🦉 Data Versioning and ML Experiments

Refine high-quality datasets and visual AI models

Neo4j graph construction from unstructured data using LLMs

A system for agentic LLM-powered data processing and ETL

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure

Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.

🔮 Instill Core is a full-stack AI infrastructure tool for data, model and pipeline orchestration, designed to streamline every aspect of building versatile AI-first applications

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

Nomic Developer API SDK

ContextGem: Effortless LLM extraction from documents

Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.

A multi-modal vector database that supports upserts and vector queries using unified SQL (MySQL-Compatible) on structured and unstructured data, while meeting the requirements of high concurrency and ultra-low latency.

AI-Powered Data Processing: Use LOTUS to process all of your datasets with LLMs and embeddings. Enjoy up to 1000x speedups with fast, accurate query processing, that's as simple as writing Pandas code

Get clean data from tricky documents, powered by vision-language models ⚡

A curated list of resources for Document Understanding (DU) topic

visual data prep powered by python

Humans and AI agents, building knowledge bases together. Self-hosted document annotation, version control, semantic search, and MCP.

Interactively explore unstructured datasets from your dataframe.

Curate better data for LLMs