Real-time sync for Postgres.

Rust port of Yjs

Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.

AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data…

Python bindings for Tantivy

Rich is a Python library for rich text and beautiful formatting in the terminal.

A complement to pgvector for high performance, cost efficient vector search on large workloads.

Extract structured text from pdfs quickly

Navigate SEC Edgar data in Python

Rust library for regular expressions using "fancy" features like look-around and backreferences

OCR, layout analysis, reading order, table recognition in 90+ languages

Python API for https://vespa.ai, the open big data serving engine

Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

A blazing fast inference solution for text embeddings models

Locality Sensitive Hashing

Postgres for Search and Analytics

A high-throughput and memory-efficient inference and serving engine for LLMs

Infers JSON Schemas and Type Definitions from example JSON

Modern utility library and typescript typings for building JSON Schema documents

Infers the type and format of JSON values