Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active
TypeScript aianthropicartifactsawsazurechatgptchatgpt-cloneclaudeclonedeepseekgeminigooglegpt-5librechatmcpo1openairesponses-apivisionwebui
🤖 docs: add `copilot-gpt4-service` AI setup info (#1695)
zimmraa9220375d3eb
diff --git a/docs/install/configuration/ai_setup.md b/docs/install/configuration/ai_setup.mdindex e7b297e8d7..7f8db5974a 100644--- a/docs/install/configuration/ai_setup.md+++ b/docs/install/configuration/ai_setup.md@@ -457,11 +457,76 @@ I recommend using Microsoft Edge for this:- Look for `lsp.asx` (if it's not there look into the other entries for one with a **very long** cookie)- Copy the whole cookie value. (Yes it's very long 😉)- Use this **"full cookie string"** for your "BingAI Token"--<p align="left">+ - <p align="left"><img src="https://github.com/danny-avila/LibreChat/assets/32828263/d4dfd370-eddc-4694-ab16-076f913ff430" width="50%"></p>+### copilot-gpt4-service+For this setup, an additional docker container will need to be setup.++***It is necessary to obtain your token first.***++Follow these instructions provided at **[copilot-gpt4-service#obtaining-token](https://github.com/aaamoon/copilot-gpt4-service#obtaining-copilot-token)** and keep your token for use within the service. Additionally, more detailed instructions for setting copilot-gpt4-service are available at the [GitHub repo](https://github.com/aaamoon/copilot-gpt4-service).++It is *not* recommended to use the copilot token obtained directly, instead use the `SUPER_TOKEN` variable. (You can generate your own `SUPER_TOKEN` with the OpenSSL command `openssl rand -hex 16` and set the `ENABLE_SUPER_TOKEN` variable to `true`)++1. Once your Docker environment is ready and your tokens are generated, proceed with this Docker run command to start the service:+ ```+ docker run -d \+ --name copilot-gpt4-service \+ -e HOST=0.0.0.0 \+ -e COPILOT_TOKEN=ghp_xxxxxxx \+ -e SUPER_TOKEN=your_super_token \+ -e ENABLE_SUPER_TOKEN=true \+ --restart always \+ -p 8080:8080 \+ aaamoon/copilot-gpt4-service:latest+ ```++2. For Docker Compose users, use the equivalent yaml configuration provided below:+ ```yaml+ version: '3.8'+ services:+ copilot-gpt4-service:+ image: aaamoon/copilot-gpt4-service:latest+ environment:+ - HOST=0.0.0.0+ - COPILOT_TOKEN=ghp_xxxxxxx # Default GitHub Copilot Token, if this item is set, the Token carried with the request will be ignored. Default is empty.+ - SUPER_TOKEN=your_super_token # Super Token is a user-defined standalone token that can access COPILOT_TOKEN above. This allows you to share the service without exposing your COPILOT_TOKEN. Multiple tokens are separated by commas. Default is empty.+ - ENABLE_SUPER_TOKEN=true # Whether to enable SUPER_TOKEN, default is false. If false, but COPILOT_TOKEN is not empty, COPILOT_TOKEN will be used without any authentication for all requests.+ ports:+ - 8080:8080+ restart: unless-stopped+ container_name: copilot-gpt4-service+ ```++3. After setting up the Docker container for `copilot-gpt4-service`, you can add it to your `librechat.yaml` configuration. Here is an example configuration:+ ```yaml+ version: 1.0.1+ cache: true+ endpoints:+ custom:+ - name: "OpenAI via Copilot"+ apiKey: "your_super_token"+ baseURL: "http://[copilotgpt4service_host_ip]:8080/v1"+ models:+ default: ["gpt-4", "gpt-3.5-turbo"] # *See Notes+ titleConvo: true+ titleModel: "gpt-3.5-turbo"+ summarize: true+ summaryModel: "gpt-3.5-turbo"+ forcePrompt: false+ modelDisplayLabel: "OpenAI"+ dropParams: ["user"]+ ```+ Replace `your_super_token` with the token you obtained following the instructions highlighted above and `[copilotgpt4service_host_ip]` with the IP of your Docker host. *****See Notes***++ Restart Librechat after adding the needed configuration, and select `OpenAI via Copilot` to start using!++ >Notes:+ > - *Only allowed models are `gpt-4` and `gpt-3.5-turbo`.+ > - **Advanced users can add this to their existing docker-compose file/existing docker network and avoid having to expose port 8080 (or any port) to the copilot-gpt4-service container.+---## Conclusion