Merge branch 'main' into vector-search-hybrid

langchain-ai · Dec 17, 2024 · fcc7905 · fcc7905
2 parents 961546e + 8c569ed
commit fcc7905
Show file tree

Hide file tree

Showing 5 changed files with 43 additions and 5 deletions.
diff --git a/libs/community/langchain_google_community/bq_storage_vectorstores/bigquery.py b/libs/community/langchain_google_community/bq_storage_vectorstores/bigquery.py
@@ -301,7 +301,7 @@ def _create_search_query(
         if table_to_query is not None:
             embeddings_query = f"""
             with embeddings as (
-            SELECT {self.embedding_field}, ROW_NUMBER() OVER() as row_num
+            SELECT {self.embedding_field}, row_num
             from `{table_to_query}`
             )"""
 
@@ -390,14 +390,16 @@ def _create_temp_bq_table(
         df = pd.DataFrame([])
 
         df[self.embedding_field] = embeddings
+        df["row_num"] = list(range(len(df)))
         table_id = (
             f"{self.project_id}."
             f"{self.temp_dataset_name}."
             f"{self.table_name}_{uuid.uuid4().hex}"
         )
 
         schema = [
-            bigquery.SchemaField(self.embedding_field, "FLOAT64", mode="REPEATED")
+            bigquery.SchemaField(self.embedding_field, "FLOAT64", mode="REPEATED"),
+            bigquery.SchemaField("row_num", "INT64"),
         ]
         table_ref = bigquery.Table(table_id, schema=schema)
         table = self._bq_client.create_table(table_ref)
@@ -483,7 +485,7 @@ def batch_search(
             )
 
         if queries is not None:
-            embeddings = self.embedding.embed_documents(queries)
+            embeddings = [self.embedding.embed_query(query) for query in queries]
 
         if embeddings is None:
             raise ValueError("Could not obtain embeddings - value is None.")

diff --git a/libs/community/langchain_google_community/bq_storage_vectorstores/featurestore.py b/libs/community/langchain_google_community/bq_storage_vectorstores/featurestore.py
@@ -421,6 +421,7 @@ def _search_embedding(
         entity_id: Optional[str] = None,
         k: int = 5,
         string_filters: Optional[List[dict]] = None,
+        numeric_filters: Optional[List[dict]] = None,
         per_crowding_attribute_neighbor_count: Optional[int] = None,
         approximate_neighbor_candidates: Optional[int] = None,
         leaf_nodes_search_fraction: Optional[float] = None,
@@ -438,6 +439,7 @@ def _search_embedding(
             embedding=embedding,
             neighbor_count=k,
             string_filters=string_filters,
+            numeric_filters=numeric_filters,
             per_crowding_attribute_neighbor_count=per_crowding_attribute_neighbor_count,
             parameters={
                 "approximate_neighbor_candidates": approximate_neighbor_candidates,

diff --git a/libs/genai/langchain_google_genai/chat_models.py b/libs/genai/langchain_google_genai/chat_models.py
@@ -1374,7 +1374,11 @@ def create_cached_content(
 
     @property
     def _supports_tool_choice(self) -> bool:
-        return "gemini-1.5-pro" in self.model or "gemini-1.5-flash" in self.model
+        return (
+            "gemini-1.5-pro" in self.model
+            or "gemini-1.5-flash" in self.model
+            or "gemini-2" in self.model
+        )
 
 
 def _get_tool_name(

diff --git a/libs/genai/pyproject.toml b/libs/genai/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langchain-google-genai"
-version = "2.0.6"
+version = "2.0.7"
 description = "An integration package connecting Google's genai package and LangChain"
 authors = []
 readme = "README.md"

diff --git a/libs/genai/tests/integration_tests/test_standard.py b/libs/genai/tests/integration_tests/test_standard.py
@@ -11,6 +11,36 @@
 from langchain_google_genai import ChatGoogleGenerativeAI
 
 rate_limiter = InMemoryRateLimiter(requests_per_second=0.25)
+rate_limiter_2_0 = InMemoryRateLimiter(requests_per_second=0.1)
+
+
+class TestGeminiAI2Standard(ChatModelIntegrationTests):
+    @property
+    def chat_model_class(self) -> Type[BaseChatModel]:
+        return ChatGoogleGenerativeAI
+
+    @property
+    def chat_model_params(self) -> dict:
+        return {
+            "model": "models/gemini-2.0-flash-exp",
+            "rate_limiter": rate_limiter_2_0,
+        }
+
+    @pytest.mark.xfail(reason="with_structured_output with JSON schema not supported.")
+    async def test_structured_output_async(self, model: BaseChatModel) -> None:
+        await super().test_structured_output_async(model)
+
+    @pytest.mark.xfail(reason="with_structured_output with JSON schema not supported.")
+    def test_structured_output(self, model: BaseChatModel) -> None:
+        super().test_structured_output(model)
+
+    @pytest.mark.xfail(reason="with_structured_output with JSON schema not supported.")
+    def test_structured_output_pydantic_2_v1(self, model: BaseChatModel) -> None:
+        super().test_structured_output_pydantic_2_v1(model)
+
+    @pytest.mark.xfail(reason="investigate")
+    def test_bind_runnables_as_tools(self, model: BaseChatModel) -> None:
+        super().test_bind_runnables_as_tools(model)
 
 
 class TestGeminiAIStandard(ChatModelIntegrationTests):