multiple: fix codespell (v0.1) (#22785)

docs/docs/integrations/providers/langchain_decorators.mdx

@@ -205,7 +205,7 @@ For chat models is very useful to define prompt as a set of message templates...
 def simulate_conversation(human_input:str, agent_role:str="a pirate"):
     """
     ## System message
-     - note the `:system` sufix inside the <prompt:_role_> tag
+     - note the `:system` suffix inside the <prompt:_role_> tag
      
 
     ```<prompt:system>

libs/community/langchain_community/retrievers/google_cloud_documentai_warehouse.py

@@ -32,7 +32,7 @@ class GoogleDocumentAIWarehouseRetriever(BaseRetriever):
 
     Documents should be created and documents should be uploaded
         in a separate flow, and this retriever uses only Document AI
-        schema_id provided to search for revelant documents.
+        schema_id provided to search for relevant documents.
 
     More info: https://cloud.google.com/document-ai-warehouse.
     """

libs/community/langchain_community/tools/e2b_data_analysis/unparse.py

@@ -543,7 +543,7 @@ class Unparser:
         "Is": "is",
         "IsNot": "is not",
         "In": "in",
-        "NotIn": "not in",
+        "NotIn": "not in",  # codespell:ignore
     }
 
     def _Compare(self, t):

libs/community/langchain_community/vectorstores/milvus.py

@@ -62,7 +62,7 @@ class Milvus(VectorStore):
         primary_field (str): Name of the primary key field. Defaults to "pk".
         text_field (str): Name of the text field. Defaults to "text".
         vector_field (str): Name of the vector field. Defaults to "vector".
-        metadata_field (str): Name of the metadta field. Defaults to None.
+        metadata_field (str): Name of the metadata field. Defaults to None.
             When metadata_field is specified,
             the document's metadata will store as json.
 

libs/community/tests/integration_tests/graphs/test_age_graph.py

@@ -330,7 +330,7 @@ class TestAGEGraph(unittest.TestCase):
         graph.refresh_schema()
 
         # check that schema is refreshed
-        self.assertIn(
+        self.assertIn(  # codespell:ignore
             re.sub(r"\s", "", graph.get_schema),
             [re.sub(r"\s", "", x) for x in expected_possibilities],
         )

libs/community/tests/unit_tests/callbacks/fake_callback_handler.py

@@ -21,7 +21,7 @@ class BaseFakeCallbackHandler(BaseModel):
     ignore_retriever_: bool = False
     ignore_chat_model_: bool = False
 
-    # to allow for similar callback handlers that are not technicall equal
+    # to allow for similar callback handlers that are not technically equal
     fake_id: Union[str, None] = None
 
     # add finer-grained counters for easier debugging of failing tests

libs/core/tests/unit_tests/fake/callbacks.py

@@ -1,4 +1,5 @@
 """A fake callback handler for testing purposes."""
+
 from itertools import chain
 from typing import Any, Dict, List, Optional, Union
 from uuid import UUID
@@ -22,7 +23,7 @@ class BaseFakeCallbackHandler(BaseModel):
     ignore_retriever_: bool = False
     ignore_chat_model_: bool = False
 
-    # to allow for similar callback handlers that are not technicall equal
+    # to allow for similar callback handlers that are not technically equal
     fake_id: Union[str, None] = None
 
     # add finer-grained counters for easier debugging of failing tests

libs/langchain/langchain/evaluation/scoring/prompt.py

@@ -1,6 +1,6 @@
 """Prompts for scoring the outputs of a models for a given question.
 
-This prompt is used to socre the responses and evaluate how it follows the instructions
+This prompt is used to score the responses and evaluate how it follows the instructions
 and answers the question. The prompt is based on the paper from
 Zheng, et. al. https://arxiv.org/abs/2306.05685
 """

libs/langchain/tests/unit_tests/callbacks/fake_callback_handler.py

@@ -1,4 +1,5 @@
 """A fake callback handler for testing purposes."""
+
 from itertools import chain
 from typing import Any, Dict, List, Optional, Union
 from uuid import UUID
@@ -21,7 +22,7 @@ class BaseFakeCallbackHandler(BaseModel):
     ignore_retriever_: bool = False
     ignore_chat_model_: bool = False
 
-    # to allow for similar callback handlers that are not technicall equal
+    # to allow for similar callback handlers that are not technically equal
     fake_id: Union[str, None] = None
 
     # add finer-grained counters for easier debugging of failing tests

libs/partners/anthropic/tests/unit_tests/_utils.py

@@ -19,7 +19,7 @@ class BaseFakeCallbackHandler(BaseModel):
     ignore_retriever_: bool = False
     ignore_chat_model_: bool = False
 
-    # to allow for similar callback handlers that are not technicall equal
+    # to allow for similar callback handlers that are not technically equal
     fake_id: Union[str, None] = None
 
     # add finer-grained counters for easier debugging of failing tests

libs/partners/openai/tests/unit_tests/fake/callbacks.py

@@ -1,4 +1,5 @@
 """A fake callback handler for testing purposes."""
+
 from itertools import chain
 from typing import Any, Dict, List, Optional, Union
 from uuid import UUID
@@ -22,7 +23,7 @@ class BaseFakeCallbackHandler(BaseModel):
     ignore_retriever_: bool = False
     ignore_chat_model_: bool = False
 
-    # to allow for similar callback handlers that are not technicall equal
+    # to allow for similar callback handlers that are not technically equal
     fake_id: Union[str, None] = None
 
     # add finer-grained counters for easier debugging of failing tests

pyproject.toml

@@ -58,30 +58,29 @@ ipykernel = "^6.29.2"
 [tool.poetry.group.typing.dependencies]
 
 [tool.codespell]
-skip = '.git,*.pdf,*.svg,*.pdf,*.yaml,*.ipynb,poetry.lock,*.min.js,*.css,package-lock.json,example_data,_dist,examples,templates,*.trig'
+skip = '.git,*.pdf,*.svg,*.pdf,*.yaml,*.ipynb,poetry.lock,*.min.js,*.css,package-lock.json,example_data,_dist,examples,templates,*.trig,trulens.mdx'
 # Ignore latin etc
 ignore-regex = '.*(Stati Uniti|Tense=Pres).*'
 # whats is a typo but used frequently in queries so kept as is
 # aapply - async apply
 # unsecure - typo but part of API, decided to not bother for now
-ignore-words-list = 'momento,collison,ned,foor,reworkd,parth,whats,aapply,mysogyny,unsecure,damon,crate,aadd,symbl,precesses,accademia,nin'
+ignore-words-list = 'momento,collison,ned,foor,reworkd,parth,whats,aapply,mysogyny,unsecure,damon,crate,aadd,symbl,precesses,accademia,nin,checkin'
 
 [tool.ruff]
 extend-include = ["*.ipynb"]
 extend-exclude = [
-    "docs/docs/expression_language/why.ipynb"  # TODO: look into why linter errors
+    "docs/docs/expression_language/why.ipynb", # TODO: look into why linter errors
 ]
 
 [tool.ruff.lint.per-file-ignores]
 "**/{cookbook,docs}/*" = [
-    "E402",  # allow imports to appear anywhere in docs
+    "E402", # allow imports to appear anywhere in docs
-    "F401",  # allow "imported but unused" example code
+    "F401", # allow "imported but unused" example code
-    "F811",  # allow re-importing the same module, so that cells can stay independent
+    "F811", # allow re-importing the same module, so that cells can stay independent
-    "F841",  # allow assignments to variables that are never read -- it's example code
+    "F841", # allow assignments to variables that are never read -- it's example code
 ]
 
 # These files were failing the listed rules at the time ruff was adopted for notebooks.
 # Don't require them to change at once, though we should look into them eventually.
 "cookbook/gymnasium_agent_simulation.ipynb" = ["F821"]
 "docs/docs/integrations/document_loaders/tensorflow_datasets.ipynb" = ["F821"]
-