enhancementhelp wantedsdk-typescriptsize:Lvector-store
Métriques du dépôt
- Stars
- (55 741 stars)
- Métriques de merge PR
- (Merge moyen 6j 11h) (208 PRs mergées en 30 j)
Description
Summary
The Python SDK supports Vertex AI Vector Search as a vector store provider, but the TypeScript OSS SDK (mem0ai/oss) does not. Add it to bring the TS SDK to parity.
| Python reference | mem0/vector_stores/vertex_ai_vector_search.py |
| Registered in (Python) | mem0/utils/factory.py (VectorStoreFactory) |
| Target file (TypeScript) | mem0-ts/src/oss/src/vector_stores/vertex_ai_vector_search.ts |
| Suggested implementation | Use @google-cloud/aiplatform (index + deployed index endpoint). |
Requirements
- Implement
VertexAIVectorSearchinmem0-ts/src/oss/src/vector_stores/vertex_ai_vector_search.ts, extendingVectorStore(mem0-ts/src/oss/src/vector_stores/base.ts) and mirroring the Python provider's behavior (insert / search / get / update / delete / list / reset). - Register the
"vertex_ai_vector_search"provider inmem0-ts/src/oss/src/utils/factory.ts(VectorStoreFactory). - Add config typing in
mem0-ts/src/oss/src/types/. - Add a unit test under
mem0-ts/src/oss/src/tests/. - Add
@google-cloud/aiplatformtomem0-ts/package.json(optional/peer dependency, lazy-imported like other providers). - Update docs under
docs/if this provider is user-facing.
Reference pattern
Mirror an existing TS provider: vector_stores/qdrant.ts.
Notes
Heaviest vector store — requires a created index and a deployed index endpoint. Mirror mem0/vector_stores/vertex_ai_vector_search.py. GCP auth.
Part of the TypeScript ↔ Python SDK provider-parity effort. One provider per issue (atomic).