Qdrant
A vector similarity search engine and vector database. For the things here it is where embedded chunks are stored and searched, running locally beside the process that wrote them or as a server of its own.
Where it sits
Used by
Optionally used: the optional local index is used as the sink; the README states it is intended for development and smaller indexes the vector index the embedded chunks are written to and searched in, the first end-to-end local target the README names
Functional boundary
An early alpha release whose README says to pin the version and test recipes against non-production data first. HANA synchronisation is snapshot-only and does not reconcile deleted rows, so a document for a row deleted in the source stays in the index. A recipe's field allow-list does not decide what the service account may read: the README states that field allow-listing does not replace SAP authorization, and that the package infers no SAP module semantics, authorization scope or safe fields from table names. Only Business Partner has a built-in recipe, every other dataset needs a `KnowledgeRecipe` written for it, and [Qdrant](external:qdrant) local mode is stated to be for development and smaller indexes.
Details
Graph
For your agent
- Ref
external:qdrant- JSON
- /externals/qdrant.json
- MCP
- Connecting an agent