# alejandro-ao/ask-multiple-pdfs

A Langchain app that allows you to chat with multiple PDFs

Repository: https://github.com/alejandro-ao/ask-multiple-pdfs
Canonical: https://ross.abutalabs.com/products/ask-multiple-pdfs
Language: Python
License Family: other
Last push: 2024-04-20T01:51:18+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 85
- inputs: {"age_days": 1202, "days_push": 866, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1873, forks 1017 (observed 2026-08-28T04:05:47.095192+00:00)

## What it is
A Streamlit-based Python application built with Langchain that lets users chat with multiple PDF documents using natural language. It extracts and chunks PDF text, embeds it, and uses an LLM to answer questions grounded in the document content.

## Use cases
- chat with multiple pdfs
- ask questions about pdf documents
- build a pdf question-answering app with langchain
- query documents with an llm
- learn how to build a rag chatbot
- extract answers from pdf content

## When to choose
- you want a ready-made starting point for a document chat app
- you're learning Langchain and RAG via a tutorial project
- you need to ask natural-language questions across several PDFs

## When to avoid
- you need a production-grade, actively maintained document chat solution
- you don't want to depend on an OpenAI API key
- you need a license for commercial use clarity (repo states MIT but no license file)
- you expect community contributions or support

## Facets
- artifact type: application
- maturity: maintenance
- function: rag, pdf, chat-interface, llm-inference, vector-database
- domain: artificial-intelligence, large-language-models, pdf, education
- platform: python, cross-platform
- tags: langchain, streamlit, openai, embeddings, tutorial-project, pdf-chat, retrieval-augmented-generation, web-server

## Member repositories
- alejandro-ao/ask-multiple-pdfs (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:47.095192+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:14:49.096725+00:00, confidence not recorded.
  - readme: https://github.com/alejandro-ao/ask-multiple-pdfs (fetched 2026-08-28T04:05:47.095192+00:00, sha 5074aa4adebf)
- Data as of 2026-08-30T08:39:29.467469+00:00.