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
devflowinc/trieve
Trieve is a comprehensive platform designed for integrating search, recommendations, and RAG functionalities into applications through a unified API. It emphasizes operational efficiency for AI models, providing tools for serving and retrieving information relevant to AI tasks. Key features include self-hosting options, semantic dense vector search that integrates with services like OpenAI and Jina embeddings and stores vectors in Qdrant, and typo-tolerant full-text/neural search using sparse vector models like efficient-splade. The platform also offers advanced RAG API routes that can utilize OpenRouter for multi-LLM access and includes topic-based memory management for RAG or context-specific generation. Users can bring their own text-embedding, SPLADE, cross-encoder re-ranking, and large-language models (LLMs) to plug into Trieve's infrastructure. Other capabilities include hybrid search with cross-encoder re-ranking, recency biasing, tunable merchandising based on user signals, and various filtering options. Trieve supports grouping multiple data chunks as part of the same file to enable file-level searches, enhancing organization and relevance. It aims to be a complete solution for deploying and managing AI-driven information retrieval systems.
https://github.com/devflowinc/trieve
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.