Modular Telegram assistant: Haystack Agent, Docling document RAG, Pinecone memory, OpenAI tools for weather/cats/dogs.
Local-first ETL for document intelligence: layout analysis, OCR, structural chunking
Make image-heavy PDFs grep-able for AI agents. Convert PDF corpora into structured Markdown where every diagram, screenshot and table is searchable as text. No vector DB, no embeddings - just clean Markdown with LLM-generated image descriptions.
Telegram-бот для командного чата: Haystack pipelines, Pinecone, OpenAI (ProxyAPI), Docling, запись и RAG по переписке и документам.
CUDA-accelerated PDF -> Markdown/HTML converter using Docling + IBM Granite Vision chart extraction
A comparative evaluation suite benchmarking 6 PDF-to-Markdown parsers for RAG indexing performance.
Multimodal RAG pipeline to transform static PDF manuals into image-aware AI chatbots. Local, secure, and transparent.
A system designed to ingest complex multi-page invoices, extract line-item data, and perform grounded Q&A using Retrieval Augmented Generation.
Querywise is a multi-agent Retrieval-Augmented Generation (RAG) system designed to help users query long, complex documents with accurate, fact-verified answers. Unlike traditional chatbots like ChatGPT or DeepSeek, which may hallucinate responses...
Robust local AI document tools: GPU-accelerated PDF parsing and schema-enforced JSON extraction.
Repository for testing and demonstrating the capabilities of Docling for document conversion.
Open-source document cleanup and RAG-prep tool powered by Docling. Convert PDFs, DOCX, images, and text into Markdown, JSON, and RAG-ready chunks.
Minimal RAG for chatting with your documents.
基于大模型的软件工程文档结构化提取系统
Docling: Explore Document Processing Basics on Linux Mint 22.3
StudyAI is an AI-powered academic assistant that turns documents into learning experiences. Built with LangGraph, FastAPI, and Gradio, it supports question generation, AI exams, RAG Q&A, and intelligent summarization with human-in-the-loop refinement.
Telegram RAG-бот: обработка PDF и DOCX, индексация через Docling и Pinecone, ответы на вопросы по документу.
To associate your repository with the docling topic, visit your repo's landing page and select "manage topics."