infra: update mypy 1.10, ruff 0.5 (#23721)

```python
"""python scripts/update_mypy_ruff.py"""
import glob
import tomllib
from pathlib import Path

import toml
import subprocess
import re

ROOT_DIR = Path(__file__).parents[1]


def main():
    for path in glob.glob(str(ROOT_DIR / "libs/**/pyproject.toml"), recursive=True):
        print(path)
        with open(path, "rb") as f:
            pyproject = tomllib.load(f)
        try:
            pyproject["tool"]["poetry"]["group"]["typing"]["dependencies"]["mypy"] = (
                "^1.10"
            )
            pyproject["tool"]["poetry"]["group"]["lint"]["dependencies"]["ruff"] = (
                "^0.5"
            )
        except KeyError:
            continue
        with open(path, "w") as f:
            toml.dump(pyproject, f)
        cwd = "/".join(path.split("/")[:-1])
        completed = subprocess.run(
            "poetry lock --no-update; poetry install --with typing; poetry run mypy . --no-color",
            cwd=cwd,
            shell=True,
            capture_output=True,
            text=True,
        )
        logs = completed.stdout.split("\n")

        to_ignore = {}
        for l in logs:
            if re.match("^(.*)\:(\d+)\: error:.*\[(.*)\]", l):
                path, line_no, error_type = re.match(
                    "^(.*)\:(\d+)\: error:.*\[(.*)\]", l
                ).groups()
                if (path, line_no) in to_ignore:
                    to_ignore[(path, line_no)].append(error_type)
                else:
                    to_ignore[(path, line_no)] = [error_type]
        print(len(to_ignore))
        for (error_path, line_no), error_types in to_ignore.items():
            all_errors = ", ".join(error_types)
            full_path = f"{cwd}/{error_path}"
            try:
                with open(full_path, "r") as f:
                    file_lines = f.readlines()
            except FileNotFoundError:
                continue
            file_lines[int(line_no) - 1] = (
                file_lines[int(line_no) - 1][:-1] + f"  # type: ignore[{all_errors}]\n"
            )
            with open(full_path, "w") as f:
                f.write("".join(file_lines))

        subprocess.run(
            "poetry run ruff format .; poetry run ruff --select I --fix .",
            cwd=cwd,
            shell=True,
            capture_output=True,
            text=True,
        )


if __name__ == "__main__":
    main()

```

.github/actions/people/app/main.py

@@ -350,11 +350,7 @@ def get_graphql_pr_edges(*, settings: Settings, after: Union[str, None] = None):
         print("Querying PRs...")
     else:
         print(f"Querying PRs with cursor {after}...")
-    data = get_graphql_response(
+    data = get_graphql_response(settings=settings, query=prs_query, after=after)
-        settings=settings,
-        query=prs_query,
-        after=after
-    )
     graphql_response = PRsResponse.model_validate(data)
     return graphql_response.data.repository.pullRequests.edges
 
@@ -484,10 +480,16 @@ def get_contributors(settings: Settings):
             lines_changed = pr.additions + pr.deletions
             score = _logistic(files_changed, 20) + _logistic(lines_changed, 100)
             contributor_scores[pr.author.login] += score
-            three_months_ago = (datetime.now(timezone.utc) - timedelta(days=3*30))
+            three_months_ago = datetime.now(timezone.utc) - timedelta(days=3 * 30)
             if pr.createdAt > three_months_ago:
                 recent_contributor_scores[pr.author.login] += score
-    return contributors, contributor_scores, recent_contributor_scores, reviewers, authors
+    return (
+        contributors,
+        contributor_scores,
+        recent_contributor_scores,
+        reviewers,
+        authors,
+    )
 
 
 def get_top_users(
@@ -524,9 +526,13 @@ if __name__ == "__main__":
     # question_commentors, question_last_month_commentors, question_authors = get_experts(
     #     settings=settings
     # )
-    contributors, contributor_scores, recent_contributor_scores, reviewers, pr_authors = get_contributors(
+    (
-        settings=settings
+        contributors,
-    )
+        contributor_scores,
+        recent_contributor_scores,
+        reviewers,
+        pr_authors,
+    ) = get_contributors(settings=settings)
     # authors = {**question_authors, **pr_authors}
     authors = {**pr_authors}
     maintainers_logins = {
@@ -559,7 +565,7 @@ if __name__ == "__main__":
         maintainers.append(
             {
                 "login": login,
-                "count": contributors[login], #+ question_commentors[login],
+                "count": contributors[login],  # + question_commentors[login],
                 "avatarUrl": user.avatarUrl,
                 "twitterUsername": user.twitterUsername,
                 "url": user.url,
@@ -615,9 +621,7 @@ if __name__ == "__main__":
     new_people_content = yaml.dump(
         people, sort_keys=False, width=200, allow_unicode=True
     )
-    if (
+    if people_old_content == new_people_content:
-        people_old_content == new_people_content
-    ):
         logging.info("The LangChain People data hasn't changed, finishing.")
         sys.exit(0)
     people_path.write_text(new_people_content, encoding="utf-8")
@@ -630,9 +634,7 @@ if __name__ == "__main__":
     logging.info(f"Creating a new branch {branch_name}")
     subprocess.run(["git", "checkout", "-B", branch_name], check=True)
     logging.info("Adding updated file")
-    subprocess.run(
+    subprocess.run(["git", "add", str(people_path)], check=True)
-        ["git", "add", str(people_path)], check=True
-    )
     logging.info("Committing updated file")
     message = "👥 Update LangChain people data"
     result = subprocess.run(["git", "commit", "-m", message], check=True)

.github/scripts/check_diff.py

@@ -1,11 +1,12 @@
+import glob
 import json
-import sys
 import os
-from typing import Dict, List, Set
+import re
-
+import sys
 import tomllib
 from collections import defaultdict
-import glob
+from typing import Dict, List, Set
+
 
 LANGCHAIN_DIRS = [
     "libs/core",
@@ -15,8 +16,13 @@ LANGCHAIN_DIRS = [
     "libs/experimental",
 ]
 
+
 def all_package_dirs() -> Set[str]:
-    return {"/".join(path.split("/")[:-1]) for path in glob.glob("./libs/**/pyproject.toml", recursive=True)}
+    return {
+        "/".join(path.split("/")[:-1]).lstrip("./")
+        for path in glob.glob("./libs/**/pyproject.toml", recursive=True)
+        if "libs/cli" not in path and "libs/standard-tests" not in path
+    }
 
 
 def dependents_graph() -> dict:
@@ -26,9 +32,9 @@ def dependents_graph() -> dict:
         if "template" in path:
             continue
         with open(path, "rb") as f:
-            pyproject = tomllib.load(f)['tool']['poetry']
+            pyproject = tomllib.load(f)["tool"]["poetry"]
         pkg_dir = "libs" + "/".join(path.split("libs")[1].split("/")[:-1])
-        for dep in pyproject['dependencies']:
+        for dep in pyproject["dependencies"]:
             if "langchain" in dep:
                 dependents[dep].add(pkg_dir)
     return dependents
@@ -122,9 +128,12 @@ if __name__ == "__main__":
 
     outputs = {
         "dirs-to-lint": add_dependents(
-            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
+            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"],
+            dependents,
+        ),
+        "dirs-to-test": add_dependents(
+            dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
         ),
-        "dirs-to-test": add_dependents(dirs_to_run["test"] | dirs_to_run["extended-test"], dependents),
         "dirs-to-extended-test": list(dirs_to_run["extended-test"]),
         "docs-edited": "true" if docs_edited else "",
     }

.github/scripts/get_min_versions.py

@@ -74,6 +74,4 @@ if __name__ == "__main__":
     # Call the function to get the minimum versions
     min_versions = get_min_version_from_toml(toml_file)
 
-    print(
+    print(" ".join([f"{lib}=={version}" for lib, version in min_versions.items()]))
-        " ".join([f"{lib}=={version}" for lib, version in min_versions.items()])
-    )

libs/community/Makefile

@@ -48,14 +48,14 @@ lint lint_diff lint_package lint_tests:
 	./scripts/check_pydantic.sh .
 	./scripts/lint_imports.sh
 	./scripts/check_pickle.sh .
-	poetry run ruff .
+	poetry run ruff check .
 	[ "$(PYTHON_FILES)" = "" ] || poetry run ruff format $(PYTHON_FILES) --diff
-	[ "$(PYTHON_FILES)" = "" ] || poetry run ruff --select I $(PYTHON_FILES)
+	[ "$(PYTHON_FILES)" = "" ] || poetry run ruff check --select I $(PYTHON_FILES)
 	[ "$(PYTHON_FILES)" = "" ] || mkdir -p $(MYPY_CACHE) && poetry run mypy $(PYTHON_FILES) --cache-dir $(MYPY_CACHE)
 
 format format_diff:
 	poetry run ruff format $(PYTHON_FILES)
-	poetry run ruff --select I --fix $(PYTHON_FILES)
+	poetry run ruff check --select I --fix $(PYTHON_FILES)
 
 spell_check:
 	poetry run codespell --toml pyproject.toml

libs/community/langchain_community/__init__.py

@@ -1,4 +1,5 @@
 """Main entrypoint into package."""
+
 from importlib import metadata
 
 try:

libs/community/langchain_community/adapters/openai.py

@@ -206,8 +206,7 @@ class ChatCompletion:
         provider: str = "ChatOpenAI",
         stream: Literal[False] = False,
         **kwargs: Any,
-    ) -> dict:
+    ) -> dict: ...
-        ...
 
     @overload
     @staticmethod
@@ -217,8 +216,7 @@ class ChatCompletion:
         provider: str = "ChatOpenAI",
         stream: Literal[True],
         **kwargs: Any,
-    ) -> Iterable:
+    ) -> Iterable: ...
-        ...
 
     @staticmethod
     def create(
@@ -249,8 +247,7 @@ class ChatCompletion:
         provider: str = "ChatOpenAI",
         stream: Literal[False] = False,
         **kwargs: Any,
-    ) -> dict:
+    ) -> dict: ...
-        ...
 
     @overload
     @staticmethod
@@ -260,8 +257,7 @@ class ChatCompletion:
         provider: str = "ChatOpenAI",
         stream: Literal[True],
         **kwargs: Any,
-    ) -> AsyncIterator:
+    ) -> AsyncIterator: ...
-        ...
 
     @staticmethod
     async def acreate(
@@ -319,8 +315,7 @@ class Completions:
         provider: str = "ChatOpenAI",
         stream: Literal[False] = False,
         **kwargs: Any,
-    ) -> ChatCompletions:
+    ) -> ChatCompletions: ...
-        ...
 
     @overload
     @staticmethod
@@ -330,8 +325,7 @@ class Completions:
         provider: str = "ChatOpenAI",
         stream: Literal[True],
         **kwargs: Any,
-    ) -> Iterable:
+    ) -> Iterable: ...
-        ...
 
     @staticmethod
     def create(
@@ -366,8 +360,7 @@ class Completions:
         provider: str = "ChatOpenAI",
         stream: Literal[False] = False,
         **kwargs: Any,
-    ) -> ChatCompletions:
+    ) -> ChatCompletions: ...
-        ...
 
     @overload
     @staticmethod
@@ -377,8 +370,7 @@ class Completions:
         provider: str = "ChatOpenAI",
         stream: Literal[True],
         **kwargs: Any,
-    ) -> AsyncIterator:
+    ) -> AsyncIterator: ...
-        ...
 
     @staticmethod
     async def acreate(

libs/community/langchain_community/cache.py

@@ -2189,14 +2189,14 @@ class AzureCosmosDBSemanticCache(BaseCache):
                 index_name=index_name,
             )
         else:
-            self._cache_dict[
+            self._cache_dict[index_name] = (
-                index_name
+                AzureCosmosDBVectorSearch.from_connection_string(
-            ] = AzureCosmosDBVectorSearch.from_connection_string(
+                    connection_string=self.cosmosdb_connection_string,
-                connection_string=self.cosmosdb_connection_string,
+                    namespace=namespace,
-                namespace=namespace,
+                    embedding=self.embedding,
-                embedding=self.embedding,
+                    index_name=index_name,
-                index_name=index_name,
+                    application_name=self.application_name,
-                application_name=self.application_name,
+                )
             )
 
         # create index for the vectorstore

libs/community/langchain_community/callbacks/__init__.py

@@ -6,6 +6,7 @@
 
     BaseCallbackHandler --> <name>CallbackHandler  # Example: AimCallbackHandler
 """
+
 import importlib
 from typing import TYPE_CHECKING, Any
 

libs/community/langchain_community/callbacks/arize_callback.py

@@ -82,9 +82,9 @@ class ArizeCallbackHandler(BaseCallbackHandler):
                 "completion_tokens", 0
             )
         else:
-            self.prompt_tokens = (
+            self.prompt_tokens = self.total_tokens = self.completion_tokens = (
-                self.total_tokens
+                0  # assign default value
-            ) = self.completion_tokens = 0  # assign default value
+            )
 
         for generations in response.generations:
             for generation in generations:

libs/community/langchain_community/callbacks/arthur_callback.py

@@ -1,4 +1,5 @@
 """ArthurAI's Callback Handler."""
+
 from __future__ import annotations
 
 import os

libs/community/langchain_community/callbacks/promptlayer_callback.py

@@ -1,4 +1,5 @@
 """Callback handler for promptlayer."""
+
 from __future__ import annotations
 
 import datetime

libs/community/langchain_community/callbacks/tracers/wandb.py

@@ -1,4 +1,5 @@
 """A Tracer Implementation that records activity to Weights & Biases."""
+
 from __future__ import annotations
 
 import json
@@ -234,9 +235,9 @@ def build_tree(runs: List[Dict[str, Any]]) -> Dict[str, Any]:
 
     for child_id, parent_id in child_to_parent.items():
         parent_dict = id_to_data[parent_id]
-        parent_dict[next(iter(parent_dict))][
+        parent_dict[next(iter(parent_dict))][next(iter(id_to_data[child_id]))] = (
-            next(iter(id_to_data[child_id]))
+            id_to_data[child_id][next(iter(id_to_data[child_id]))]
-        ] = id_to_data[child_id][next(iter(id_to_data[child_id]))]
+        )
 
     root_dict = next(
         data for id_val, data in id_to_data.items() if id_val not in child_to_parent

libs/community/langchain_community/chains/ernie_functions/base.py

@@ -1,4 +1,5 @@
 """Methods for creating chains that use Ernie function-calling APIs."""
+
 import inspect
 from typing import (
     Any,
@@ -191,9 +192,9 @@ def get_ernie_output_parser(
             }
         else:
             pydantic_schema = functions[0]
-        output_parser: Union[
+        output_parser: Union[BaseOutputParser, BaseGenerationOutputParser] = (
-            BaseOutputParser, BaseGenerationOutputParser
+            PydanticOutputFunctionsParser(pydantic_schema=pydantic_schema)
-        ] = PydanticOutputFunctionsParser(pydantic_schema=pydantic_schema)
+        )
     else:
         output_parser = JsonOutputFunctionsParser(args_only=len(functions) <= 1)
     return output_parser

libs/community/langchain_community/chains/graph_qa/arangodb.py

@@ -1,4 +1,5 @@
 """Question answering over a graph."""
+
 from __future__ import annotations
 
 import re

libs/community/langchain_community/chains/graph_qa/base.py

@@ -1,4 +1,5 @@
 """Question answering over a graph."""
+
 from __future__ import annotations
 
 from typing import Any, Dict, List, Optional

libs/community/langchain_community/chains/graph_qa/cypher.py

@@ -1,4 +1,5 @@
 """Question answering over a graph."""
+
 from __future__ import annotations
 
 import re

libs/community/langchain_community/chains/graph_qa/falkordb.py

@@ -1,4 +1,5 @@
 """Question answering over a graph."""
+
 from __future__ import annotations
 
 import re

libs/community/langchain_community/chains/graph_qa/gremlin.py

@@ -1,4 +1,5 @@
 """Question answering over a graph."""
+
 from __future__ import annotations
 
 from typing import Any, Dict, List, Optional

libs/community/langchain_community/chains/graph_qa/hugegraph.py

@@ -1,4 +1,5 @@
 """Question answering over a graph."""
+
 from __future__ import annotations
 
 from typing import Any, Dict, List, Optional

libs/community/langchain_community/chains/graph_qa/kuzu.py

@@ -1,4 +1,5 @@
 """Question answering over a graph."""
+
 from __future__ import annotations
 
 import re

libs/community/langchain_community/chains/graph_qa/nebulagraph.py

@@ -1,4 +1,5 @@
 """Question answering over a graph."""
+
 from __future__ import annotations
 
 from typing import Any, Dict, List, Optional

libs/community/langchain_community/chains/graph_qa/neptune_sparql.py

@@ -1,6 +1,7 @@
 """
 Question answering over an RDF or OWL graph using SPARQL.
 """
+
 from __future__ import annotations
 
 from typing import Any, Dict, List, Optional

libs/community/langchain_community/chains/graph_qa/ontotext_graphdb.py

@@ -1,4 +1,5 @@
 """Question answering over a graph."""
+
 from __future__ import annotations
 
 from typing import TYPE_CHECKING, Any, Dict, List, Optional

libs/community/langchain_community/chains/graph_qa/sparql.py

@@ -1,6 +1,7 @@
 """
 Question answering over an RDF or OWL graph using SPARQL.
 """
+
 from __future__ import annotations
 
 from typing import Any, Dict, List, Optional

libs/community/langchain_community/chains/llm_requests.py

@@ -1,4 +1,5 @@
 """Chain that hits a URL and then uses an LLM to parse results."""
+
 from __future__ import annotations
 
 from typing import Any, Dict, List, Optional

libs/community/langchain_community/chains/openapi/chain.py

@@ -1,4 +1,5 @@
 """Chain that makes API calls and summarizes the responses to answer a question."""
+
 from __future__ import annotations
 
 import json

libs/community/langchain_community/chat_loaders/utils.py

@@ -1,4 +1,5 @@
 """Utilities for chat loaders."""
+
 from copy import deepcopy
 from typing import Iterable, Iterator, List
 

libs/community/langchain_community/chat_message_histories/astradb.py

@@ -1,4 +1,5 @@
 """Astra DB - based chat message history, based on astrapy."""
+
 from __future__ import annotations
 
 import json

libs/community/langchain_community/chat_message_histories/cassandra.py

@@ -1,4 +1,5 @@
 """Cassandra-based chat message history, based on cassIO."""
+
 from __future__ import annotations
 
 import json

libs/community/langchain_community/chat_message_histories/cosmos_db.py

@@ -1,4 +1,5 @@
 """Azure CosmosDB Memory History."""
+
 from __future__ import annotations
 
 import logging

libs/community/langchain_community/chat_message_histories/firestore.py

@@ -1,4 +1,5 @@
 """Firestore Chat Message History."""
+
 from __future__ import annotations
 
 import logging

libs/community/langchain_community/chat_message_histories/kafka.py

@@ -1,7 +1,8 @@
-""" Kafka-based chat message history by using confluent-kafka-python.
+"""Kafka-based chat message history by using confluent-kafka-python.
-    confluent-kafka-python is under Apache 2.0 license.
+confluent-kafka-python is under Apache 2.0 license.
-    https://github.com/confluentinc/confluent-kafka-python
+https://github.com/confluentinc/confluent-kafka-python
 """
+
 from __future__ import annotations
 
 import json

libs/community/langchain_community/chat_models/anyscale.py

@@ -1,4 +1,5 @@
 """Anyscale Endpoints chat wrapper. Relies heavily on ChatOpenAI."""
+
 from __future__ import annotations
 
 import logging

libs/community/langchain_community/chat_models/azure_openai.py

@@ -1,4 +1,5 @@
 """Azure OpenAI chat wrapper."""
+
 from __future__ import annotations
 
 import logging

libs/community/langchain_community/chat_models/everlyai.py

@@ -1,4 +1,5 @@
 """EverlyAI Endpoints chat wrapper. Relies heavily on ChatOpenAI."""
+
 from __future__ import annotations
 
 import logging

libs/community/langchain_community/chat_models/fake.py

@@ -1,4 +1,5 @@
 """Fake ChatModel for testing purposes."""
+
 import asyncio
 import time
 from typing import Any, AsyncIterator, Dict, Iterator, List, Optional, Union

libs/community/langchain_community/chat_models/google_palm.py

@@ -1,4 +1,5 @@
 """Wrapper around Google's PaLM Chat API."""
+
 from __future__ import annotations
 
 import logging

libs/community/langchain_community/chat_models/jinachat.py

@@ -1,4 +1,5 @@
 """JinaChat wrapper."""
+
 from __future__ import annotations
 
 import logging

libs/community/langchain_community/chat_models/konko.py

@@ -1,4 +1,5 @@
 """KonkoAI chat wrapper."""
+
 from __future__ import annotations
 
 import logging

libs/community/langchain_community/chat_models/litellm.py

@@ -1,4 +1,5 @@
 """Wrapper around LiteLLM's model I/O library."""
+
 from __future__ import annotations
 
 import logging

libs/community/langchain_community/chat_models/litellm_router.py

@@ -1,4 +1,5 @@
 """LiteLLM Router as LangChain Model."""
+
 from typing import (
     Any,
     AsyncIterator,

libs/community/langchain_community/chat_models/moonshot.py

@@ -1,4 +1,5 @@
 """Wrapper around Moonshot chat models."""
+
 from typing import Dict
 
 from langchain_core.pydantic_v1 import root_validator

libs/community/langchain_community/chat_models/oci_generative_ai.py

@@ -27,28 +27,22 @@ CUSTOM_ENDPOINT_PREFIX = "ocid1.generativeaiendpoint"
 class Provider(ABC):
     @property
     @abstractmethod
-    def stop_sequence_key(self) -> str:
+    def stop_sequence_key(self) -> str: ...
-        ...
 
     @abstractmethod
-    def chat_response_to_text(self, response: Any) -> str:
+    def chat_response_to_text(self, response: Any) -> str: ...
-        ...
 
     @abstractmethod
-    def chat_stream_to_text(self, event_data: Dict) -> str:
+    def chat_stream_to_text(self, event_data: Dict) -> str: ...
-        ...
 
     @abstractmethod
-    def chat_generation_info(self, response: Any) -> Dict[str, Any]:
+    def chat_generation_info(self, response: Any) -> Dict[str, Any]: ...
-        ...
 
     @abstractmethod
-    def get_role(self, message: BaseMessage) -> str:
+    def get_role(self, message: BaseMessage) -> str: ...
-        ...
 
     @abstractmethod
-    def messages_to_oci_params(self, messages: Any) -> Dict[str, Any]:
+    def messages_to_oci_params(self, messages: Any) -> Dict[str, Any]: ...
-        ...
 
 
 class CohereProvider(Provider):

libs/community/langchain_community/chat_models/octoai.py

@@ -1,4 +1,5 @@
 """OctoAI Endpoints chat wrapper. Relies heavily on ChatOpenAI."""
+
 from typing import Dict
 
 from langchain_core.pydantic_v1 import Field, SecretStr, root_validator

libs/community/langchain_community/chat_models/promptlayer_openai.py

@@ -1,4 +1,5 @@
 """PromptLayer wrapper."""
+
 import datetime
 from typing import Any, Dict, List, Optional
 

libs/community/langchain_community/chat_models/vertexai.py

@@ -1,4 +1,5 @@
 """Wrapper around Google VertexAI chat-based models."""
+
 from __future__ import annotations
 
 import base64

libs/community/langchain_community/chat_models/yandex.py

@@ -1,4 +1,5 @@
 """Wrapper around YandexGPT chat models."""
+
 from __future__ import annotations
 
 import logging

libs/community/langchain_community/chat_models/yuan2.py

@@ -1,4 +1,5 @@
 """ChatYuan2 wrapper."""
+
 from __future__ import annotations
 
 import logging

libs/community/langchain_community/cross_encoders/__init__.py

@@ -9,6 +9,7 @@
 
     BaseCrossEncoder --> <name>CrossEncoder  # Examples: SagemakerEndpointCrossEncoder
 """
+
 import importlib
 from typing import TYPE_CHECKING, Any
 

libs/community/langchain_community/docstore/base.py

@@ -1,4 +1,5 @@
 """Interface to access to place that stores documents."""
+
 from abc import ABC, abstractmethod
 from typing import Dict, List, Union
 

libs/community/langchain_community/docstore/in_memory.py

@@ -1,4 +1,5 @@
 """Simple in memory docstore in the form of a dict."""
+
 from typing import Dict, List, Optional, Union
 
 from langchain_core.documents import Document

libs/community/langchain_community/docstore/wikipedia.py

@@ -1,6 +1,5 @@
 """Wrapper around wikipedia API."""
 
-
 from typing import Union
 
 from langchain_core.documents import Document

libs/community/langchain_community/document_loaders/base_o365.py

@@ -60,9 +60,9 @@ def fetch_mime_types(file_types: Sequence[_FileType]) -> Dict[str, str]:
         if file_type.value == "doc":
             mime_types_mapping[file_type.value] = "application/msword"
         elif file_type.value == "docx":
-            mime_types_mapping[
+            mime_types_mapping[file_type.value] = (
-                file_type.value
+                "application/vnd.openxmlformats-officedocument.wordprocessingml.document"  # noqa: E501
-            ] = "application/vnd.openxmlformats-officedocument.wordprocessingml.document"  # noqa: E501
+            )
         elif file_type.value == "pdf":
             mime_types_mapping[file_type.value] = "application/pdf"
     return mime_types_mapping

libs/community/langchain_community/document_loaders/blob_loaders/cloud_blob_loader.py

@@ -1,4 +1,5 @@
 """Use to load blobs from the local file system."""
+
 import contextlib
 import mimetypes
 import tempfile

libs/community/langchain_community/document_loaders/blob_loaders/youtube_audio.py

@@ -5,7 +5,6 @@ from langchain_community.document_loaders.blob_loaders.schema import Blob, BlobL
 
 
 class YoutubeAudioLoader(BlobLoader):
-
     """Load YouTube urls as audio file(s)."""
 
     def __init__(self, urls: List[str], save_dir: str):

libs/community/langchain_community/document_loaders/docusaurus.py

@@ -1,4 +1,5 @@
 """Load Documents from Docusarus Documentation"""
+
 from typing import Any, List, Optional
 
 from langchain_community.document_loaders.sitemap import SitemapLoader

libs/community/langchain_community/document_loaders/evernote.py

@@ -2,6 +2,7 @@
 
 https://gist.github.com/foxmask/7b29c43a161e001ff04afdb2f181e31c
 """
+
 import hashlib
 import logging
 from base64 import b64decode

libs/community/langchain_community/document_loaders/excel.py

@@ -1,4 +1,5 @@
 """Loads Microsoft Excel files."""
+
 from pathlib import Path
 from typing import Any, List, Union
 

libs/community/langchain_community/document_loaders/news.py

@@ -1,4 +1,5 @@
 """Loader that uses unstructured to load HTML files."""
+
 import logging
 from typing import Any, Iterator, List
 

libs/community/langchain_community/document_loaders/notebook.py

@@ -1,4 +1,5 @@
 """Loads .ipynb notebook files."""
+
 import json
 from pathlib import Path
 from typing import Any, List, Union

libs/community/langchain_community/document_loaders/onedrive.py

@@ -1,4 +1,5 @@
 """Loads data from OneDrive"""
+
 from __future__ import annotations
 
 import logging

libs/community/langchain_community/document_loaders/parsers/docai.py

@@ -4,6 +4,7 @@ You need to install two libraries to use this parser:
 pip install google-cloud-documentai
 pip install google-cloud-documentai-toolbox
 """
+
 import logging
 import re
 import time

libs/community/langchain_community/document_loaders/parsers/generic.py

@@ -2,6 +2,7 @@
 
 This module contains some logic to help assemble more sophisticated parsers.
 """
+
 from typing import Iterator, Mapping, Optional
 
 from langchain_core.documents import Document

libs/community/langchain_community/document_loaders/parsers/pdf.py

@@ -1,4 +1,5 @@
 """Module contains common parsers for PDFs."""
+
 from __future__ import annotations
 
 import warnings

libs/community/langchain_community/document_loaders/parsers/registry.py

@@ -1,4 +1,5 @@
 """Module includes a registry of default parser configurations."""
+
 from langchain_community.document_loaders.base import BaseBlobParser
 from langchain_community.document_loaders.parsers.generic import MimeTypeBasedParser
 from langchain_community.document_loaders.parsers.msword import MsWordParser

libs/community/langchain_community/document_loaders/parsers/txt.py

@@ -1,4 +1,5 @@
 """Module for parsing text files.."""
+
 from typing import Iterator
 
 from langchain_core.documents import Document

libs/community/langchain_community/document_loaders/pebblo.py

@@ -213,9 +213,9 @@ class PebbloSafeLoader(BaseLoader):
         if loading_end is True:
             payload["loading_end"] = "true"
             if "loader_details" in payload:
-                payload["loader_details"][
+                payload["loader_details"]["source_aggregate_size"] = (
-                    "source_aggregate_size"
+                    self.source_aggregate_size
-                ] = self.source_aggregate_size
+                )
         payload = Doc(**payload).dict(exclude_unset=True)
         # Raw payload to be sent to classifier
         if self.classifier_location == "local":

libs/community/langchain_community/document_loaders/rst.py

@@ -1,4 +1,5 @@
 """Loads RST files."""
+
 from pathlib import Path
 from typing import Any, List, Union
 

libs/community/langchain_community/document_loaders/rtf.py

@@ -1,4 +1,5 @@
 """Loads rich text files."""
+
 from pathlib import Path
 from typing import Any, List, Union
 

libs/community/langchain_community/document_loaders/scrapfly.py

@@ -1,4 +1,5 @@
 """Scrapfly Web Reader."""
+
 import logging
 from typing import Iterator, List, Literal, Optional
 

libs/community/langchain_community/document_loaders/tensorflow_datasets.py

@@ -61,9 +61,9 @@ class TensorflowDatasetLoader(BaseLoader):
         self.split_name: str = split_name
         self.load_max_docs = load_max_docs
         """The maximum number of documents to load."""
-        self.sample_to_document_function: Optional[
+        self.sample_to_document_function: Optional[Callable[[Dict], Document]] = (
-            Callable[[Dict], Document]
+            sample_to_document_function
-        ] = sample_to_document_function
+        )
         """Custom function that transform a dataset sample into a Document."""
 
         self._tfds_client = TensorflowDatasets(  # type: ignore[call-arg]

libs/community/langchain_community/document_loaders/unstructured.py

@@ -1,4 +1,5 @@
 """Loader that uses unstructured to load files."""
+
 import collections
 from abc import ABC, abstractmethod
 from pathlib import Path

libs/community/langchain_community/document_loaders/url.py

@@ -1,4 +1,5 @@
 """Loader that uses unstructured to load HTML files."""
+
 import logging
 from typing import Any, List
 

libs/community/langchain_community/document_loaders/url_playwright.py

@@ -1,5 +1,5 @@
-"""Loader that uses Playwright to load a page, then uses unstructured to load the html.
+"""Loader that uses Playwright to load a page, then uses unstructured to parse html."""
-"""
+
 import logging
 from abc import ABC, abstractmethod
 from typing import TYPE_CHECKING, AsyncIterator, Dict, Iterator, List, Optional

libs/community/langchain_community/document_loaders/url_selenium.py

@@ -1,5 +1,5 @@
-"""Loader that uses Selenium to load a page, then uses unstructured to load the html.
+"""Loader that uses Selenium to load a page, then uses unstructured to load the html."""
-"""
+
 import logging
 from typing import TYPE_CHECKING, List, Literal, Optional, Union
 

libs/community/langchain_community/document_loaders/weather.py

@@ -1,4 +1,5 @@
 """Simple reader that reads weather data from OpenWeatherMap API"""
+
 from __future__ import annotations
 
 from datetime import datetime

libs/community/langchain_community/document_loaders/word_document.py

@@ -1,4 +1,5 @@
 """Loads word documents."""
+
 import os
 import tempfile
 from abc import ABC

libs/community/langchain_community/document_loaders/xml.py

@@ -1,4 +1,5 @@
 """Loads Microsoft Excel files."""
+
 from pathlib import Path
 from typing import Any, List, Union
 

libs/community/langchain_community/document_loaders/youtube.py

@@ -1,4 +1,5 @@
 """Loads YouTube transcript."""
+
 from __future__ import annotations
 
 import logging

libs/community/langchain_community/document_transformers/embeddings_redundant_filter.py

@@ -1,4 +1,5 @@
 """Transform documents"""
+
 from typing import Any, Callable, List, Sequence
 
 import numpy as np

libs/community/langchain_community/document_transformers/long_context_reorder.py

@@ -1,4 +1,5 @@
 """Reorder documents"""
+
 from typing import Any, List, Sequence
 
 from langchain_core.documents import BaseDocumentTransformer, Document

libs/community/langchain_community/document_transformers/openai_functions.py

@@ -1,4 +1,5 @@
 """Document transformers that use OpenAI Functions models"""
+
 from typing import Any, Dict, Optional, Sequence, Type, Union
 
 from langchain_core.documents import BaseDocumentTransformer, Document

libs/community/langchain_community/embeddings/anyscale.py

@@ -1,4 +1,5 @@
 """Anyscale embeddings wrapper."""
+
 from __future__ import annotations
 
 from typing import Dict

libs/community/langchain_community/embeddings/llm_rails.py

@@ -1,4 +1,5 @@
-""" This file is for LLMRails Embedding """
+"""This file is for LLMRails Embedding"""
+
 from typing import Dict, List, Optional
 
 import requests

libs/community/langchain_community/embeddings/oci_generative_ai.py

@@ -132,13 +132,13 @@ class OCIGenAIEmbeddings(BaseModel, Embeddings):
                     oci_config=client_kwargs["config"]
                 )
             elif values["auth_type"] == OCIAuthType(3).name:
-                client_kwargs[
+                client_kwargs["signer"] = (
-                    "signer"
+                    oci.auth.signers.InstancePrincipalsSecurityTokenSigner()
-                ] = oci.auth.signers.InstancePrincipalsSecurityTokenSigner()
+                )
             elif values["auth_type"] == OCIAuthType(4).name:
-                client_kwargs[
+                client_kwargs["signer"] = (
-                    "signer"
+                    oci.auth.signers.get_resource_principals_signer()
-                ] = oci.auth.signers.get_resource_principals_signer()
+                )
             else:
                 raise ValueError("Please provide valid value to auth_type")
 

libs/community/langchain_community/embeddings/sentence_transformer.py

@@ -1,4 +1,5 @@
 """HuggingFace sentence_transformer embedding models."""
+
 from langchain_community.embeddings.huggingface import HuggingFaceEmbeddings
 
 SentenceTransformerEmbeddings = HuggingFaceEmbeddings

libs/community/langchain_community/embeddings/yandex.py

@@ -1,4 +1,5 @@
 """Wrapper around YandexGPT embedding models."""
+
 from __future__ import annotations
 
 import logging
@@ -105,15 +106,15 @@ class YandexGPTEmbeddings(BaseModel, Embeddings):
         if not values.get("doc_model_uri"):
             if values["folder_id"] == "":
                 raise ValueError("'doc_model_uri' or 'folder_id' must be provided.")
-            values[
+            values["doc_model_uri"] = (
-                "doc_model_uri"
+                f"emb://{values['folder_id']}/{values['doc_model_name']}/{values['model_version']}"
-            ] = f"emb://{values['folder_id']}/{values['doc_model_name']}/{values['model_version']}"
+            )
         if not values.get("model_uri"):
             if values["folder_id"] == "":
                 raise ValueError("'model_uri' or 'folder_id' must be provided.")
-            values[
+            values["model_uri"] = (
-                "model_uri"
+                f"emb://{values['folder_id']}/{values['model_name']}/{values['model_version']}"
-            ] = f"emb://{values['folder_id']}/{values['model_name']}/{values['model_version']}"
+            )
         if values["disable_request_logging"]:
             values["_grpc_metadata"].append(
                 (

libs/community/langchain_community/example_selectors/__init__.py

@@ -6,6 +6,7 @@ There could be multiple strategies for selecting examples. For example, one coul
 select examples based on the similarity of the input to the examples. Another
 strategy could be to select examples based on the diversity of the examples.
 """
+
 from langchain_community.example_selectors.ngram_overlap import (
     NGramOverlapExampleSelector,
     ngram_overlap_score,

libs/community/langchain_community/example_selectors/ngram_overlap.py

@@ -3,6 +3,7 @@
 https://www.nltk.org/_modules/nltk/translate/bleu_score.html
 https://aclanthology.org/P02-1040.pdf
 """
+
 from typing import Dict, List
 
 import numpy as np

libs/community/langchain_community/graphs/networkx_graph.py

@@ -1,4 +1,5 @@
 """Networkx wrapper for graph operations."""
+
 from __future__ import annotations
 
 from typing import Any, List, NamedTuple, Optional, Tuple

libs/community/langchain_community/llms/anyscale.py

@@ -1,4 +1,5 @@
 """Wrapper around Anyscale Endpoint"""
+
 from typing import (
     Any,
     Dict,

libs/community/langchain_community/llms/databricks.py

@@ -44,8 +44,7 @@ class _DatabricksClientBase(BaseModel, ABC):
     @abstractmethod
     def post(
         self, request: Any, transform_output_fn: Optional[Callable[..., str]] = None
-    ) -> Any:
+    ) -> Any: ...
-        ...
 
     @property
     def llm(self) -> bool:

libs/community/langchain_community/llms/edenai.py

@@ -1,4 +1,5 @@
 """Wrapper around EdenAI's Generation API."""
+
 import logging
 from typing import Any, Dict, List, Literal, Optional
 

libs/community/langchain_community/llms/konko.py

@@ -1,4 +1,5 @@
 """Wrapper around Konko AI's Completion API."""
+
 import logging
 import warnings
 from typing import Any, Dict, List, Optional

libs/community/langchain_community/llms/layerup_security.py

@@ -39,12 +39,12 @@ class LayerupSecurity(LLM):
     response_guardrails: Optional[List[str]] = []
     mask: bool = False
     metadata: Optional[Dict[str, Any]] = {}
-    handle_prompt_guardrail_violation: Callable[
+    handle_prompt_guardrail_violation: Callable[[dict], str] = (
-        [dict], str
+        default_guardrail_violation_handler
-    ] = default_guardrail_violation_handler
+    )
-    handle_response_guardrail_violation: Callable[
+    handle_response_guardrail_violation: Callable[[dict], str] = (
-        [dict], str
+        default_guardrail_violation_handler
-    ] = default_guardrail_violation_handler
+    )
     client: Any  #: :meta private:
 
     @root_validator(pre=True)

libs/community/langchain_community/llms/loading.py

@@ -1,4 +1,5 @@
 """Base interface for loading large language model APIs."""
+
 import json
 from pathlib import Path
 from typing import Any, Union

libs/community/langchain_community/llms/minimax.py

@@ -1,4 +1,5 @@
 """Wrapper around Minimax APIs."""
+
 from __future__ import annotations
 
 import logging

libs/community/langchain_community/llms/oci_generative_ai.py

@@ -18,12 +18,10 @@ CUSTOM_ENDPOINT_PREFIX = "ocid1.generativeaiendpoint"
 class Provider(ABC):
     @property
     @abstractmethod
-    def stop_sequence_key(self) -> str:
+    def stop_sequence_key(self) -> str: ...
-        ...
 
     @abstractmethod
-    def completion_response_to_text(self, response: Any) -> str:
+    def completion_response_to_text(self, response: Any) -> str: ...
-        ...
 
 
 class CohereProvider(Provider):
@@ -144,13 +142,13 @@ class OCIGenAIBase(BaseModel, ABC):
                     oci_config=client_kwargs["config"]
                 )
             elif values["auth_type"] == OCIAuthType(3).name:
-                client_kwargs[
+                client_kwargs["signer"] = (
-                    "signer"
+                    oci.auth.signers.InstancePrincipalsSecurityTokenSigner()
-                ] = oci.auth.signers.InstancePrincipalsSecurityTokenSigner()
+                )
             elif values["auth_type"] == OCIAuthType(4).name:
-                client_kwargs[
+                client_kwargs["signer"] = (
-                    "signer"
+                    oci.auth.signers.get_resource_principals_signer()
-                ] = oci.auth.signers.get_resource_principals_signer()
+                )
             else:
                 raise ValueError(
                     "Please provide valid value to auth_type, "

libs/community/langchain_community/llms/openllm.py

@@ -93,9 +93,9 @@ class OpenLLM(LLM):
     """Keyword arguments to be passed to openllm.LLM"""
 
     _runner: Optional[openllm.LLMRunner] = PrivateAttr(default=None)
-    _client: Union[
+    _client: Union[openllm.client.HTTPClient, openllm.client.GrpcClient, None] = (
-        openllm.client.HTTPClient, openllm.client.GrpcClient, None
+        PrivateAttr(default=None)
-    ] = PrivateAttr(default=None)
+    )
 
     class Config:
         extra = "forbid"
@@ -108,8 +108,7 @@ class OpenLLM(LLM):
         model_id: Optional[str] = ...,
         embedded: Literal[True, False] = ...,
         **llm_kwargs: Any,
-    ) -> None:
+    ) -> None: ...
-        ...
 
     @overload
     def __init__(
@@ -118,8 +117,7 @@ class OpenLLM(LLM):
         server_url: str = ...,
         server_type: Literal["grpc", "http"] = ...,
         **llm_kwargs: Any,
-    ) -> None:
+    ) -> None: ...
-        ...
 
     def __init__(
         self,

libs/community/langchain_community/llms/rwkv.py

@@ -3,6 +3,7 @@
 Based on https://github.com/saharNooby/rwkv.cpp/blob/master/rwkv/chat_with_bot.py
          https://github.com/BlinkDL/ChatRWKV/blob/main/v2/chat.py
 """
+
 from typing import Any, Dict, List, Mapping, Optional, Set
 
 from langchain_core.callbacks import CallbackManagerForLLMRun