Lint

Author: aclark4life

libs/langchain-mongodb/langchain_mongodb/docstores.py

@@ -99,12 +99,13 @@ def mset(
             batch_size: Number of documents to insert at a time.
                 Tuning this may help with performance and sidestep MongoDB limits.
         """
-        keys, docs = zip(*key_value_pairs)
+        keys, docs = zip(*key_value_pairs, strict=False)
         n_docs = len(docs)
         start = 0
         for end in range(batch_size, n_docs + batch_size, batch_size):
             texts, metadatas = zip(
-                *[(doc.page_content, doc.metadata) for doc in docs[start:end]]
+                *[(doc.page_content, doc.metadata) for doc in docs[start:end]],
+                strict=False,
             )
             self.insert_many(texts=texts, metadatas=metadatas, ids=keys[start:end])  # type: ignore
             start = end
@@ -149,6 +150,7 @@ def insert_many(
         in the batch that do not have conflicting _ids will still be inserted.
         """
         to_insert = [
-            {"_id": i, self._text_key: t, **m} for i, t, m in zip(ids, texts, metadatas)
+            {"_id": i, self._text_key: t, **m}
+            for i, t, m in zip(ids, texts, metadatas, strict=False)
         ]
         self.collection.insert_many(to_insert)  # type: ignore

libs/langchain-mongodb/langchain_mongodb/index.py

@@ -2,9 +2,10 @@
 
 import logging
 from time import monotonic, sleep
-from typing import Any, Callable, Dict, List, Optional
+from typing import Any, Callable, Dict, List, Optional, Union
 
 from pymongo.collection import Collection
+from pymongo.operations import SearchIndexModel
 
 # Don't break imports for modules that expect these functions
 # to be in this module.
@@ -40,60 +41,6 @@ def _vector_search_index_definition(
     return definition
 
 
-def create_vector_search_index(
-    collection: Collection,
-    index_name: str,
-    dimensions: int,
-    path: str,
-    similarity: str,
-    filters: Optional[List[str]] = None,
-    *,
-    wait_until_complete: Optional[float] = None,
-    **kwargs: Any,
-) -> None:
-    """Experimental Utility function to create a vector search index
-
-    Args:
-        collection (Collection): MongoDB Collection
-        index_name (str): Name of Index
-        dimensions (int): Number of dimensions in embedding
-        path (str): field with vector embedding
-        similarity (str): The similarity score used for the index
-        filters (List[str]): Fields/paths to index to allow filtering in $vectorSearch
-        wait_until_complete (Optional[float]): If provided, number of seconds to wait
-            until search index is ready.
-        kwargs: Keyword arguments supplying any additional options to SearchIndexModel.
-    """
-    logger.info("Creating Search Index %s on %s", index_name, collection.name)
-
-    if collection.name not in collection.database.list_collection_names(
-        authorizedCollections=True
-    ):
-        collection.database.create_collection(collection.name)
-
-    result = collection.create_search_index(
-        SearchIndexModel(
-            definition=_vector_search_index_definition(
-                dimensions=dimensions,
-                path=path,
-                similarity=similarity,
-                filters=filters,
-                **kwargs,
-            ),
-            name=index_name,
-            type="vectorSearch",
-        )
-    )
-
-    if wait_until_complete:
-        _wait_for_predicate(
-            predicate=lambda: _is_index_ready(collection, index_name),
-            err=f"{index_name=} did not complete in {wait_until_complete}!",
-            timeout=wait_until_complete,
-        )
-    logger.info(result)
-
-
 def drop_vector_search_index(
     collection: Collection,
     index_name: str,
@@ -121,54 +68,6 @@ def drop_vector_search_index(
     logger.info("Vector Search index %s.%s dropped", collection.name, index_name)
 
 
-def update_vector_search_index(
-    collection: Collection,
-    index_name: str,
-    dimensions: int,
-    path: str,
-    similarity: str,
-    filters: Optional[List[str]] = None,
-    *,
-    wait_until_complete: Optional[float] = None,
-    **kwargs: Any,
-) -> None:
-    """Update a search index.
-
-    Replace the existing index definition with the provided definition.
-
-    Args:
-        collection (Collection): MongoDB Collection
-        index_name (str): Name of Index
-        dimensions (int): Number of dimensions in embedding
-        path (str): field with vector embedding
-        similarity (str): The similarity score used for the index.
-        filters (List[str]): Fields/paths to index to allow filtering in $vectorSearch
-        wait_until_complete (Optional[float]): If provided, number of seconds to wait
-            until search index is ready.
-        kwargs: Keyword arguments supplying any additional options to SearchIndexModel.
-    """
-    logger.info(
-        "Updating Search Index %s from Collection: %s", index_name, collection.name
-    )
-    collection.update_search_index(
-        name=index_name,
-        definition=_vector_search_index_definition(
-            dimensions=dimensions,
-            path=path,
-            similarity=similarity,
-            filters=filters,
-            **kwargs,
-        ),
-    )
-    if wait_until_complete:
-        _wait_for_predicate(
-            predicate=lambda: _is_index_ready(collection, index_name),
-            err=f"Index {index_name} update did not complete in {wait_until_complete}!",
-            timeout=wait_until_complete,
-        )
-    logger.info("Update succeeded")
-
-
 def _is_index_ready(collection: Collection, index_name: str) -> bool:
     """Check for the index name in the list of available search indexes to see if the
     specified index is of status READY

libs/langchain-mongodb/langchain_mongodb/indexes.py

@@ -85,7 +85,7 @@ def update(
         if len(keys) != len(group_ids):
             raise ValueError("Number of keys does not match number of group_ids")
 
-        for key, group_id in zip(keys, group_ids):
+        for key, group_id in zip(keys, group_ids, strict=False):
             self._collection.find_one_and_update(
                 {"namespace": self.namespace, "key": key},
                 {"$set": {"group_id": group_id, "updated_at": self.get_time()}},

libs/langchain-mongodb/tests/integration_tests/test_cache.py

@@ -203,7 +203,7 @@ def test_mongodb_atlas_cache_matrix(
         for prompt_i_generations in generations
     ]
 
-    for prompt_i, llm_generations_i in zip(prompts, llm_generations):
+    for prompt_i, llm_generations_i in zip(prompts, llm_generations, strict=False):
         _execute_test(prompt_i, llm_string, llm_generations_i)
     assert llm.generate(prompts) == LLMResult(
         generations=llm_generations, llm_output={}

libs/langchain-mongodb/tests/unit_tests/test_cache.py

@@ -221,7 +221,7 @@ def test_mongodb_atlas_cache_matrix(
         for prompt_i_generations in generations
     ]
 
-    for prompt_i, llm_generations_i in zip(prompts, llm_generations):
+    for prompt_i, llm_generations_i in zip(prompts, llm_generations, strict=False):
         _execute_test(prompt_i, llm_string, llm_generations_i)
 
     get_llm_cache()._collection._simulate_cache_aggregation_query = True  # type: ignore