pdfGPT is a command-line and UI-based tool that enables users to interact with PDF documents using large language models. It allows natural language querying of one or multiple PDF files, offering answers based on the contents of those documents. Designed for research, summarization, or knowledge extraction, pdfGPT simplifies document exploration through conversational AI.
Key Features
Support for local and API-based LLM models like GPT, LLaMA, etc.
Command-line and Streamlit web UI for interaction
Extracts and chunks text from PDF documents intelligently
Handles multi-document querying
Stores embeddings using FAISS for efficient retrieval
Android DevHub
.png)
.png)