A simple application to upload multiple pdfs at once and ask questions across them. It will return you the most closest answer along with pinpointing the source of information too.
-
PyPDF2
for pdf reading/parsing. -
Langchain
for most of the LLM related tasks like splitting, embedding and semantic search. -
FAISS
for vectorstore. -
Streamlit
for putting it all together.
- Start by cloning the repository to your local machine:
git clone https://github.com/suyogdahal/chat-with-multiple-pdfs.git
cd chat-with-multiple-pdfs
-
Poetry is being used as the dependency manager in this project. If you don't have it installed, install it from the official Poetry documentation.
-
Once you have Poetry installed, simply run the following command to install the application dependencies:
poetry install
- Activate the Poetry shell to handle dependencies in a virtual environment:
poetry shell
- Use the command below to run the app:
streamlit run app.py
Once the application is running, navigate to the localhost URL (usually http://localhost:8501) displayed in your terminal. Now, you are all set to upload your PDFs and chat with them!