Parsing-free RAG supported by VLMs

Vector search demo with the arXiv paper dataset, RedisVL, HuggingFace, OpenAI, Cohere, FastAPI, React, and Redis.

🐊 Snappy's unique approach unifies vision-language late interaction with structured OCR for region-level knowledge retrieval. Like the project? Drop a star! ⭐

pgvector + embeddings API

Vietnamese long form question answering system with documents retrieval.

[VLSP 2025] ViDRILL is a Vietnamese document retrieval system for VLSP 2025. It combines dense and sparse retrieval, reranking, and optional LLM-based query rewriting and reasoning to support high-accuracy information retrieval and future LLM-enhanced pipelines.

Implementation of ECIR 2022 Paper: How Can Graph Neural Networks Help Document Retrieval: A Case Study on CORD19 with Concept Map Generation

Retrieves the top 10 documents from the Wikipedia corpus for a user inputted free-text query

Document Querying with LLMs - Google PaLM API: Semantic Search With LLM Embeddings

A Python-based tool for context-based search across text documents using OpenAI embeddings and Chroma vector storage. This system enables efficient querying of document collections by generating vector embeddings, storing them persistently, and retrieving relevant results based on textual queries.

The Intelligent "ASKDOC" project combines the power of Langchain, Azure, OpenAI models, and Python to deliver an intelligent question-answering system, that scans your PDF documents and answer queries based on its contents. It can be queried using Human Natural Language.

A comprehensive multimodal OCR application that supports both image and video document processing using state-of-the-art vision-language models. This application provides an intuitive Gradio interface for extracting text, converting documents to markdown, and performing advanced document analysis.

Code and dataset for the paper "Redefining Absent Keyphrases and their Effect on Retrieval Effectiveness"

"LangChat Explorer: Your intuitive document companion. Effortlessly explore vast information with natural language conversations. Simplify queries, gain insights, and embark on a seamless journey of knowledge discovery. Unleash the power of language with LangChat Explorer."

An experimental document-focused Vision-Language Model application that provides advanced document analysis, text extraction, and multimodal understanding capabilities. This application features a streamlined Gradio interface for processing both images and videos using state-of-the-art vision-language models specialized in document understanding.

Neural text summarization for document retrieval

CodeXpert: A cutting-edge AI-powered code analysis tool leveraging CodeLlama, FAISS, and HuggingFace for efficient code understanding, explanation, and optimization. 🚀✨

A two-stage information retrieval model using baseline TF-IDF model and refined BM25.

Doc-VLMs-v2-Localization is a demo app for the Camel-Doc-OCR-062825 model, fine-tuned from Qwen2.5-VL-7B-Instruct for advanced document retrieval, extraction, and analysis. It enhances document understanding and also integrates other notable Hugging Face models.