Search Results for "pentaho data integration"

OpenViking is an open-source context database engineered for efficient indexing and retrieval of large amounts of unstructured or semi-structured context data used by AI applications. It’s primarily designed to serve as a high-performance, scalable backend for storing app context, embeddings, conversational histories, and other textual artifacts that need rapid lookup and semantic search, which makes it especially useful for systems like chatbots or memory-augmented agents. The project is...

pgai is a suite of PostgreSQL extensions developed by Timescale to empower developers in building AI applications directly within their databases. It integrates tools for vector storage, advanced indexing, and AI model interactions, facilitating the development of applications like semantic search and Retrieval-Augmented Generation (RAG) without leaving the SQL environment.

Generate a backend and frontend stack using Python, including interactive API documentation. Production ready Python web server using Uvicorn and Gunicorn. Very high performance, on par with NodeJS and Go (thanks to Starlette and Pydantic). Great editor support. Completion everywhere. Less time debugging. Designed to be easy to use and learn. Less time reading docs. Minimize code duplication. Multiple features from each parameter declaration. Get production-ready code. With automatic...

zetadb is a python/zope tool that allows a rapid application development of relational database oriented web applications. It generates transladable and user friendly applications to maintain data over the web. It also implements OpenOffice integration

A lightweight, browsing-based, 100% Python, federated data integration framework. Users may create custom schemas for disparate sources, query and expand results across sources to find related data; for use in fields such as bioinformatics and datamining

SnapLogic is an Open Source Data Integration framework that combines the power of state-of-the-art dynamic programming languages with standard Web interfaces to solve today's most pressing problems in data integration.

Crow - Computational Representation Of Whatever. A platform for the integration and mining of complex and distributed data. Represents cross-linked semantic web documents as a network of software objects and offers easy ways to filter, and sort them.