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
Restream/reindexer
Reindexer is a high-performance, embeddable, in-memory, document-oriented database with a sophisticated Query builder interface. Developed in C++ with a Go API, it focuses on fast search capabilities for complex queries, positioning itself as a more performant alternative to systems like Elasticsearch. Key features include full-text search, k-nearest neighbors (KNN) and Approximate Nearest Neighbors (ANN) vector indexing, and hybrid search combining both. It is designed for minimal memory consumption, employing optimizations like dense binary C++ structs for data storage, string deduplication, and an object cache for deserialized documents to reduce Go garbage collector overhead. The database supports various index types, complex primary keys, composite indices, join operations, and SQL-compatible queries. It also provides features like replication, sharding (though details are not fully elaborated in the provided text), aggregations, TTL for data expiration, and direct JSON operations. With connectors for Python, Java, PHP, Rust, and .NET, Reindexer offers a versatile solution for applications requiring efficient data storage and retrieval with advanced search functionalities, especially those leveraging vector embeddings for AI-driven search and recommendations.
https://github.com/Restream/reindexer
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.