Back to Projects

PDFhelper: Intelligent Document Retrieval

RAG-based system for efficient document querying and management.

LLaMA 3.2QdrantHugging Face

Problem

Managing and extracting insights from large collections of PDF documents is a bottleneck for research. Standard keyword search often misses semantic context.

Solution: RAG Pipeline

PDFhelper is a Retrieval-Augmented Generation (RAG) system that uses vector embeddings to understand the "meaning" of queries.

Tech Stack

  • Embeddings: Hugging Face all-MiniLM-L6-v2.
  • Vector DB: Qdrant (local Docker instance).
  • LLM: LLaMA 3.2 (via Ollama) for generation.
  • Orchestration: LangChain.

Workflow

  1. Ingestion: PDFs are parsed, chunked (500 chars with 50 overlap), and embedded.
  2. Storage: Vectors stored in Qdrant collections.
  3. Retrieval: User query is embedded; Top-K cosine similarity match found.
  4. Generation: Retrieved chunks + Query sent to LLaMA 3.2 to generate the answer.

Impact

  • Reduced search time by ~60% for technical documentation.
  • Enable "Chat with your Data" functionality locally without data leaving the machine.
Ask AIABOUT MY WORK