High-performance EPUB to PDF converter optimized for large files. Features smart splitting, hierarchical TOC reconstruction, and perfect layout rendering.
-
Updated
Jan 6, 2026 - Python
#
pdfprocessing
Here are 17 public repositories matching this topic...
Enterprise Multi-Tenant RAG system for compliance document analysis with a 30-document benchmark dataset using FastAPI, LangGraph, Gemini, and Qdrant.
nlp machine-learning exploratory-data-analysis python3 artificial-intelligence semantic-search rag fastapi streamlit qdrant langchain vectordb vectordatabase retrieval-augmented-generation langgraph googlegemini pdfprocessing
-
Updated
Jul 26, 2026 - Jupyter Notebook
An intelligent chatbot that allows users to upload text-based Ayurveda PDFs and ask questions based on the content using RAG (Retrieval-Augmented Generation) combining semantic search and LLM-based responses.
python pdf embeddings question-answering pymupdf fastapi vector-database llm langchain text-splitting llama3 fiass langchain-groq pdfprocessing
-
Updated
Jun 28, 2025 - Python
GenZx is a student-focused web platform built using Django to provide useful academic tools and resources in one place. The project was developed with a focus on clean backend structure, production deployment, and basic SEO practices.
python pdf django backend filesystem django-rest-framework logic-programming backend-api fron pdfprocessing
-
Updated
Feb 19, 2026 - HTML
Vakta is a Python-based desktop application that converts text from PDF, DOC, and TXT files into audio files.
-
Updated
Oct 24, 2025 - Python
AI-assisted systematic review PDF coder for the Social Connectedness & Health lab (Claude + CSV export, local web UI)
-
Updated
Jun 18, 2026 - Python
A file processor for ZipGrade
-
Updated
Jun 25, 2026 - JavaScript
AI-powered PDF question-answering system using Experimental Retrieval-Augmented Generation project using local embeddings, FAISS indexing, and Mistral via Ollama.
python pdf chunk embedding faiss rag fastapi sentence-transformers llm textextraction ollama pdfprocessing vectore-database
-
Updated
May 14, 2026 - Python
AI bot for PYQ solutions—simple, smart. Now Scan, solve and succeed
javascript front-end ai reactjs tailwindcss googleappsscript vite supabase googlesheets-api openrouter-api pdfprocessing
-
Updated
Aug 6, 2025 - JavaScript
Chat with your PDF documents using RAG — FastAPI + Groq (LLaMA 3.1) + Pinecone + FastEmbed. Streaming answers, conversation memory, table extraction, query rewriting, and one-click Render deployment.
-
Updated
Apr 26, 2026 - Python
Automated API test suite for Indus Electricity Board to validate PDF invoice uploads. Ensures accurate extraction of billing fields like account number, invoice number, billing date, and invoice amount, enabling digitization of electricity invoice workflows.
-
Updated
Aug 5, 2025 - Java
A sophisticated web intelligence platform that fuses a RAG-powered LLM chatbot with on-demand web scraping.
javascript python flask authentication postgresql webscraping authentication-backend faiss rag vector-database generative-ai langchain pdfprocessing
-
Updated
Sep 19, 2025 - Python
An OCR-based Python application that extracts VAT amounts and percentages from PDF and image files, then exports the results to an Excel spreadsheet.
pymupdf dataextraction easyocr pythonautomation pdfprocessing vatextraction ocrprocessing invoiceparsing
-
Updated
Sep 29, 2026 - Python
A Flask-based web app integrating GPT with Retrieval-Augmented Generation (RAG) for interactive chat, document querying, and user account management.
mysql docker flask webapp gpt rag userauthentication tavily chathistory documentquerying pdfprocessing
-
Updated
Aug 30, 2024 - Python
AI-powered resume screening system using Flask, NLP, Sentence Transformers, and cosine similarity.
python nlp flask machine-learning deep-learning numpy jupyter-notebook pandas artificial-intelligence cosine-similarity semantic-search resume-screening pdfplumber sentence-transformers pdfprocessing
-
Updated
Jul 11, 2026 - HTML
Retrieval-augmented QA system built from scratch to answer questions grounded in PDF documents — including tables and figures — with hybrid retrieval, multimodal table transcription, and an automated evaluation harness.
python evaluation embeddings question-answering bm25 multidimensional table-extraction rag fastapi vector-search hybrid-search qdrant qdrant-vector-database document-qa retrieval-augmented-generation llm-evaluation pdfprocessing bm25-search
-
Updated
Oct 16, 2026 - Python
Add this topic to your repo
To associate your repository with the pdfprocessing topic, visit your repo's landing page and select "manage topics."