Update .env and README.md files

.env

@@ -1,6 +1,7 @@
 THREADS=4
 ADDRESS=0.0.0.0:8085
 GALLERIES=[{"name":"model-gallery", "url":"github:go-skynet/model-gallery/index.yaml"}, {"url": "github:go-skynet/model-gallery/huggingface.yaml","name":"huggingface"}]
-DEBUG=true
+DEBUG=false
 MODELS_PATH=/models
-# BUILD_TYPE=openblas
+#BUILD_TYPE=openblas
+#REBUILD=true

README.md

@@ -1,23 +1,32 @@
-# Use AI models in terminal locally, free and without a connection.
+# Use AI models in terminal locally, free and without a connection
 
 ![Usage](cli_ai.gif)
 
 ## Table of contents
 
-- [Use AI models in terminal locally, free and without a connection.](#use-ai-models-in-terminal-locally-free-and-without-a-connection)
+- [Use AI models in terminal locally, free and without a connection](#use-ai-models-in-terminal-locally-free-and-without-a-connection)
   - [Table of contents](#table-of-contents)
   - [What is this?](#what-is-this)
   - [Requirements](#requirements)
-  - [In your terminal](#in-your-terminal)
-    - [Install](#install)
-      - [Install zsh\_local\_ai plugin](#install-zsh_local_ai-plugin)
-      - [Using oh-my-zsh edit ~/.zshrc](#using-oh-my-zsh-edit-zshrc)
-      - [Reload zsh](#reload-zsh)
-      - [Run local api in docker](#run-local-api-in-docker)
-      - [Fetch the models](#fetch-the-models)
+  - [Installation](#installation)
+    - [Run local api in docker](#run-local-api-in-docker)
+    - [Fetch the models](#fetch-the-models)
     - [Restart the api](#restart-the-api)
     - [Make your first request](#make-your-first-request)
   - [Usage](#usage)
+    - [In your terminal](#in-your-terminal)
+      - [Terminal Requirements](#terminal-requirements)
+      - [Install zsh\_local\_ai plugin](#install-zsh_local_ai-plugin)
+      - [Using oh-my-zsh edit ~/.zshrc](#using-oh-my-zsh-edit-zshrc)
+      - [Reload zsh](#reload-zsh)
+    - [In VS Code](#in-vs-code)
+      - [VS Code Requirements](#vs-code-requirements)
+      - [Install Vscode and Continue Plugin](#install-vscode-and-continue-plugin)
+      - [Configure extension](#configure-extension)
+    - [In your notes or markdown files](#in-your-notes-or-markdown-files)
+      - [Notes Requirements](#notes-requirements)
+      - [Install obsidian and text generator plugin](#install-obsidian-and-text-generator-plugin)
+      - [Setup text generator](#setup-text-generator)
   - [License](#license)
 
 ## What is this?
@@ -29,14 +38,51 @@ This is a simple api that runs locally and can be used to run ai models locally
 - Docker
 - Docker-compose
 - Make
+
+## Installation
+
+### Run local api in docker
+
+Wont demonize the process, so you can see the logs (Also debug mode is on)
+
+```bash
+make start
+```
+
+### Fetch the models
+
+This will take a while to download the models for the first time. Wait until this is done before making a request.
+
+```bash
+make get_models
+```
+
+### Restart the api
+
+Give it a few seconds to stop the container and start it again.
+
+```bash
+make restart
+```
+
+### Make your first request
+
+That will take a while to load the model for the first time
+
+```bash
+make test
+```
+
+## Usage
+
+### In your terminal
+
+#### Terminal Requirements
+
 - Zsh
 - Oh-my-zsh
 - Python3
 
-## In your terminal
-
-### Install
-
 #### Install zsh_local_ai plugin
 
 ```bash
@@ -61,43 +107,84 @@ bindkey '^X' create_completion
 source ~/.zshrc
 ```
 
-#### Run local api in docker
+Start typing the command or a comment and press ctrl+x to get the completion. Then press enter to run the command.
 
-Wont demonize the process, so you can see the logs (Also debug mode is on)
+### In VS Code
 
-```bash
-make start
-```
+#### VS Code Requirements
 
-#### Fetch the models
+- VS Code
+- Continue - Claude, CodeLlama, GPT-4, and more extension
 
-This will take a while to download the models for the first time. Wait until this is done before making a request.
+#### Install Vscode and Continue Plugin
 
-```bash
-make get_models
-```
+Download and install VSCode, then from the extensions search and install the Continue plugin.
 
-### Restart the api
+#### Configure extension
 
-Give it a few seconds to stop the container and start it again.
+- At you vscode Toolbar click on the new Continue icon, then click on the gear icon at the bottom right to open the settings.
 
-```bash
-make restart
+- In the models array add the following first
+```
+{
+  "title": "Monday AI",
+  "provider": "openai",
+  "model": "gpt4all-j",
+  "apiBase": "http://localhost:8085/v1/"
+},
 ```
 
-### Make your first request
+- Replace the "tabAutocompleteModel" Object with the following
 
-That will take a while to load the model for the first time
+```
+  "tabAutocompleteModel": {
+    "title": "Tab Autocomplete Model",
+    "provider": "openai",
+    "model": "gpt4all-j",
+    "apiBase": "http://localhost:8085/v1/"
+  },
+  "tabAutocompleteOptions": {
+    "useCopyBuffer": false,
+    "maxPromptTokens": 400,
+    "prefixPercentage": 0.5,
+    "debounceDelay": 2000
+  },
+```
 
-```bash
-make test
+
+Save the config and now you can chat with Monday in the continue chat and use it as autocompletion..... it is slow and depends on your setup
+
+### In your notes or markdown files
+
+#### Notes Requirements
+
+- Obsidian
+- Text Generator plugin
+
+#### Install obsidian and text generator plugin
+
+You can find obsidian [here](https://obsidian.md/). In the settings, go to community plugins and install text generator.
+
+#### Setup text generator
+
+- In the settings under community plugins settings, select text generator. Then in LLM Providers select Custom and add the url of the local api. This will be
+`http://localhost:8085/v1/chat/completions`.
+
+- Toggle advance mode and in Header section remove the bearer token header. Headers should look like that:
+
+```json
+{
+    "Content-Type": "application/json",
+}
 ```
 
-## Usage
+- In the Variables section, change the model to be `gpt4all-j`
+
+- Lastly, enable CORS Bypass.
 
-Start typing the command or a comment and press ctrl+x to get the completion. Then press enter to run the command.
 
+Now you can use the text generator plugin to generate text in your notes.
 
 ## License
 
-[MIT](LICENSE)
+[MIT](LICENSE)