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
HelixDB/helix-db
HelixDB is an OLTP graph-vector database engineered in Rust, providing a comprehensive solution for building AI applications by consolidating various data models. Unlike traditional setups requiring separate databases for different data types, HelixDB integrates graph, vector, key-value, document, and relational data within a single platform. This unification aims to simplify the architecture for AI agents, offering federated access to enterprise data for memory management, knowledge graphs, and diverse AI applications, particularly for Retrieval Augmented Generation (RAG). The database's core strength lies in its ability to manage interconnected data through a graph model alongside high-dimensional embeddings for semantic search and retrieval. This makes it suitable for scenarios where relationships between data points are as crucial as their content or similarity. HelixDB offers a CLI for local instance management and interaction with Helix Cloud, which provides a managed, distributed, and highly available service with integrated vector and full-text search, ACID transactions, and auto-scaling. Developers can interact with HelixDB using Rust or TypeScript SDKs, defining queries that translate into dynamic JSON requests to the database instance, streamlining the development of AI-driven applications without complex build or deploy steps.
https://github.com/HelixDB/helix-db
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.