Skip to content

Hemachandra9899/Pdf-Rag-Assistant

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RAG PDF Assistant

RAG PDF Assistant is a Streamlit-powered AI app that allows you to upload PDFs and ask natural language questions about their contents using Retrieval-Augmented Generation (RAG). It’s perfect for research papers, reports, contracts, or any document where you need quick insights.


🚀 Features

  • Upload any PDF and extract text automatically.
  • Ask questions in natural language about your document.
  • Retrieve accurate answers using RAG (text chunking + vector search + LLM generation).
  • Interactive Streamlit interface for seamless user experience.

🛠️ Tech Stack

  • Frontend/UI: Streamlit
  • Backend: Python
  • PDF Extraction: PyPDF2 or pdfplumber
  • Embeddings & RAG: LangChain, SentenceTransformers
  • Vector Database: FAISS / Chroma / Pinecone
  • LLM: OpenAI API (or any compatible LLM)

⚡ How It Works

  1. PDF Upload: Users upload a PDF file via the Streamlit interface.
  2. Text Extraction & Chunking: The PDF content is extracted and split into smaller chunks.
  3. Vectorization: Each chunk is converted into embeddings for semantic search.
  4. RAG Pipeline: When a user asks a question, the most relevant chunks are retrieved from the vector store.
  5. Answer Generation: The LLM generates a response using the retrieved chunks as context.

💻 Installation

  1. Clone this repository:
git clone https://github.com/your-username/rag-pdf-assistant.git
cd rag-pdf-assistant

About

RAG PDF Assistant — A Streamlit-powered AI app that lets you upload PDFs and ask natural language questions about their contents using Retrieval-Augmented Generation (RAG)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages