {'ticker': {'type': 'string', 'description': \"The stock ticker symbol (e.g., 'AAPL' for Apple Inc.)\"}, 'days': {'type': 'string', 'description': 'Number of days of historical data to fetch (default: 1d).'}}, 'required': ['ticker']}}\n",
+      "Result: {'prices': [228.52000427246094, 229.8699951171875, 232.8699951171875, 235.05999755859375, 234.9499969482422], 'currency': 'USD', 'timestamps': [datetime.datetime(2024, 11, 21, 0, 0, tzinfo=<DstTzInfo 'America/New_York' EST-1 day, 19:00:00 STD>), datetime.datetime(2024, 11, 22, 0, 0, tzinfo=<DstTzInfo 'America/New_York' EST-1 day, 19:00:00 STD>), datetime.datetime(2024, 11, 25, 0, 0, tzinfo=<DstTzInfo 'America/New_York' EST-1 day, 19:00:00 STD>), datetime.datetime(2024, 11, 26, 0, 0, tzinfo=<DstTzInfo 'America/New_York' EST-1 day, 19:00:00 STD>), datetime.datetime(2024, 11, 27, 0, 0, tzinfo=<DstTzInfo 'America/New_York' EST-1 day, 19:00:00 STD>)]}\n"
+     ]
+    }
+   ],
+   "source": [
+    "from hf_hub_prompts import ToolLoader\n",
+    "\n",
+    "tool = ToolLoader.from_local(\"./tests/test_data/get_stock_price.py\")\n",
+    "#print(\"Tool class:\", tool.__dict__)\n",
+    "#print(\"OpenAI function:\", tool.to_openai_function())\n",
+    "result = tool(ticker=\"AAPL\", days=\"5d\")\n",
+    "print(\"Result:\", result)\n",
+    "\n",
+    "tool = ToolLoader.from_hub(repo_id=\"MoritzLaurer/example_tools\", filename=\"get_stock_price.py\")\n",
+    "#print(\"Tool class:\", tool.__dict__)\n",
+    "#print(\"OpenAI function:\", tool.to_openai_function())\n",
+    "result = tool(ticker=\"AAPL\", days=\"5d\")\n",
+    "print(\"Result:\", result)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "307d7efb",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "AttributeError",
+     "evalue": "module 'hf_hub_prompts' has no attribute 'load_tool'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[4], line 4\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mhf_hub_prompts\u001b[39;00m\n\u001b[1;32m      2\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mos\u001b[39;00m\n\u001b[0;32m----> 4\u001b[0m tool \u001b[38;5;241m=\u001b[39m \u001b[43mhf_hub_prompts\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload_tool\u001b[49m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m./tests/test_data/get_stock_price.py\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m      6\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mUninstalled dependencies:\u001b[39m\u001b[38;5;124m\"\u001b[39m, tool\u001b[38;5;241m.\u001b[39mreturn_uninstalled_dependencies())\n\u001b[1;32m      8\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mTool class:\u001b[39m\u001b[38;5;124m\"\u001b[39m, tool\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__dict__\u001b[39m)\n",
+      "\u001b[0;31mAttributeError\u001b[0m: module 'hf_hub_prompts' has no attribute 'load_tool'"
+     ]
+    }
+   ],
+   "source": [
+    "import hf_hub_prompts\n",
+    "import os\n",
+    "\n",
+    "tool = hf_hub_prompts.load_tool(\"./tests/test_data/get_stock_price.py\")\n",
+    "\n",
+    "print(\"Uninstalled dependencies:\", tool.return_uninstalled_dependencies())\n",
+    "\n",
+    "print(\"Tool class:\", tool.__dict__)\n",
+    "\n",
+    "print(\"OpenAI function:\", tool.to_openai_function())\n",
+    "\n",
+    "result = tool(ticker=\"AAPL\", days=\"5d\")\n",
+    "\n",
+    "print(\"Result:\", result)\n"
    ]
   },
   {

diff --git a/hf_hub_prompts/__init__.py b/hf_hub_prompts/__init__.py
@@ -1,13 +1,17 @@
-from .hub_api import download_prompt_template, list_prompt_templates
+from .hub_api import PromptTemplateLoader, ToolLoader, list_prompt_templates, list_tools
 from .populated_prompt import PopulatedPrompt
 from .prompt_templates import BasePromptTemplate, ChatPromptTemplate, TextPromptTemplate
+from .tools import Tool
 
 
 __all__ = [
+    "PromptTemplateLoader",
+    "list_prompt_templates",
+    "BasePromptTemplate",
     "TextPromptTemplate",
     "ChatPromptTemplate",
-    "BasePromptTemplate",
     "PopulatedPrompt",
-    "download_prompt_template",
-    "list_prompt_templates",
+    "ToolLoader",
+    "list_tools",
+    "Tool",
 ]