An open-source data framework for connecting LLMs to a team's own documents and data sources - ingestion, indexing and retrieval pipelines - as the plumbing underneath a RAG application.
Visit tool This is mine — claim it
Listing URL: https://www.llamaindex.ai
Show your listing is live — the card backlinks here and picks up the verified badge automatically once you claim it.
<iframe src="https://wingmanprotocol.com/embed/card/llamaindex" width="340" height="170" style="border:0;border-radius:10px" loading="lazy" title="LlamaIndex — live on WingMan Protocol"></iframe>
Or the one-line script:
<script src="https://wingmanprotocol.com/embed/card.js" data-slug="llamaindex" async></script>
Or a README badge:
[](https://wingmanprotocol.com/directory/llamaindex?utm_source=badge)
An open-source embedding database built specifically for AI application developers - lightweight to run locally during development, with a hosted version for pr
A managed vector database built for similarity search at scale - the retrieval half of most RAG pipelines - so teams don't have to run and tune their own vector
An open-source vector database and search engine written for high-performance similarity search, offered self-hosted or as a managed cloud service for RAG and r
An end-to-end RAG-as-a-service platform: send it documents and it handles chunking, embedding, retrieval and grounded answer generation through one API, instead
An open-source vector database supporting hybrid (keyword + vector) search, usable self-hosted or as a managed cloud service, aimed at semantic search and RAG a
A fully managed cloud service for Milvus, an open-source vector database built for very large-scale similarity search, so teams get Milvus without operating the