PDFQuest is an AI-powered PDF QA tool that enables you to easily upload and analyze PDF documents with advanced question-answering capabilities. PDFQuest goes beyond traditional keyword-based search and utilizes vector embeddings and semantic search to deliver precise and efficient results from your PDFs to improve your workflow efficiency.
- Clone the repository using
git clone https://github.com/ayush-vibrant/PDFQuest.git - Navigate to the project directory by running
cd PDFQuest - Install the required packages using
pip install -r requirements.txt
To use PDFQuest, simply run python -m streamlit run folder-location/PDFQuest/streamlit/main.py in your terminal. This will start a local server that you can access through your web browser.
In the command, replace folder-location/ with the actual path to the PDFQuest directory on your machine.
Before running the app, make sure to create a .env file in your local system and add the following environment variables:
OPENAI_API_KEY=<your openai api key>
PINECONE_API_KEY=<your pinecone api key>
PINECONE_API_ENV=<your pinecone api env>
USE_PINECONE=false
PINECONE_INDEX_NAME=<test>
TEMPERATURE=0
QA_WITH_SOURCE=false
For streamlit applications. Secrets management happens from a different file. See this for more information.
Add a file called secrets.toml in a folder called .streamlit at the root of your app repo, and copy/paste your secrets into that file.
OPENAI_API_KEY="your openai api key"
PINECONE_API_KEY="your pinecone api key"
PINECONE_API_ENV="your pinecone api env"
USE_PINECONE="false"
PINECONE_INDEX_NAME="test"
TEMPERATURE="0"
QA_WITH_SOURCE="false"
