 kartik-mem0
|
fbb8e71224
|
docs(vectordbs): correct vector store config defaults and imports
Each fix verified against mem0/vector_stores/ source and configs:
- baidu: table_name default mem0_table → mem0 (BaiduDBConfig)
- langchain: TS import mem0ai → mem0ai/oss; fix undefined LangchainVectorStore
variable to use MemoryVectorStore directly
- mongodb: collection_name default mem0_collection → mem0; mongo_uri default
corrected to mongodb://localhost:27017 (MongoDBConfig)
- neon: hnsw default False → True (PGVectorConfig.hnsw = True)
- neptune_analytics: extra name vector_stores → vector-stores (pyproject.toml)
- pgvector: diskann default True → False; hnsw default False → True
(PGVectorConfig)
- upstash-vector: move enable_embeddings inside config: {} block
(UpstashVectorConfig field, not top-level VectorStoreConfig)
- valkey: remove non-existent distance_metric row (not in ValkeyConfig);
fix extra name vector_stores → vector-stores
- vertex_ai: region is required (no default in GoogleMatchingEngineConfig)
- weaviate: install pip install weaviate weaviate-client → weaviate-client
(weaviate is not a separate package)
- overview: update TS supported vector DBs list to reflect actual
mem0-ts/src/oss/src/vector_stores/ files
|
2026-06-25 11:59:37 +05:30 |
|