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
nuclia/nucliadb
NucliaDB is an AI Search database specifically designed for handling and searching unstructured data, making it particularly suitable for Retrieval Augmented Generation (RAG) applications. Its core strength lies in its hybrid search capabilities, combining vector, full-text, and graph indexes to provide comprehensive and semantically rich results. Built with Rust and Python, NucliaDB is engineered for large datasets and multi-tenancy, offering features such as storing text, files, vectors, labels, and annotations. It supports both traditional text searches and semantic searches using vectors, which allows for finding similar sentences or concepts without relying on exact keywords. The database also integrates with Nuclia's ecosystem, including the Nuclia Understanding API for data extraction, enrichment, and inference, and the Nuclia Learning API for training ML models. Key features encompass an export format compatible with NLP pipelines (like HuggingFace datasets), storage of original and extracted data, indexing at various granularities (fields, paragraphs, semantic sentences), role-based security, and cloud-native capabilities with blob support for S3-compatible, GCS, and Azure Blob Storage. Its architecture is explicitly differentiated from traditional search engines like Elasticsearch by being purpose-built for unstructured data and AI-driven insights from the ground up.
https://github.com/nuclia/nucliadb
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.