https://github.com/pors/langchain-chat-websockets

LangChain LLM chat with streaming response over websockets
https://github.com/pors/langchain-chat-websockets

async fastapi langchain langchain-python llm openai openai-api openai-chatgpt websockets

Last synced: 7 days ago
JSON representation

LangChain LLM chat with streaming response over websockets

• Host: GitHub
• URL: https://github.com/pors/langchain-chat-websockets
• Owner: pors
• License: apache-2.0
• Created: 2023-05-02T12:32:18.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-11-30T07:25:04.000Z (11 months ago)
• Last Synced: 2024-10-23T10:34:40.143Z (16 days ago)
• Topics: async, fastapi, langchain, langchain-python, llm, openai, openai-api, openai-chatgpt, websockets
• Language: HTML
• Homepage:
• Size: 18.6 KB
• Stars: 88
• Watchers: 2
• Forks: 8
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-langchain-zh - Langchain Chat Websocket - chat-websockets?style=social): 关于 LangChain LLM 聊天，通过 websockets 进行流响应 (开源项目 / 其他聊天机器人)
• awesome-langchain - Langchain Chat Websocket - chat-websockets?style=social) (Open Source Projects / Other / Chatbots)

README

        
### LangChain chat with streaming response over FastAPI websockets

Install and run like:

```

pip install -r requirements.txt # use a virtual env

cp dotenv-example .env # add your secrets to the .env file

uvicorn main:app --reload

```

Or using docker-compose :

### Run with Docker Compose

To run the LangChain chat application using Docker Compose, follow these steps:

1. Make sure you have [Docker](https://www.docker.com/) installed on your machine.

2. Create a file named `.env` file 

3. Open the newly created `.env` file in a text editor and add your OpenAI API key:

   ```dotenv

   OPENAI_API_KEY=your_openai_api_key_here

   ```

   Replace `your_openai_api_key_here` with your actual OpenAI API key.

4. Run the following command to build the Docker image and start the FastAPI application inside a Docker container:

   ```bash

   docker-compose up --build

   ```

5. Access the application at [http://localhost:8000](http://localhost:8000).

Thanks to [@hwchase17](https://github.com/hwchase17) for showing the way in [chat-langchain](https://github.com/hwchase17/chat-langchain/tree/master)