Tonic Validate is a platform for Retrieval Augmented Generation (RAG) development and experiment tracking. To check it out, go to our repo here
This is a LlamaIndex project using FastAPI bootstrapped with create-llama.
First, setup the environment:
poetry install
poetry shell
By default, we use the OpenAI LLM (though you can customize, see app/api/routers/chat.py). As a result you need to specify an OPENAI_API_KEY in an .env file in this directory.
Example backend/.env file:
OPENAI_API_KEY=<openai_api_key>
Second, generate the embeddings of the documents in the ./data directory (if this folder exists - otherwise, skip this step):
python app/engine/generate.py
Third, run the development server:
python main.py
Then call the API endpoint /api/chat to see the result:
curl --location 'localhost:8000/api/chat' \
--header 'Content-Type: application/json' \
--data '{ "messages": [{ "role": "user", "content": "Hello" }] }'
You can start editing the API by modifying app/api/routers/chat.py. The endpoint auto-updates as you save the file.
Open http://localhost:8000/docs with your browser to see the Swagger UI of the API.
The API allows CORS for all origins to simplify development. You can change this behavior by setting the ENVIRONMENT environment variable to prod:
ENVIRONMENT=prod uvicorn main:app
To learn more about LlamaIndex, take a look at the following resources:
- LlamaIndex Documentation - learn about LlamaIndex.
You can check out the LlamaIndex GitHub repository - your feedback and contributions are welcome!