{"ref":"artifact:mi8y-cap-agents-cds-vectorstore","page":"/artifacts/mi8y-cap-agents-cds-vectorstore","json":"/artifacts/mi8y-cap-agents-cds-vectorstore.json","generated":"2026-10-26","drafted_with_ai":true,"entity":{"id":"mi8y-cap-agents-cds-vectorstore","name":"@mi8y/cap-agents-cds-vectorstore","artifact_type":"package","ecosystem":"cap","domain":"ai-and-agents","origin_ring":"independent","description":{"one_line":"A LangChain vector store whose documents and embeddings are CDS entities, so retrieval runs as a CDS query against the database the CAP service is already bound to.","short":"LangChain vector store with CDS entities for embeddings","what_it_solves":"Retrieval inside a CAP application has to put the chunks and their embeddings somewhere, and LangChain's retrieval APIs expect a `VectorStore` behind them. `CDSVectorStore` is that implementation over CDS: `cds add agent-cds-vectorstore` generates `Documents` and `DocumentMetadata` entities in the `plugin.langchain.vectorstore` namespace with a `Vector(1536)` embedding sized for `text-embedding-3-small`, and both are aspects, so a project that wants a second store or another dimension declares its own entities and passes their names to the constructor. `similaritySearch`, `similaritySearchWithScore`, `maxMarginalRelevanceSearch` and `asRetriever` are the read side, with cosine similarity, a threshold that defaults to 0.75, and metadata filters over direct equality, `$eq`, `$ne`, `$in` and `$notIn`. Turning text into a vector is the caller's: an `Embeddings` implementation is passed to the constructor, and nothing here splits a long document into chunks."},"links":{"npm":"https://www.npmjs.com/package/@mi8y/cap-agents-cds-vectorstore","repo":"https://github.com/mi8y/cap-agents-addons/tree/main/packages/cap-agents-cds-vectorstore"},"identity":{"license":"MIT"},"compat":{"runtimes":["node"],"cds_range":">=10","typed":true},"provides":[{"capability":"capability:retrieval-augmented-generation","what_it_does":"Holds chunks, their embeddings and their metadata as CDS entities in the application's own database, and retrieves them by cosine similarity through the LangChain vector store interface.","sources":[{"url":"https://github.com/mi8y/cap-agents-addons/tree/main/packages/cap-agents-cds-vectorstore","title":"@mi8y/cap-agents-cds-vectorstore — README","checked":"2026-09-21","quote":"This package gives you a `VectorStore` implementation backed by CAP CDS entities, so you can store embeddings and documents in your CAP application's database and use standard LangChain retrieval APIs for RAG and semantic search."},{"url":"https://github.com/mi8y/cap-agents-addons/tree/main/packages/cap-agents-cds-vectorstore","title":"@mi8y/cap-agents-cds-vectorstore — README, Notes","checked":"2026-09-21","quote":"The package uses cosine similarity for retrieval."}]}],"provenance":{"discovered_via":[{"source":"source:curator"}],"first_seen":"2026-09-21"},"maintainers":["actor:anselm94","actor:mi8y"],"contributors":["actor:anselm94"],"drafted_with_ai":true},"effective_normative_relations":[],"readings":{"liveness":[{"label":"Maintenance","tier":"good","evidence":"1 month since release"},{"label":"Continuity","tier":"good","evidence":"3 contributors, 2 publishers, org-owned"},{"label":"Repository","tier":"good","evidence":"pushed 2026-10, not archived"}],"compatibility":[{"label":"Declared for","tier":"good","evidence":">=10 — includes cds 10"},{"label":"Survived majors","tier":"unknown","evidence":"first released after @sap/cds 10 shipped"},{"label":"Maintainer's CI","tier":"good","evidence":"release green, 2026-10-21"}],"practice":[{"label":"Tests","tier":"good","evidence":"24 test files, npm test"},{"label":"Docs","tier":"good","evidence":"docs/ with 1 page, README 7 KB"},{"label":"Changelog","tier":"fair","evidence":"none in the repo"}],"reach":[{"value":11,"unit":"installs/week"},{"value":2,"unit":"watching"}]},"signals":{"crawled_at":"2026-10-26","latest_version":"0.2.0","majors":{"0.2":{"version":"0.2.0","date":"2026-09-17"}},"license":"MIT","first_release":"2026-09-17","last_release":"2026-09-17","releases":1,"cadence_days":null,"maintainers":2,"repository":"git+https://github.com/mi8y/cap-agents-plugins.git","repository_directory":null,"peer_cds":">=10","test_script":true,"types":true,"downloads_weekly":11,"stars":2,"forks":0,"open_issues":2,"archived":false,"pushed_at":"2026-10-21","license_spdx":"MIT","org_owned":true,"default_branch":"main","contributors":3,"tree_truncated":false,"test_files":24,"workflows":3,"other_ci":false,"readme_bytes":6903,"docs_files":1,"changelog":false,"license_file":true,"dts_files":0,"first_commit":"2026-09-08","last_commit":"2026-10-09","commits":9,"ci_status":"success","ci_run_at":"2026-10-21","ci_workflow":"release","ci_event":"push","readme_path":"packages/cap-agents-cds-vectorstore/README.md","readme_sha":"3c0c5429ae1271e0f7d749b075df6dc27f0a3d24","months_since_release":1,"dormant":false,"dependencies":1,"node_engine":null,"downloads_monthly":42,"created_at":"2026-07-08T05:15:34Z","open_prs":1,"repo_read":"2026-10-26"},"release_notes":{"license":"MIT","quotable":true,"source":{"kind":"repo","path":"packages/cap-agents-cds-vectorstore/CHANGELOG.md","ref":"main","url":"https://github.com/mi8y/cap-agents-addons/blob/main/packages/cap-agents-cds-vectorstore/CHANGELOG.md"},"format":"changesets","releases":[{"version":"0.2.0","date":"2026-09-17","date_source":"registry","heading":"0.2.0","url":"https://github.com/mi8y/cap-agents-addons/blob/main/packages/cap-agents-cds-vectorstore/CHANGELOG.md#020","sections":[{"kind":"feature","heading":"Minor Changes","items":1}],"hash":"f13bc5869da4b763"}],"versions":[{"version":"0.2.0","date":"2026-09-17"}],"crawled_at":"2026-10-25"},"edges":{"maintainers":[{"ref":"actor:anselm94","name":"Merbin J Anselm","json":"/actors/anselm94.json"},{"ref":"actor:mi8y","name":"Mi8Y Technologies","json":"/actors/mi8y.json"}],"contributors":[{"ref":"actor:anselm94","name":"Merbin J Anselm","json":"/actors/anselm94.json"}],"explained_by":[],"alternative_to_this":[],"needed_by":[],"available_via":[],"parts":[],"add_ons":[],"answered_through_parts":[]}}