CAD-pdf-chatbot

Upload a CAD PDF and get a concise engineering summary with extracted measurements through a local LLM.

AgentNot statedStaleMCAD

What it does and how it connects

This project works with CAD drawing PDFs through two interfaces: a Flask web app that uploads a PDF and generates a concise engineering summary with a local LLM, and a Gradio chatbot that uploads a PDF, verifies measurements, and answers questions from the extracted data and diagrams.

Text extraction uses PyMuPDF, with pytesseract OCR as a fallback for scanned or image-based PDFs, and embedded diagrams are extracted from the file. Measurement parsing detects dimensions in mm, cm, m, and inches and verifies formula-based expressions. Summaries and answers run through Ollama-hosted local models such as llama3 or phi, so no cloud LLM is involved. Python 3.9 or later is required, plus Poppler for PDF to image conversion and Tesseract for OCR.

Sources

  1. 1READMEgithub.com
  2. 2GitHub repo statsapi.github.com

Not verified

  • License: the GitHub API returns no license and no LICENSE file was found in the repo, so no license is stated.
  • Pricing: none stated on the repo.
  • Real user voices: no real linked post read for this page; the repo has no open issues.
  • Related Error Index entries: no matching entry verified.
  • No GitHub releases exist, so latest release fields are null.
  • A named individual builder beyond the repository owner handle adityawalture

Last verified November 6, 2026. Listings are informational. The evidence score measures public, verifiable evidence and is not an endorsement or a compatibility claim.