VikParuchuri / pdftext
Extract structured text from pdfs quickly
☆469Updated last month
Alternatives and similar repositories for pdftext:
Users that are interested in pdftext are comparing it to the libraries listed below
- Detect and extract tables to markdown and csv☆742Updated 3 months ago
- Fast Semantic Text Deduplication☆638Updated this week
- UniTable: Towards a Unified Table Foundation Model☆463Updated 10 months ago
- TF-ID: Table/Figure IDentifier for academic papers☆232Updated 9 months ago
- A fast, lightweight and easy-to-use Python library for splitting text into semantically meaningful chunks.☆293Updated 3 weeks ago
- Python bindings to PDFium☆562Updated this week
- Lightweight, performant, deep table extraction☆456Updated 3 weeks ago
- Use late-interaction multi-modal models such as ColPali in just a few lines of code.☆775Updated 2 months ago
- ☆218Updated 4 months ago
- Recipes for learning, fine-tuning, and adapting ColPali to your multimodal RAG use cases. 👨🏻🍳☆271Updated last week
- ☆177Updated last week
- RAG (Retrieval-Augmented Generation) Chatbot Examples Using PyMuPDF☆877Updated 2 weeks ago
- Structured information extraction from documents☆314Updated 7 months ago
- OCR Benchmark☆464Updated last week
- Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.☆197Updated 2 weeks ago
- High-performance retrieval engine for unstructured data☆1,348Updated last week
- A python library to define and validate data types in Docling.☆122Updated this week
- ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.☆1,205Updated this week
- ☆210Updated 9 months ago
- Vision-Augmented Retrieval and Generation (VARAG) - Vision first RAG Engine☆450Updated 3 months ago
- Math OCR model that outputs LaTeX and markdown☆1,041Updated 2 months ago
- Code for explaining and evaluating late chunking (chunked pooling)☆375Updated 4 months ago
- Things you can do with the token embeddings of an LLM☆1,437Updated 3 weeks ago
- Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cro…☆786Updated 4 months ago
- Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, imp…☆174Updated 7 months ago
- A Docker-powered service for PDF document layout analysis. This service provides a powerful and flexible PDF analysis service. The servic…☆480Updated 3 weeks ago
- Fast State-of-the-Art Static Embeddings☆1,359Updated this week
- 🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with PostgreSQL or SQLite☆923Updated this week
- A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.☆1,391Updated 3 weeks ago
- YOLO models trained by DocLayNet - power your Document Intelligent by Layout Analysis☆100Updated last month