Skip to content

Simple QnA solution for performing Retrieval-Augmented QnA on a custom knowledge base of documents, using Pinecone, OpenAI / LLMs. FastAPI endpoint and Streamlit for simple demo.

Notifications You must be signed in to change notification settings

gurug-dev/BioMedAI---Retrieval-Augmented-QnA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Retrieval-Augmented-QnA

Workflow

Try it yourself:

!! Please set your OPENAI KEY and PINECONE KEYs as required, refer to init_setup.py for required ENV variables !!

pip install -r requirements.txt
pip install detectron2@git+https://github.com/facebookresearch/detectron2.git@d1e04565d3bec8719335b88be9e9b961bf3ec464
cd ./app
streamlit run main.py

OR: Create .secrets file with the following :

OPENAPI_KEY=

PINECONE_API_KEY=

PINECONE_ENV=

then,

docker build -t demopubmedqa .
docker run -it -p 8501:8501 --env-file .secrets demopubmedqa env

About

Simple QnA solution for performing Retrieval-Augmented QnA on a custom knowledge base of documents, using Pinecone, OpenAI / LLMs. FastAPI endpoint and Streamlit for simple demo.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published