chrisdeadman / open-chatbot-js

Chatbot with text-generation-webui and ChatGPT 3.5 backend with a sort-of long-term memory.

🤖 Open Chat Bot

Chatbot with a 'sort-of' long-term memory 🧠 with Text generation web UI and ChatGPT backend.

🌟 Features

• Support for multiple clients
  • web: 🌐 browser based chats (recommended)
  • discord: 🎮 a discord bot you can add to your server
  • terminal: 💻 terminal based chats
  • sttts: 🗣️ Speech-To-Text & Text-To-Speech
• Rolling message history
• Long-term memory using embeddings with Redi🔍 backend
• Message correction that feeds corrections back into message history
  (e.g. corrects some command syntax issues)
• Bots can call Tools (including web-browsing and code execution)
• Multiple bots can be added to the conversation
  (reuses same model if model config is the same)

💥 Demo

📦 Dependencies

Required

• Redis with Redi🔍: docker run -p 6379:6379 redis/redis-stack.
• 📄 Refer to Dockerfile for OS dependencies.
• One of the following backends:
  • llama-node compatible models
  • Text generation web UI (with API enabled)
  • OpenAI API key

Optional

• Audio Samples
• Browser Extensions
• python-executor

🛠️ Configuration

• llama-node Example
• Text generation web UI Example
• OpenAI Example

Copy an example configuration from data/persistent/settings.example.*.json to data/persistent/settings.json.

🚀 Build and run docker image

docker build -t deads-inc/open-chatbot-js .

• <mode> is one of the implemented clients, e.g. terminal
• -d selects data/persistent as data directory
• -b selects one of the backends under data/persistent/backends
• -t selects one of the turn templates under data/persistent/turn_templates
• -c selects one of the characters under data/persistent/characters

docker run -it --rm --net=host -v ./data/persistent/:/app/data/persistent/ deads-inc/open-chatbot-js <mode> -d data/persistent -b webui.example.json -t vicuna.json -c eva.example.json

🏗️ Build locally

cd ./open-chatbot-js
npm install --omit=dev
npx tsc --project tsconfig.prod.json

🐞 Run/Debug locally

see launch.json

open-chatbot-js's Issues

Voice/Audio does not work in docker container

Describe the bug
Voice and audio do not work in docker container, so sttts client only works when running outside of container..

To Reproduce
Steps to reproduce the behavior:

$ docker run -it --rm --net=host -v ./data/settings.json:/app/data/settings.json deads-inc/open-chatbot-js sttts

ERROR: audio-capture
Started listening...
ERROR: audio-capture
Started listening...
ERROR: audio-capture
Started listening...
ERROR: audio-capture

Expected behavior
There should be a way to pipe audio streams.

Desktop (please complete the following information):

• OS: node:alpine docker
• Browser chromium
• Version 112