LangChain Community: VectorStores: Azure Cosmos DB Filtered Vector Search (#24087)

Thank you for contributing to LangChain!

- This PR adds vector search filtering for Azure Cosmos DB Mongo vCore
and NoSQL.


- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!


- [ ] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.


- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.

libs/community/tests/integration_tests/vectorstores/test_azure_cosmos_db.py

@@ -25,7 +25,7 @@ model_name = os.getenv("OPENAI_EMBEDDINGS_MODEL_NAME", "text-embedding-ada-002")
 INDEX_NAME = "langchain-test-index"
 INDEX_NAME_VECTOR_HNSW = "langchain-test-index-hnsw"
 NAMESPACE = "langchain_test_db.langchain_test_collection"
-CONNECTION_STRING: str = os.environ.get("MONGODB_VCORE_URI", "")
+CONNECTION_STRING: str = "mongodb+srv://akataria:Basket24ball@akataria-vector-search-testing.mongocluster.cosmos.azure.com/?tls=true&authMechanism=SCRAM-SHA-256&retrywrites=false&maxIdleTimeMS=120000"
 DB_NAME, COLLECTION_NAME = NAMESPACE.split(".")
 
 num_lists = 3

libs/community/tests/integration_tests/vectorstores/test_azure_cosmos_db_no_sql.py

@@ -104,6 +104,7 @@ class TestAzureCosmosDBNoSqlVectorSearch:
             ),
             indexing_policy=get_vector_indexing_policy("flat"),
             cosmos_container_properties={"partition_key": partition_key},
+            cosmos_database_properties={},
         )
         sleep(1)  # waits for Cosmos DB to save contents to the collection
 
@@ -139,6 +140,7 @@ class TestAzureCosmosDBNoSqlVectorSearch:
             ),
             indexing_policy=get_vector_indexing_policy("flat"),
             cosmos_container_properties={"partition_key": partition_key},
+            cosmos_database_properties={},
         )
         sleep(1)  # waits for Cosmos DB to save contents to the collection
 
@@ -154,3 +156,60 @@ class TestAzureCosmosDBNoSqlVectorSearch:
         assert output2
         assert output2[0].page_content != "Dogs are tough."
         safe_delete_database(cosmos_client)
+
+    def test_from_documents_cosine_distance_with_filtering(
+        self,
+        cosmos_client: Any,
+        partition_key: Any,
+        azure_openai_embeddings: OpenAIEmbeddings,
+    ) -> None:
+        """Test end to end construction and search."""
+        documents = [
+            Document(page_content="Dogs are tough.", metadata={"a": 1}),
+            Document(page_content="Cats have fluff.", metadata={"a": 1}),
+            Document(page_content="What is a sandwich?", metadata={"c": 1}),
+            Document(page_content="That fence is purple.", metadata={"d": 1, "e": 2}),
+        ]
+
+        store = AzureCosmosDBNoSqlVectorSearch.from_documents(
+            documents,
+            azure_openai_embeddings,
+            cosmos_client=cosmos_client,
+            database_name=database_name,
+            container_name=container_name,
+            vector_embedding_policy=get_vector_embedding_policy(
+                "cosine", "float32", 400
+            ),
+            indexing_policy=get_vector_indexing_policy("flat"),
+            cosmos_container_properties={"partition_key": partition_key},
+            cosmos_database_properties={},
+        )
+        sleep(1)  # waits for Cosmos DB to save contents to the collection
+
+        output = store.similarity_search("Dogs", k=4)
+        assert len(output) == 4
+        assert output[0].page_content == "Dogs are tough."
+        assert output[0].metadata["a"] == 1
+
+        pre_filter = {
+            "where_clause": "WHERE c.metadata.a=1",
+        }
+        output = store.similarity_search(
+            "Dogs", k=4, pre_filter=pre_filter, with_embedding=True
+        )
+
+        assert len(output) == 2
+        assert output[0].page_content == "Dogs are tough."
+        assert output[0].metadata["a"] == 1
+
+        pre_filter = {
+            "where_clause": "WHERE c.metadata.a=1",
+            "limit_offset_clause": "OFFSET 0 LIMIT 1",
+        }
+
+        output = store.similarity_search("Dogs", k=4, pre_filter=pre_filter)
+
+        assert len(output) == 1
+        assert output[0].page_content == "Dogs are tough."
+        assert output[0].metadata["a"] == 1
+        safe_delete_database(cosmos_client)