ChatwithMultiplePDFs
The project is a Streamlit-based app that allows users to upload PDF files, processes the text into chunks, stores it in a FAISS vector store using Google Generative AI embeddings, and enables conversational Q&A with the documents using Google Generative AI’s chat model for answers.
Install / Use
/learn @harshvardhan-11/ChatwithMultiplePDFsREADME
Chat with Multiple PDFs using LangChain and Gemini
Image 1: Represents the developed user interface, showcasing the design and layout.
Image 2: Depicts a user uploading pdf file and inputting their query into the dialogue box.
Image 3: Illustrates the response generated by the application based on the user's input.
Project Overview
This project enables users to interact with PDF files by asking questions and receiving answers using Google's Gemini AI model. The application processes PDF files by extracting text, breaking it into manageable chunks, storing the text in a vector database using FAISS, and allowing for conversational queries. The queries are matched against the stored content, and if the answer is found, it is generated using a language model.
The app is built with Streamlit for the front end, Google Generative AI for embeddings and conversational chains, and FAISS for efficient document retrieval. It is designed to simplify interaction with large PDF files by turning them into a conversational experience.
Features
- PDF Text Extraction: Upload multiple PDFs, extract text, and process it.
- Text Chunking: Break large texts into chunks for better management and retrieval.
- Vector Storage: Store chunks in a FAISS vector database for efficient semantic search.
- Google Embeddings: Use Google Generative AI embeddings for vectorization.
- Conversational AI: Ask questions and receive detailed answers from the uploaded PDFs using a conversational chain powered by Google's Gemini AI.
How It Works
- Upload PDFs: Users can upload one or more PDF files through the Streamlit interface.
- Text Extraction and Chunking: The app reads the uploaded PDFs and extracts the text. This text is split into chunks to improve search accuracy.
- Store in FAISS: The text chunks are embedded using Google Generative AI embeddings and stored in a FAISS vector database.
- Ask Questions: Users can type a question in the input box, and the system will search for the most relevant text from the PDF's vector database.
- Conversational Response: A conversational AI model (Google Gemini AI) uses the relevant context to generate detailed answers.
Related Skills
node-connect
352.9kDiagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps
claude-opus-4-5-migration
111.5kMigrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5
frontend-design
111.5kCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
model-usage
352.9kUse CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
