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

docs/components/vectordbs/dbs/neon.mdx

@@ -112,7 +112,7 @@ DATABASE_URL=postgresql://user:password@ep-example.us-east-2.aws.neon.tech/neond
 | `connection_string` | Neon Postgres connection string. | Required |
 | `collection_name` | Name for the vector collection. | `mem0` |
 | `embedding_model_dims` | Embedding model dimensions. | `1536` |
-| `hnsw` | Enables HNSW indexing. | `False` |
+| `hnsw` | Enables HNSW indexing. | `True` |
 | `sslmode` | PostgreSQL SSL mode. Use `require` for Neon. | Driver default |
 </Tab>
 <Tab title="TypeScript">