yobulkdev

VectorFlow is an open-source, high-throughput vector embedding pipeline. It ingests raw data and transforms it into vectors. The tool writes the vectors to a vector database. VectorFlow provides a simple API endpoint for processing and storing vectors quickly and reliably.

Kedro is a toolbox for creating production-ready data science pipelines. It uses software engineering best practices to help create reproducible, maintainable, and modular data engineering and data science pipelines. Kedro facilitates efficient and collaborative data science workflows.

llm-app provides ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. It supports Docker and synchronizes with data sources like Sharepoint, Google Drive, S3, Kafka, and PostgreSQL. It enables high-accuracy RAG and AI enterprise search at scale.

Alluxio is an open-source data orchestration system for analytics and machine learning in the cloud. It provides a unified interface for accessing data stored in various storage systems. Alluxio helps improve data locality and reduces data access latency for AI and data-intensive applications. It is designed to be deployed in cloud environments.

Mosaico is a data platform designed for Robotics and Physical AI. It streamlines data management, compression, and search. Mosaico replaces monolithic files with a structured archive. It is powered by Rust and Python.

vulcan-sql is an open-source data API framework for AI agents and data applications. It helps data professionals deliver RESTful APIs from databases, data warehouses, and data lakes. The tool turns SQL queries into APIs, making data accessible for AI and application development.