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...
Awesome Infra for AI › Vector Databases & Retrieval Infrastructure
pathwaycom/llm-app
Pathway's AI Pipelines offer a framework for rapidly deploying AI applications with high-accuracy Retrieval-Augmented Generation (RAG) and enterprise search at scale, ensuring they leverage the most current knowledge from diverse data sources. It provides ready-to-deploy LLM App Templates designed for local testing and cloud/on-premises deployment (GCP, AWS, Azure, Render). These applications seamlessly connect and synchronize with data sources like file systems, Google Drive, SharePoint, S3, Kafka, PostgreSQL, and real-time data APIs, automatically handling new data additions, deletions, and updates. The framework includes built-in data indexing capabilities for vector, hybrid, and full-text search, all managed in-memory with caching, eliminating the need for separate infrastructure dependencies like external vector databases, caches, or API frameworks. The templates support scaling up to millions of documents, with options optimized for simplicity or accuracy. It integrates quickly with existing LLM orchestration tools like Langchain and LlamaIndex. The applications run as Docker containers, exposing HTTP APIs for frontend connectivity, and some templates include optional Streamlit UIs for quick testing. The core technology leverages Pathway's Live Data Framework for data synchronization and API serving, using optimized libraries like Usearch for vector indexing and Tantivy for hybrid full-text indexing, providing a unified application logic for backend, embedding, retrieval, and LLM stack.
https://github.com/pathwaycom/llm-app
Also in Vector Databases & Retrieval Infrastructure
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.
weaviate/weaviate
Weaviate is an open-source, cloud-native vector database for semantic search, combining vector similarity search with keyword filtering, RAG, and reranking capabilities.