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
llmware-ai/llmware
llmware is a unified framework designed for building enterprise Retrieval-Augmented Generation (RAG) pipelines using small, specialized language models. It enables organizations to deploy these models privately, integrate them securely with enterprise knowledge sources, and cost-effectively tune and adapt them for various business processes. The framework consists of two main components: a RAG pipeline that manages the full lifecycle of connecting knowledge sources to generative AI models, and a catalog of over 50 small, specialized models fine-tuned for key enterprise tasks such as fact-based question answering, classification, summarization, and information extraction. llmware supports a wide range of models and technologies, including GGUF, HuggingFace, Sentence Transformers, and API-based models, all accessible through a unified Model Catalog interface. This catalog allows easy lookup, loading, and integration of models into prompts or applications. The framework also includes a Library component for ingesting, organizing, and indexing diverse document types at scale, supporting formats like PDF, PPTX, DOCX, XLSX, TXT, CSV, JSON, audio, images, and HTML. Libraries can be embedded with various embedding models and vector databases such as Milvus and ChromaDB. The Query module enables flexible querying of libraries using text, semantic, hybrid, metadata, and custom filters, facilitating precise information retrieval. Additionally, the Prompt component simplifies combining knowledge retrieval with LLM inference, allowing users to build prompts that integrate retrieved sources for enhanced responses. llmware is designed to be accessible without requiring GPU servers, making it easy to get started on standard laptops. It offers extensive documentation, examples, and community support through Discord and YouTube tutorials. The framework is ideal for enterprises looking to build secure, efficient, and scalable AI applications that leverage specialized models and their own knowledge bases.
https://github.com/llmware-ai/llmware
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.
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.
electric-sql/electric
Electric is a Postgres sync engine that provides real-time data synchronization, partial replication, and data delivery for modern applications and AI agents.