How shreyasbgr/pdf-info-extractor works
Project Type and Purpose
• This is a small, monolithic “full-stack” Python app built with Streamlit.
• Purpose: allow users to upload or point to PDF documents, extract information via a PDF parsing library, then enrich or summarize that info by calling the Google Gemini API, and display results in an interactive web UI.
File Structure Analysis
• Root files only—no subdirectories:
• app-local.py: Streamlit entrypoint for local dev (loads .env).
• app-streamlit.py: Streamlit entrypoint for cloud deployment.
• requirements.txt: Python dependencies (Streamlit, PDF parser, dotenv, HTTP client).
• .gitignore, README.md.
• No database, no microservices—everything lives in one process.
• Config sourced from a .env file (API key).
Key README Insights
• Uses Conda to create a Python 3.10 env.
• Requires a GOOGLE_API_KEY in .env.
• Two execution modes: local vs. Streamlit Cloud.
• Hosted publicly at a Streamlit app URL.