pathwaycom/llm-app
Ready-to-run cloud templates for building real-time RAG, AI pipelines, and enterprise search applications that synchronize with various live data sources.
Awesome Infra for AI › Vector Databases & Retrieval Infrastructure
zilliztech/deep-searcher
DeepSearcher is a sophisticated open-source project designed for advanced information retrieval and knowledge management within enterprise environments. It leverages cutting-edge Large Language Models (LLMs) such as OpenAI o3, Qwen3, DeepSeek, and Grok 4, alongside robust vector databases like Milvus and Zilliz Cloud, to process and analyze private data. The primary function of DeepSearcher is to conduct in-depth searches, comprehensive evaluations, and intelligent reasoning, ensuring data security while providing highly accurate answers and detailed reports. This makes it particularly suitable for scenarios like enterprise knowledge management, intelligent Q&A systems, and enhanced information retrieval. The tool offers several key features, including private data search capabilities that maximize the utility of internal corporate data while safeguarding its integrity. It also supports the integration of online content to enrich search results when necessary. DeepSearcher provides flexible vector database management with support for Milvus and other vector databases, enabling efficient data partitioning and retrieval. It supports a variety of embedding models for optimal selection and is compatible with multiple LLMs for diverse intelligent Q&A and content generation tasks. Additionally, it includes a document loader for local files and is developing web crawling functionalities, enhancing its data ingestion capabilities. The project's architecture is designed to facilitate robust data processing and intelligent response generation, catering to a wide range of analytical needs.
https://github.com/zilliztech/deep-searcher
Also in Vector Databases & Retrieval Infrastructure
run-llama/llama_index
LlamaIndex is an open-source data framework for building LLM applications by connecting custom data sources to large language models, focusing on data ingestion, indexing, and retrieval augmented g...
milvus-io/milvus
Milvus is a high-performance, cloud-native vector database designed for scalable vector Approximate Nearest Neighbor (ANN) search, efficiently organizing and searching vast amounts of unstructured ...
VectifyAI/PageIndex
PageIndex is a vectorless, reasoning-based RAG system that builds hierarchical tree indexes from documents and uses LLMs to reason over them for context-aware retrieval.
qdrant/qdrant
Qdrant is an open-source, high-performance vector similarity search engine and vector database designed specifically for AI applications, enabling fast storage, search, and management of vectors wi...
Tencent/WeKnora
WeKnora is an open-source, LLM-powered knowledge framework for enterprise document understanding, semantic retrieval, and autonomous reasoning, featuring RAG, ReAct agents, and an auto-maintaining ...
topoteretes/cognee
Cognee is an open-source AI memory platform that provides AI agents with persistent long-term memory through a self-hosted knowledge graph, combining vector embeddings and graph reasoning.
RyanCodrai/turbovec
TurboVec is a Rust-based approximate nearest neighbor (ANN) vector index with Python bindings, built on Google Research's TurboQuant algorithm for efficient, memory-optimized vector similarity search.