jacobweiss2305 / pdf-ai-streamlit-template

Autonomous RAG

This cookbook shows how to do Autonomous retrieval-augmented generation with GPT4.

Auto-RAG is just a fancy name for giving the LLM tools like "search_knowledge_base", "read_chat_history", "search_the_web" and letting it decide how to retrieve the information it needs to answer the question.

Note: Fork and clone this repository if needed

1. Create a virtual environment

python3 -m venv ~/.venvs/aienv
source ~/.venvs/aienv/bin/activate

2. Export OPENAI_API_KEY

export OPENAI_API_KEY=***

3. Install libraries

pip install -r cookbook/examples/auto_rag/requirements.txt

4. Run PgVector

Install docker desktop first.

• Run using a helper script

./cookbook/run_pgvector.sh

• OR run using the docker run command

docker run -d \
  -e POSTGRES_DB=ai \
  -e POSTGRES_USER=ai \
  -e POSTGRES_PASSWORD=ai \
  -e PGDATA=/var/lib/postgresql/data/pgdata \
  -v pgvolume:/var/lib/postgresql/data \
  -p 5532:5432 \
  --name pgvector \
  phidata/pgvector:16

5. Run Autonomous RAG App

streamlit run cookbook/examples/auto_rag/app.py

• Open localhost:8501 to view your RAG app.

• Add websites or PDFs and ask question.

• Example Website: https://techcrunch.com/2024/04/18/meta-releases-llama-3-claims-its-among-the-best-open-models-available/

• Ask questions like:

  • What did Meta release?
  • Tell me more about the Llama 3 models?
  • Whats the latest news from Meta?
  • Summarize our conversation

6. Message on discord if you have any questions

7. Star ⭐️ the project if you like it.

8. Share with your friends: https://git.new/auto-rag