integration: adding Azure Database for PostgreSQL example notebook

[AbeOmor]

Overview

Description: Added vector store and memory usage documentation for Azure Database for PostgreSQL using our NEW LangChain/LangGraph connector

This PR to show support for the Azure Database for PostgreSQL Vector Store and pgVector in a Notebook

Azure Database for PostgreSQL - Flexible Server
Azure Database for PostgreSQL pgvector extension

Issue: Last PR was closed because we didn't have a LangChain package of Azure Postgres #27129. We just release one this month: https://pypi.org/project/langchain-azure-postgresql/

Twitter handle: @_aiabe

Type of change

New documentation page

Related issues/PRs

• See docs(langchain): adding Azure Database for PostgreSQL example notebook langchain#32927

Checklist

• I have read the contributing guidelines
• I have tested my changes locally using docs dev
• All code examples have been tested and work correctly
• I have used root relative paths for internal links
• I have updated navigation in src/docs.json if needed
• I have gotten approval from the relevant reviewers

Additional notes

This was already reviewed by @ccurme, @mdrxy and @Kpreya in the LangChain repo. I was asked to move to this repo.

[vercel]

@AbeOmor is attempting to deploy a commit to the LangChain Team on Vercel.

A member of the Team first needs to authorize it.

[Copilot]

Pull Request Overview

This PR adds comprehensive documentation for the Azure Database for PostgreSQL vector store integration by introducing a new notebook demonstrating vector storage and memory usage capabilities using the newly released LangChain Azure PostgreSQL connector package.

• Adds a new documentation page for Azure Database for PostgreSQL - Flexible Server vector store
• Updates the vector stores index to include the new Azure PostgreSQL integration
• Demonstrates both Microsoft Entra authentication and password-based authentication methods

Reviewed Changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File	Description
src/oss/python/integrations/vectorstores/index.mdx	Adds navigation card for the new Azure Database for PostgreSQL integration and reorganizes Azure service cards
src/oss/python/integrations/vectorstores/azure_db_for_postgresql.mdx	New comprehensive documentation page covering setup, authentication, vector operations, and usage examples for Azure PostgreSQL vector store

[Copilot]

Pull Request Overview

Copilot reviewed 2 out of 2 changed files in this pull request and generated no new comments.

[Copilot]

Pull Request Overview

Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.

[Copilot]

The href path appears incorrect. The original line referenced '/oss/integrations/vectorstores/azure_cosmos_db_mongo_vcore' but the new path is '/oss/integrations/vectorstores/azure_cosmos_db'. Verify this path change is intentional and that the corresponding file exists at this location.

Suggested change

	<Card title="Azure Cosmos DB Mongo vCore" icon="link" href="/oss/integrations/vectorstores/azure_cosmos_db" arrow="true" cta="View guide"/>
	<Card title="Azure Cosmos DB Mongo vCore" icon="link" href="/oss/integrations/vectorstores/azure_cosmos_db_mongo_vcore" arrow="true" cta="View guide"/>

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Preview	Comments	Updated (UTC)
reference-docs	Canceled			Oct 24, 2025 5:03pm

[Copilot]

Pull Request Overview

Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.

[Copilot]

This statement is misleading. The documentation then proceeds to use the langchain-azure-postgresql package exclusively, not LangChain's standard Postgres support. Consider revising to: 'Azure Database for PostgreSQL is based on open-source Postgres. This integration uses the dedicated langchain-azure-postgresql package which provides optimized support including DiskANN indexing and Microsoft Entra authentication.'

Suggested change

	Since Azure Database for PostgreSQL is open-source Postgres, you can use [LangChain's Postgres support](https://python.langchain.com/docs/integrations/vectorstores/pgvector/) to connect to Azure Database for PostgreSQL.
	Azure Database for PostgreSQL is based on open-source Postgres. This integration uses the dedicated [`langchain-azure-postgresql`](https://pypi.org/project/langchain-azure-postgresql/) package, which provides optimized support including DiskANN indexing and Microsoft Entra authentication.

[Copilot]

The azure-identity package is only required when using Microsoft Entra authentication. Consider adding a note that this dependency is optional for password-based authentication, or restructure the installation instructions to clarify when each package is needed.

Suggested change

	First download the partner package:
	```python
	%pip install -qU langchain-azure-postgresql
	%pip install -qU langchain-openai
	First download the partner packages:
	```python
	%pip install -qU langchain-azure-postgresql
	%pip install -qU langchain-openai

If you plan to use Microsoft Entra authentication, you will also need to install the azure-identity package:

[Copilot]

These output messages suggest that parameters can be explicitly specified to override defaults, but the documentation doesn't explain how to configure these options (metadata type, embedding dimension, index type, etc.). Consider adding a section or note explaining these configuration options, especially since DiskANN indexing is highlighted as a key feature.

Suggested change

	## Configuring Vector Store Parameters
	You can override the default parameters for metadata type, embedding dimension, index type, and more when initializing `AzurePGVectorStore`. This allows you to tailor the vector store to your specific use case and data.
	**Key configuration options:**
	- `metadata_column_type`: The type of the metadata column (default: `'jsonb'`). Set to `'jsonb'`, `'text'`, etc.
	- `embedding_column_type`: The type of the embedding column (default: `'vector'`).
	- `embedding_dimension`: The dimension of your embedding vectors (default: `1536`).
	- `embedding_index_type`: The index type for vector search (default: `'DiskANN'`). Other options may include `'ivfflat'`, `'hnsw'`, etc.
	- `embedding_index_opclass`: The operator class for the index (default: `'vector_cosine_ops'`).
	**Example:**
	```python
	vector_store = AzurePGVectorStore(
	embedding=embeddings,
	table_name=table_name,
	connection=connection,
	metadata_column_type="jsonb", # or "text"
	embedding_column_type="vector",
	embedding_dimension=768, # set to match your model's output
	embedding_index_type="DiskANN", # or "ivfflat", "hnsw", etc.
	embedding_index_opclass="vector_cosine_ops", # or "vector_l2_ops", etc.
	)

For a full list of options and their defaults, refer to the AzurePGVectorStore API reference.