run-llama/llama_index
LlamaIndex is a leading data framework that enables building LLM-powered applications by providing tools for data ingestion, structuring, and advanced querying to augment large language models with private and external data.
Awesome AI Agents › Data Integration and Specialized Solutions
pipeshub-ai/pipeshub-ai
PipesHub is an open-source workplace AI platform designed to enhance enterprise operations by enabling efficient collaboration between employees and AI agents. It addresses the common challenge of dispersed work data across multiple applications such as Google Workspace, Microsoft 365, Slack, Jira, and Confluence by providing a natural language search interface that allows users to quickly find relevant information, similar to a Google search. The platform not only retrieves the most pertinent results but also provides clear citations and sources through the use of Knowledge Graphs and Page Ranking techniques. The architecture of PipesHub supports flexibility and scalability, allowing enterprises to bring their preferred deep learning models for indexing and inference. It offers real-time or scheduled data indexing, ensuring that information is always up-to-date. Security is a key focus, with source-level permissions to restrict document visibility to authorized users only, and built-in data security measures to protect sensitive information. PipesHub supports deployment both on-premise and in the cloud, making it adaptable to various enterprise environments. Its modular and scalable architecture allows independent scaling of services to meet organizational needs. The platform includes enterprise-grade connectors for seamless and secure integration with popular workplace tools such as Google Drive, Gmail, Google Calendar, and upcoming support for OneDrive, SharePoint Online, Outlook, Slack, Notion, Jira, Confluence, and MS Teams. It supports a wide range of file formats including PDFs (even scanned), Microsoft Office documents, CSV, Markdown, HTML, Google Docs, and more, with plans to support images, audio, and video files. Beyond search, PipesHub enables enterprises to create custom applications and AI agents through a no-code interface, empowering organizations to tailor AI solutions to their specific workflows. The roadmap includes features like code search, workplace AI agents, APIs and SDKs, personalized search, and highly available Kubernetes deployments. The platform is accessible for developers with detailed deployment guides for both development and production environments using Docker Compose. Overall, PipesHub offers a comprehensive, secure, and flexible AI-powered workplace platform to improve information accessibility and operational efficiency in enterprises.
https://github.com/pipeshub-ai/pipeshub-ai
Also in Data Integration and Specialized Solutions
pingcap/tidb
TiDB is an open-source, cloud-native, distributed SQL database offering ACID guarantees, horizontal scalability, high availability, HTAP capabilities, and MySQL compatibility.
getzep/graphiti
Graphiti is a framework for building and querying real-time, temporally-aware knowledge graphs designed to support AI agents in dynamic environments with efficient incremental updates and hybrid retrieval methods.
dolthub/dolt
Dolt is a SQL database with Git-like features, enabling full version control over data, including branching, merging, and diffing of data.
vectordotdev/vector
Vector is a high-performance, end-to-end observability data pipeline designed to collect, transform, and route logs, metrics, and traces.
cube-js/cube
Cube Core is an open-source semantic layer that enables AI, business intelligence, and embedded analytics by providing a flexible, API-driven platform supporting multiple SQL data sources and real-time analytics.
llmware-ai/llmware
llmware is a unified framework for building enterprise Retrieval-Augmented Generation (RAG) pipelines using small, specialized language models integrated with secure knowledge sources for efficient AI applications.
cocoindex-io/cocoindex
CoCoIndex is an ultra-performant data transformation framework for AI, specializing in incremental processing for data indexing and real-time semantic search with Python and Rust.