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
Ontos-AI/knowhere
Knowhere is a memory layer between unstructured documents and AI agents. It ingests PDFs, Office files, images, tables, Markdown and plain text and produces persistent, navigable memory rather than a flat pile of chunks: a single pipeline handles parsing, hierarchy extraction, multimodal structuring and graph construction, and every chunk retains the semantic context of where it came from. That context preservation is what makes the output usable for agentic retrieval as well as for conventional vector-based RAG, since an agent can navigate the document structure instead of guessing how isolated fragments relate. The pipeline routes each input to a specialized parser by type, and recent work extends it to very long PDFs of several hundred pages and to atlas-style documents such as technical drawing collections, which get a dedicated layout-aware parser. Retrieval is the second half of the system: once memory is built, agents query it through the platform's API, with hybrid retrieval over the structured and graph representations. The project is written in Python, requires 3.11 or newer, and ships container images; the full stack for document ingestion, parsing and agentic RAG was open-sourced under Apache 2.0, with a separate self-hosted repository for deployment and a dashboard repository for the operator interface. A managed cloud API is offered by the same team for those who do not want to run it. Knowhere targets teams building retrieval over document corpora that defeat naive chunking — regulatory filings, manuals, engineering drawings, scanned reports — where the quality of the parse, not the vector index, is the limiting factor.
https://github.com/Ontos-AI/knowhere
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.