Intelligent Document Analysis

Ask your PDFs
anything.

DocLens uses local embeddings and state-of-the-art AI to let you have natural conversations with any PDF — instantly, privately, for free.

Try it out
pdf-rag-a1.streamlit.app
Hello! Upload a PDF to get started. I can help you understand, summarize, or answer any question about your document.
What are the key findings of this research paper?
Based on the document, the key findings are: (1) The proposed method improves accuracy by 23% over baseline…
Ask a question about the PDF…

Why DocLens

Built with the right
priorities.

Privacy First

Embeddings are generated locally on your machine. Your document content never leaves for vectorization.

Blazing Fast

Powered by Groq's inference engine running Llama 3.1. Responses in under 2 seconds, every time.

Completely Free

HuggingFace local embeddings paired with Groq's generous free API tier — no credit card needed.

Smart Retrieval

FAISS vector store with top-k semantic search finds the most relevant chunks for every question.

Chat Interface

Natural, conversational Q&A with full session history. Ask follow-ups just like you're talking to a person.

Zero Setup

Clone, install requirements, add your API key and run. Up and running in under 5 minutes.

Under the hood

Simple pipeline,
powerful results.

01

Upload your PDF

DocLens extracts raw text from your PDF using pypdf, handling multi-page documents with ease.

02

Chunking & Embedding

Text is split into 1,000-character overlapping chunks, then embedded locally with all-MiniLM-L6-v2 — no data sent externally.

03

Semantic Retrieval

Your question is embedded and compared against the FAISS index. The top 3 most relevant chunks are retrieved.

04

LLM Generation

Context + question are sent to Groq's Llama 3.1 8B Instant model, which generates a grounded, accurate answer.

Streamlit
LangChain
FAISS
HuggingFace Transformers
Groq API
Llama 3.1 8B
pypdf

Ready to read smarter?

Drop in a PDF and start getting answers in seconds.

Try DocLens free