https://github.com/alikhalajii/multi_llm_chatbot
Multilingual retrieval-augmented chatbot, FastAPI, Gradio, PGVector
https://github.com/alikhalajii/multi_llm_chatbot
chatbot fasta gradio langchain multi-llm pgv rag togetherai
Last synced: about 1 month ago
JSON representation
Multilingual retrieval-augmented chatbot, FastAPI, Gradio, PGVector
- Host: GitHub
- URL: https://github.com/alikhalajii/multi_llm_chatbot
- Owner: alikhalajii
- Created: 2025-09-08T18:55:23.000Z (9 months ago)
- Default Branch: master
- Last Pushed: 2025-09-20T18:35:10.000Z (9 months ago)
- Last Synced: 2025-09-20T20:36:55.725Z (9 months ago)
- Topics: chatbot, fasta, gradio, langchain, multi-llm, pgv, rag, togetherai
- Language: Python
- Homepage:
- Size: 2.29 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 
Multi-LLM Chatbot
> ⚠️ **Work in Progress**: This project is in early development.
> Features, structure, and documentation will evolve quickly.
A multilingual **retrieval-augmented chatbot** powered by [LangChain](https://github.com/langchain-ai/langchain), [Together AI](https://github.com/togethercomputer/together-python), [FastAPI](https://fastapi.tiangolo.com/), and [pgvector](https://github.com/pgvector/pgvector), with the ability to easily switch between different language models.
---
## Usage
### Option 1: Local Development
```bash
# 1. Create and activate a new virtual environment
python -m venv .venv
source .venv/bin/activate
# 2. Install repo as a package
pip install -e .[dev]
# 3. Add your TogetherAI API key in the `.env` file
# 4. Start backend + frontend + db (hot reload)
make dev
```
### Option 2: Docker Compose
```bash
docker compose up --build
```
Backend API → http://localhost:8000/docs
Gradio UI → http://localhost:7860
Upload Document
Select Model and Chat
