docs(vectorstores): normalize and fix links, and correct examples

pipeline/preprocessors/link_map.py

@@ -181,10 +181,12 @@ class LinkMap(TypedDict):
             # Embeddings
             "init_embeddings": "langchain/embeddings/base/init_embeddings",
             "Embeddings": "langchain-core/embeddings/embeddings/Embeddings",
+            "PineconeSparseEmbeddings": "langchain-pinecone/embeddings/PineconeSparseEmbeddings",
             # Documents
             "Document": "langchain-core/documents/base/Document",
             # Document loaders
             "BaseLoader": "langchain-core/document_loaders/base/BaseLoader",
+            "AzureBlobStorageContainerLoader": "langchain-community/document_loaders/azure_blob_storage_container/AzureBlobStorageContainerLoader",
             # Text splitters
             "CharacterTextSplitter": "langchain-text-splitters/character/CharacterTextSplitter",
             "RecursiveCharacterTextSplitter": "langchain-text-splitters/character/RecursiveCharacterTextSplitter",
@@ -199,6 +201,23 @@ class LinkMap(TypedDict):
             # VectorStores
             "VectorStore": "langchain-core/vectorstores/base/VectorStore",
             "VectorStore.max_marginal_relevance_search": "langchain-core/vectorstores/base/VectorStore/max_marginal_relevance_search",
+            "PGVector": "langchain-postgres/vectorstores/PGVector",
+            "PGVectorStore": "langchain-postgres/v2/vectorstores/PGVectorStore",
+            "AstraDBVectorStore": "langchain-astradb/vectorstores/AstraDBVectorStore",
+            "ChromaVectorStore": "langchain-chroma/vectorstores/Chroma",
+            "ClickhouseVectorStore": "langchain-community/vectorstores/Clickhouse",
+            "ElasticSearchStore": "langchain-elasticsearch/vectorstores/ElasticsearchStore",
+            "FAISSVectorStore": "langchain-community/vectorstores/FAISS",
+            "FalkorDBVector": "langchain-community/vectorstores/FalkorDBVector",
+            "MilvusVectorStore": "langchain-milvus/vectorstores/milvus/Milvus",
+            "MongoDBAtlasVectorSearch": "langchain-mongodb/vectorstores/MongoDBAtlasVectorSearch",
+            "PineconeSparseVectorStore": "langchain-pinecone/vectorstores_sparse/PineconeSparseVectorStore",
+            "PineconeVectorStore": "langchain-pinecone/vectorstores/PineconeVectorStore",
+            "QdrantVectorStore": "langchain-qdrant/qdrant/QdrantVectorStore",
+            "SQLiteVec": "langchain-community/vectorstores/SQLiteVec",
+            "SQLServer_VectorStore": "langchain-sqlserver/vectorstores/SQLServer_VectorStore",
+            "SurrealDBStore": "langchain-community/vectorstores/surrealdb/SurrealDBStore",
+            "TablestoreVectorStore": "langchain-community/vectorstores/TablestoreVectorStore",
             # Key-value stores
             "BaseStore": "langchain-core/stores/BaseStore",
             "BaseStore.put": "langgraph/store/#langgraph.store.base.BaseStore.put",

src/oss/python/integrations/vectorstores/alibabacloud_mysql.mdx

@@ -354,9 +354,9 @@ response = agent.invoke({"messages": [{"role": "user", "content": "What is task
 
 For more RAG guides and patterns, see:
 
+- [Retrieval docs](/oss/langchain/retrieval)
 - [Build a RAG app with LangChain](/oss/langchain/rag)
 - [Agentic RAG](/oss/langgraph/agentic-rag)
-- [Retrieval docs](/oss/langchain/retrieval)
 
 For detailed RAG demo with Alibaba Cloud MySQL and more examples, see:
 

src/oss/python/integrations/vectorstores/astradb.mdx

@@ -81,7 +81,7 @@ Astra DB vector stores support metadata search in vector searches; furthermore,
 
 #### Additional information
 
-The `AstraDBVectorStore` can be configured in many ways; see the [API Reference](https://python.langchain.com/api_reference/astradb/vectorstores/langchain_astradb.vectorstores.AstraDBVectorStore.html) for a full guide covering e.g. asynchronous initialization; non-Astra-DB databases; custom indexing allow-/deny-lists; manual hybrid-search control; and much more.
+The `AstraDBVectorStore` can be configured in many ways; see the @[API reference][AstraDBVectorStore] for a full guide covering e.g. asynchronous initialization; non-Astra-DB databases; custom indexing allow-/deny-lists; manual hybrid-search control; and much more.
 
 ### Explicit embedding initialization (method 1)
 
@@ -352,7 +352,7 @@ _The above example hardcodes the "autodetected" vector store, which has surely i
 
 There are a variety of other search methods that are not covered in this notebook, such as MMR search and search by vector.
 
-For a full list of the search modes available in `AstraDBVectorStore` check out the [API reference](https://python.langchain.com/api_reference/astradb/vectorstores/langchain_astradb.vectorstores.AstraDBVectorStore.html).
+For a full list of the search modes available in `AstraDBVectorStore` check out the @[API reference][AstraDBVectorStore].
 
 ### Query by turning into retriever
 
@@ -376,9 +376,9 @@ retriever.invoke("Stealing from the bank is a crime", filter={"source": "news"})
 
 For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:
 
-- [Tutorials](/oss/langchain/rag)
-- [How-to: Question and answer with RAG](https://python.langchain.com/docs/how_to/#qa-with-rag)
-- [Retrieval conceptual docs](https://python.langchain.com/docs/concepts/retrieval)
+- [Retrieval docs](/oss/langchain/retrieval)
+- [Build a RAG app with LangChain](/oss/langchain/rag)
+- [Agentic RAG](/oss/langgraph/agentic-rag)
 
 For more, check out a complete RAG template using Astra DB [here](https://github.com/langchain-ai/langchain/tree/master/templates/rag-astradb).
 
@@ -396,4 +396,4 @@ vector_store.delete_collection()
 
 ## API reference
 
-For detailed documentation of all `AstraDBVectorStore` features and configurations, consult the [API reference](https://python.langchain.com/api_reference/astradb/vectorstores/langchain_astradb.vectorstores.AstraDBVectorStore.html).
+For detailed documentation of all `AstraDBVectorStore` features and configurations, consult the @[API reference][AstraDBVectorStore].

src/oss/python/integrations/vectorstores/azure_db_for_postgresql.mdx

@@ -443,9 +443,9 @@ For a full list of the different searches you can execute on a `AzurePGVectorSto
 
 For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:
 
-* [Tutorials: working with external knowledge](https://python.langchain.com/docs/tutorials/#working-with-external-knowledge)
-* [How-to: Question and answer with RAG](https://python.langchain.com/docs/how_to/#qa-with-rag)
-* [Retrieval conceptual docs](https://python.langchain.com/docs/concepts/#retrieval)
+- [Retrieval docs](/oss/langchain/retrieval)
+- [Build a RAG app with LangChain](/oss/langchain/rag)
+- [Agentic RAG](/oss/langgraph/agentic-rag)
 
 ## API reference
 

src/oss/python/integrations/vectorstores/chroma.mdx

@@ -5,7 +5,7 @@ description: "Integrate with the Chroma vector store using LangChain Python."
 
 This notebook covers how to get started with the `Chroma` vector store.
 
->[Chroma](https://docs.trychroma.com/getting-started) is a AI-native open-source vector database focused on developer productivity and happiness. Chroma is licensed under Apache 2.0. View the full docs of `Chroma` at [this page](https://docs.trychroma.com/reference/py-collection), and find the API reference for the LangChain integration at [this page](https://python.langchain.com/api_reference/chroma/vectorstores/langchain_chroma.vectorstores.Chroma.html).
+>[Chroma](https://docs.trychroma.com/getting-started) is a AI-native open-source vector database focused on developer productivity and happiness. Chroma is licensed under Apache 2.0. View the full docs of `Chroma` at [this page](https://docs.trychroma.com/reference/py-collection), and find the API reference for the LangChain integration at [this page](https://reference.langchain.com/python/langchain-chroma/vectorstores/Chroma).
 
 <Info>
 **Chroma Cloud**
@@ -346,11 +346,11 @@ for doc in results:
 
 #### Other search methods
 
-There are a variety of other search methods that are not covered in this notebook, such as MMR search. For a full list of the search abilities available for `Chroma` check out the [API reference](https://python.langchain.com/api_reference/chroma/vectorstores/langchain_chroma.vectorstores.Chroma.html).
+There are a variety of other search methods that are not covered in this notebook, such as MMR search. For a full list of the search abilities available for `Chroma` check out the @[API reference][ChromaVectorStore].
 
 ### Query by turning into retriever
 
-You can also transform the vector store into a retriever for easier usage in your chains. For more information on the different search types and kwargs you can pass, please visit the API reference [here](https://python.langchain.com/api_reference/chroma/vectorstores/langchain_chroma.vectorstores.Chroma.html#langchain_chroma.vectorstores.Chroma.as_retriever).
+You can also transform the vector store into a retriever for easier usage in your chains. For more information on the different search types and kwargs you can pass, please visit the API reference [here](https://reference.langchain.com/python/langchain-chroma/vectorstores/Chroma#langchain_chroma.vectorstores.Chroma.as_retriever).
 
 ```python
 retriever = vector_store.as_retriever(
@@ -363,12 +363,12 @@ retriever.invoke("Stealing from the bank is a crime", filter={"source": "news"})
 
 For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:
 
-- [Tutorials](/oss/langchain/rag)
-- [How-to: Question and answer with RAG](https://python.langchain.com/docs/how_to/#qa-with-rag)
-- [Retrieval conceptual docs](https://python.langchain.com/docs/concepts/retrieval)
+- [Retrieval docs](/oss/langchain/retrieval)
+- [Build a RAG app with LangChain](/oss/langchain/rag)
+- [Agentic RAG](/oss/langgraph/agentic-rag)
 
 ---
 
 ## API reference
 
-For detailed documentation of all `Chroma` vector store features and configurations head to the API reference: [python.langchain.com/api_reference/chroma/vectorstores/langchain_chroma.vectorstores.Chroma.html](https://python.langchain.com/api_reference/chroma/vectorstores/langchain_chroma.vectorstores.Chroma.html)
+For detailed documentation of all `Chroma` vector store features and configurations head to the @[API reference][ChromaVectorStore]

src/oss/python/integrations/vectorstores/clickhouse.mdx

@@ -189,7 +189,7 @@ for res in results:
 
 #### Other search methods
 
-There are a variety of other search methods that are not covered in this notebook, such as MMR search or searching by vector. For a full list of the search abilities available for `Clickhouse` vector store check out the [API reference](https://python.langchain.com/api_reference/community/vectorstores/langchain_community.vectorstores.clickhouse.Clickhouse.html).
+There are a variety of other search methods that are not covered in this notebook, such as MMR search or searching by vector. For a full list of the search abilities available for `Clickhouse` vector store check out the @[API reference][ClickhouseVectorStore].
 
 ### Query by turning into retriever
 
@@ -209,14 +209,14 @@ retriever.invoke("Stealing from the bank is a crime", filter={"source": "news"})
 
 For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:
 
-- [Tutorials](/oss/langchain/rag)
-- [How-to: Question and answer with RAG](https://python.langchain.com/docs/how_to/#qa-with-rag)
-- [Retrieval conceptual docs](https://python.langchain.com/docs/concepts/retrieval)
+- [Retrieval docs](/oss/langchain/retrieval)
+- [Build a RAG app with LangChain](/oss/langchain/rag)
+- [Agentic RAG](/oss/langgraph/agentic-rag)
 
 For more, check out a complete RAG template using Astra DB [here](https://github.com/langchain-ai/langchain/tree/master/templates/rag-astradb).
 
 ---
 
 ## API reference
 
-For detailed documentation of all `Clickhouse` features and configurations head to the [API reference](https://python.langchain.com/api_reference/community/vectorstores/langchain_community.vectorstores.clickhouse.Clickhouse.html).
+For detailed documentation of all `Clickhouse` features and configurations head to the [API reference](https://reference.langchain.com/python/langchain-community/vectorstores/Clickhouse).

src/oss/python/integrations/vectorstores/couchbase.mdx

@@ -824,9 +824,9 @@ Similarly, you can use any of the supported Query methods like Geo Distance, Pol
 
 For guides on how to use these vector stores for retrieval-augmented generation (RAG), see the following sections:
 
-- [Tutorials](/oss/langchain/rag)
-- [How-to: Question and answer with RAG](https://python.langchain.com/docs/how_to/#qa-with-rag)
-- [Retrieval conceptual docs](https://python.langchain.com/docs/concepts/retrieval)
+- [Retrieval docs](/oss/langchain/retrieval)
+- [Build a RAG app with LangChain](/oss/langchain/rag)
+- [Agentic RAG](/oss/langgraph/agentic-rag)
 
 ---
 

src/oss/python/integrations/vectorstores/databricks_vector_search.mdx

@@ -238,12 +238,12 @@ retriever.invoke("thud")
 
 For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:
 
-* [Tutorials](/oss/langchain/rag)
-* [How-to: Question and answer with RAG](https://python.langchain.com/docs/how_to/#qa-with-rag)
-* [Retrieval conceptual docs](https://python.langchain.com/docs/concepts/retrieval)
+- [Retrieval docs](/oss/langchain/retrieval)
+- [Build a RAG app with LangChain](/oss/langchain/rag)
+- [Agentic RAG](/oss/langgraph/agentic-rag)
 
 ---
 
 ## API reference
 
-For detailed documentation of all DatabricksVectorSearch features and configurations head to the API reference: [api-docs.databricks.com/python/databricks-ai-bridge/latest/databricks_langchain.html#databricks_langchain.DatabricksVectorSearch](https://api-docs.databricks.com/python/databricks-ai-bridge/latest/databricks_langchain.html#databricks_langchain.DatabricksVectorSearch)
+For detailed documentation of all DatabricksVectorSearch features and configurations head to the [API reference](https://api-docs.databricks.com/python/databricks-ai-bridge/latest/databricks_langchain.html#databricks_langchain.DatabricksVectorSearch)

src/oss/python/integrations/vectorstores/elasticsearch.mdx

@@ -634,9 +634,9 @@ print(results[0])
 
 For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:
 
-- [Tutorials](/oss/langchain/rag)
-- [How-to: Question and answer with RAG](https://python.langchain.com/docs/how_to/#qa-with-rag)
-- [Retrieval conceptual docs](https://python.langchain.com/docs/concepts/retrieval)
+- [Retrieval docs](/oss/langchain/retrieval)
+- [Build a RAG app with LangChain](/oss/langchain/rag)
+- [Agentic RAG](/oss/langgraph/agentic-rag)
 
 # FAQ
 
@@ -744,4 +744,4 @@ db.client.indices.delete(
 
 ## API reference
 
-For detailed documentation of all `ElasticSearchStore` features and configurations head to the API reference: [python.langchain.com/api_reference/elasticsearch/vectorstores/langchain_elasticsearch.vectorstores.ElasticsearchStore.html](https://python.langchain.com/api_reference/elasticsearch/vectorstores/langchain_elasticsearch.vectorstores.ElasticsearchStore.html)
+For detailed documentation of all `ElasticSearchStore` features and configurations head to the @[API reference][ElasticSearchStore]

src/oss/python/integrations/vectorstores/faiss.mdx

@@ -228,7 +228,7 @@ for res, score in results:
 
 #### Other search methods
 
-There are a variety of other ways to search a FAISS vector store. For a complete list of those methods, please refer to the [API Reference](https://python.langchain.com/api_reference/community/vectorstores/langchain_community.vectorstores.faiss.FAISS.html)
+There are a variety of other ways to search a FAISS vector store. For a complete list of those methods, please refer to the @[API Reference][FAISSVectorStore]
 
 ### Query by turning into retriever
 
@@ -247,9 +247,9 @@ retriever.invoke("Stealing from the bank is a crime", filter={"source": "news"})
 
 For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:
 
-- [Tutorials](/oss/langchain/rag)
-- [How-to: Question and answer with RAG](https://python.langchain.com/docs/how_to/#qa-with-rag)
-- [Retrieval conceptual docs](https://python.langchain.com/docs/concepts/retrieval)
+- [Retrieval docs](/oss/langchain/retrieval)
+- [Build a RAG app with LangChain](/oss/langchain/rag)
+- [Agentic RAG](/oss/langgraph/agentic-rag)
 
 ## Saving and loading
 
@@ -313,4 +313,4 @@ db1.docstore._dict
 
 ## API reference
 
-For detailed documentation of all `FAISS` vector store features and configurations head to the API reference: [python.langchain.com/api_reference/community/vectorstores/langchain_community.vectorstores.faiss.FAISS.html](https://python.langchain.com/api_reference/community/vectorstores/langchain_community.vectorstores.faiss.FAISS.html)
+For detailed documentation of all `FAISS` vector store features and configurations head to the @[API Reference][FAISSVectorStore]

src/oss/python/integrations/vectorstores/falkordbvector.mdx

@@ -159,4 +159,4 @@ retriever.invoke("thud")
 
 ## API reference
 
-For detailed documentation of all `FalkorDBVector` features and configurations head to the API reference: [python.langchain.com/api_reference/community/vectorstores/langchain_community.vectorstores.falkordb_vector.FalkorDBVector.html](https://python.langchain.com/api_reference/community/vectorstores/langchain_community.vectorstores.falkordb_vector.FalkorDBVector.html)
+For detailed documentation of all `FalkorDBVector` features and configurations head to the @[API reference][FalkorDBVector]

src/oss/python/integrations/vectorstores/gel.mdx

@@ -242,12 +242,12 @@ retriever.invoke("kitty")
 
 For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:
 
+- [Retrieval docs](/oss/langchain/retrieval)
 - [Build a RAG app with LangChain](/oss/langchain/rag)
 - [Agentic RAG](/oss/langgraph/agentic-rag)
-- [Retrieval docs](/oss/langchain/retrieval)
 
 ---
 
 ## API reference
 
-For detailed documentation of all GelVectorStore features and configurations head to the API reference: [python.langchain.com/api_reference/](https://python.langchain.com/api_reference/)
+For detailed documentation of all GelVectorStore features and configurations head to the [GitHub docs](https://github.com/geldata/langchain-gel)

src/oss/python/integrations/vectorstores/google_bigtable.mdx

@@ -373,9 +373,9 @@ print(retrieved_docs[0].page_content)
 
 For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:
 
-- [Tutorials](https://python.langchain.com/docs/tutorials/rag/)
-- [How-to: Question and answer with RAG](https://python.langchain.com/docs/how_to/#qa-with-rag)
-- [Retrieval conceptual docs](https://python.langchain.com/docs/concepts/retrieval/)
+- [Retrieval docs](/oss/langchain/retrieval)
+- [Build a RAG app with LangChain](/oss/langchain/rag)
+- [Agentic RAG](/oss/langgraph/agentic-rag)
 
 ## API reference
 

src/oss/python/integrations/vectorstores/index.mdx

@@ -671,7 +671,7 @@ uv add langchain-postgres
 ```python
 from langchain_postgres import PGEngine, PGVectorStore
 
-$engine = PGEngine.from_connection_string(
+pg_engine = PGEngine.from_connection_string(
     url="postgresql+psycopg://..."
 )
 
@@ -802,7 +802,7 @@ vector_store = TurbopufferVectorStore(embedding=embeddings, namespace=ns)
 | [`DatabricksVectorSearch`](/oss/integrations/vectorstores/databricks_vector_search) | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ |
 | [`ElasticsearchStore`](/oss/integrations/vectorstores/elasticsearch) | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ |
 | [`FAISS`](/oss/integrations/vectorstores/faiss) | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ |
-| [`InMemoryVectorStore`](https://python.langchain.com/api_reference/core/vectorstores/langchain_core.vectorstores.in_memory.InMemoryVectorStore.html) | ✅ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ✅ |
+| [`InMemoryVectorStore`](https://reference.langchain.com/python/langchain-core/vectorstores/in_memory/InMemoryVectorStoree) | ✅ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ✅ |
 | [`LambdaDB`](/oss/integrations/vectorstores/lambdadb) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ |
 | [`Milvus`](/oss/integrations/vectorstores/milvus) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
 | [`Moorcheh`](/oss/integrations/vectorstores/moorcheh) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |

src/oss/python/integrations/vectorstores/lindorm.mdx

@@ -136,9 +136,9 @@ for doc, score in results:
 
 For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:
 
+- [Retrieval docs](/oss/langchain/retrieval)
 - [Build a RAG app with LangChain](/oss/langchain/rag)
 - [Agentic RAG](/oss/langgraph/agentic-rag)
-- [Retrieval docs](/oss/langchain/retrieval)
 
 ---