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
supervc-stack/VectorChord
VectorChord (vchord) is a PostgreSQL extension purpose-built for scalable, high-performance, and cost-effective vector search. It significantly enhances vector database capabilities within PostgreSQL, serving as a successor to pgvecto.rs. The extension leverages RaBitQ compression and autonomous reranking to efficiently store vectors while preserving search quality, vastly reducing storage costs compared to other solutions like Pinecone or pgvector/pgvecto.rs. For example, it claims to host 100M vectors on a single i4i.xlarge instance for $247/month and scale to over 1 billion vectors. VectorChord accelerates index building, capable of indexing 100 million vectors in just 20 minutes through hierarchical K-means and optimized disk operations. It allows for smooth scaling by effectively controlling memory growth via dimensionality reduction and sampling, enabling 1B-vector indexes on machines with 128GB of memory. The tool is fully compatible with pgvector data types and syntax, ensuring seamless integration and providing optimal defaults. It also introduces native 4-bit (RaBitQ4) and 8-bit (RaBitQ8) vector types for drastic storage cost reduction with minimal recall loss. VectorChord's core focus is on providing an performant and economical vector indexing and search solution within the PostgreSQL ecosystem, directly addressing the operational challenges of deploying large-scale AI applications relying on vector similarity search.
https://github.com/supervc-stack/VectorChord
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.