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
ZeroQI/Hama.bundle
Hama.bundle is a Plex metadata agent designed specifically for anime content, leveraging AniDB and other databases to provide rich metadata for both movies and series. It integrates with Plex to enhance the user experience by automatically matching AniDB IDs to TVDB and TMDB IDs using ScudLee's XML mapping files, which include studio and episode mapping lists. This agent fetches posters, episode screenshots, and summaries primarily from TVDB, ensuring that the metadata is comprehensive and visually appealing. It supports multiple languages for series names and episode titles, including Kanji characters, and provides warnings in HTML report files to help the community update missing or incomplete metadata. The agent also supports local media assets such as subtitles, movie trailers, theme songs, backgrounds, series posters, and season posters, which can be prioritized in Plex settings. It follows specific naming conventions for these assets to ensure proper recognition by Plex. Hama.bundle caches XML metadata files locally to improve performance and reliability, even when offline. It downloads and uses AniDB's HTTP API database file and ScudLee's XML files for mapping and collections, ensuring up-to-date and accurate metadata. Additionally, Hama.bundle supports Trakt scrobbling, allowing users to track their viewing progress. It generates detailed HTML log files that highlight missing posters, summaries, and other metadata elements, facilitating community contributions to improve the database. The agent is designed to work seamlessly within Plex, enhancing the anime viewing experience by providing detailed, accurate, and visually rich metadata, while also supporting local media enhancements and community-driven updates.
https://github.com/ZeroQI/Hama.bundle
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.