Skip to content

Latest commit

 

History

History
44 lines (32 loc) · 1.46 KB

README.en.md

File metadata and controls

44 lines (32 loc) · 1.46 KB

LLMApi Chat

LLMApi Chat

Self-host llmapi web chat for ChatGPT and others

Introdution

llmapi-chat is a simple web-chat-server backend that can chat with a variety of large language models (LLM, such as ChatGPT, GPT-3, GPT-4, etc.)

Supportted ability

  • Continuous Dialogue: Use ChatGPT for multiple rounds of continuous dialogue
  • Text completion: use GPT-3 or welm model for text completion
  • Text embedding: use openai's Embedding model to convert sentences into vectors, which can be used for classification, search and other tasks
  • Text to image: use dall-e model to convert text to image
  • Real-time search: Use NewBing interface to experience Bing search (based on ChatGPT, unofficial interface)

Install & Run

  1. build and run locally
./build.sh
./start.sh
  1. run with docker
docker build -t llmapi-chat:0.1.0 .
docker run --name webchat -d -p 8081:8081 llmapi-chat:0.1.0

Visit

Open http://127.0.0.1:8081 in the browser to visit the webchat page.

You can sign up on llmapi.io to get apikey, setup as below to chat with LLMs like ChatGPT GPT3 and so on.

Chat demo

Acknowledgements

This project developed based on chatGPT-web