feat(vertex): add additional args for vertex ai vector search (#1198)

<!--
# Thank you for contributing to LangChain-google!
-->

<!--
## Checklist for PR Creation

- [x] PR Title: "<type>[optional scope]: <description>"

- Where type is one of: feat, fix, docs, style, refactor, perf, test,
build, ci, chore, revert, release
- Scope is used to specifiy the package targeted. Options are: genai,
vertex, community, infra (repo-level)

- [x] PR Description and Relevant issues:

 fix issue #1197

- [ ] Add Tests and Docs:

  - If adding a new integration:
1. Include a test for the integration (preferably unit tests that do not
rely on network access)
2. Add an example notebook showing its use (place in the
`docs/docs/integrations` directory)

- [x] 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://github.com/langchain-ai/langchain-google/blob/main/README.md#contribute-code
-->

<!--
## Additional guidelines

- [ ] PR title and description are appropriate
- [ ] Necessary tests and documentation have been added
- [ ] Lint and tests pass successfully
- [ ] The following additional guidelines are adhered to:
  - Optional dependencies are imported within functions
- No unnecessary dependencies added to pyproject.toml files (except
those required for unit tests)
  - PR doesn't touch more than one package
  - Changes are backwards compatible
-->

## Description

<!-- e.g. "Implement user authentication feature" -->

## Relevant issues
fixes #1197 
<!-- e.g. "Fixes #000" -->

## Type

<!-- Select the type of Pull Request -->
<!-- Keep only the necessary ones -->

🆕 New Feature
🐛 Bug Fix
🧹 Refactoring
📖 Documentation
🚄 Infrastructure
✅ Test

## Changes(optional)

<!-- List of changes -->

## Testing(optional)

<!-- Test procedure -->
<!-- Test result -->

## Note(optional)

<!-- Information about the errors fixed by PR -->
<!-- Remaining issue or something -->
<!-- Other information about PR -->

Author: wadave

libs/vertexai/langchain_google_vertexai/vectorstores/_searcher.py

@@ -39,6 +39,7 @@ def find_neighbors(
             List[Dict[str, Union[List[int], List[float]]]]
         ] = None,
         rrf_ranking_alpha: float = 1,
+        **kwargs: Any,
     ) -> List[List[Dict[str, Any]]]:
         """Finds the k closes neighbors of each instance of embeddings.
 
@@ -249,6 +250,7 @@ def find_neighbors(
             List[Dict[str, Union[List[int], List[float]]]]
         ] = None,
         rrf_ranking_alpha: float = 1,
+        **kwargs: Any,
     ) -> List[List[Dict[str, Any]]]:
         """Finds the k closes neighbors of each instance of embeddings.
 
@@ -304,6 +306,7 @@ def find_neighbors(
                 num_neighbors=k,
                 filter=filter_,
                 numeric_filter=numeric_filter,
+                **kwargs,
             )
 
         return self._postprocess_response(response)

libs/vertexai/langchain_google_vertexai/vectorstores/vectorstores.py

@@ -76,6 +76,7 @@ def similarity_search_with_score(  # type: ignore[override]
         k: int = 4,
         filter: Optional[List[Namespace]] = None,
         numeric_filter: Optional[List[NumericNamespace]] = None,
+        **kwargs: Any,
     ) -> List[Tuple[Document, Union[float, Dict[str, float]]]]:
         """Return docs most similar to query and their cosine distance from the query.
 
@@ -103,7 +104,11 @@ def similarity_search_with_score(  # type: ignore[override]
         embedding = self._embeddings.embed_query(query)
 
         return self.similarity_search_by_vector_with_score(
-            embedding=embedding, k=k, filter=filter, numeric_filter=numeric_filter
+            embedding=embedding,
+            k=k,
+            filter=filter,
+            numeric_filter=numeric_filter,
+            **kwargs,
         )
 
     def similarity_search_by_vector_with_score(
@@ -114,6 +119,7 @@ def similarity_search_by_vector_with_score(
         rrf_ranking_alpha: float = 1,
         filter: Optional[List[Namespace]] = None,
         numeric_filter: Optional[List[NumericNamespace]] = None,
+        **kwargs: Any,
     ) -> List[Tuple[Document, Union[float, Dict[str, float]]]]:
         """Return docs most similar to the embedding and their cosine distance.
 
@@ -164,6 +170,7 @@ def similarity_search_by_vector_with_score(
             rrf_ranking_alpha=rrf_ranking_alpha,
             filter_=filter,
             numeric_filter=numeric_filter,
+            **kwargs,
         )
         if not neighbors_list:
             return []
@@ -255,7 +262,7 @@ def similarity_search(
         return [
             document
             for document, _ in self.similarity_search_with_score(
-                query, k, filter, numeric_filter
+                query, k, filter, numeric_filter, **kwargs
             )
         ]