Fix spelling errors; add spellcheck to precommit

Author: abrookins

.pre-commit-config.yaml

@@ -5,4 +5,13 @@ repos:
         name: Run pre-commit checks (format, sort-imports, check-mypy)
         entry: bash -c 'poetry run format && poetry run sort-imports && poetry run check-mypy'
         language: system
-        pass_filenames: false
+        pass_filenames: false
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.2.6
+    hooks:
+      - id: codespell
+        name: Check spelling
+        args:
+          - --write-changes
+          - --skip=*.pyc,*.pyo,*.lock,*.git,*.mypy_cache,__pycache__,*.egg-info,.pytest_cache,docs/_build,env,venv,.venv
+          - --ignore-words-list=enginee

pyproject.toml

@@ -123,3 +123,5 @@ asyncio_mode = "auto"
 [tool.mypy]
 warn_unused_configs = true
 ignore_missing_imports = true
+exclude = ["env", "venv", ".venv"]
+

redisvl/extensions/cache/llm/semantic.py

@@ -385,7 +385,7 @@ def check(
         .. code-block:: python
 
             response = cache.check(
-                prompt="What is the captial city of France?"
+                prompt="What is the capital city of France?"
             )
         """
         if not any([prompt, vector]):
@@ -476,7 +476,7 @@ async def acheck(
         .. code-block:: python
 
             response = await cache.acheck(
-                prompt="What is the captial city of France?"
+                prompt="What is the capital city of France?"
             )
         """
         aindex = await self._get_async_index()
@@ -588,7 +588,7 @@ def store(
         .. code-block:: python
 
             key = cache.store(
-                prompt="What is the captial city of France?",
+                prompt="What is the capital city of France?",
                 response="Paris",
                 metadata={"city": "Paris", "country": "France"}
             )
@@ -656,7 +656,7 @@ async def astore(
         .. code-block:: python
 
             key = await cache.astore(
-                prompt="What is the captial city of France?",
+                prompt="What is the capital city of France?",
                 response="Paris",
                 metadata={"city": "Paris", "country": "France"}
             )

redisvl/extensions/constants.py

@@ -1,7 +1,7 @@
 """
 Constants used within the extension classes SemanticCache, BaseMessageHistory,
 MessageHistory, SemanticMessageHistory and SemanticRouter.
-These constants are also used within theses classes corresponding schema.
+These constants are also used within these classes' corresponding schemas.
 """
 
 # BaseMessageHistory

redisvl/extensions/message_history/base_history.py

@@ -60,7 +60,7 @@ def get_recent(
         raw: bool = False,
         session_tag: Optional[str] = None,
     ) -> Union[List[str], List[Dict[str, str]]]:
-        """Retreive the recent conversation history in sequential order.
+        """Retrieve the recent conversation history in sequential order.
 
         Args:
             top_k (int): The number of previous exchanges to return. Default is 5.

redisvl/extensions/message_history/semantic_history.py

@@ -248,7 +248,7 @@ def get_recent(
         raw: bool = False,
         session_tag: Optional[str] = None,
     ) -> Union[List[str], List[Dict[str, str]]]:
-        """Retreive the recent message history in sequential order.
+        """Retrieve the recent message history in sequential order.
 
         Args:
             top_k (int): The number of previous exchanges to return. Default is 5.

redisvl/query/filter.py

@@ -624,7 +624,7 @@ def __str__(self) -> str:
         if not self._filter and not self._operator:
             raise ValueError("Improperly initialized FilterExpression")
 
-        # if theres an operator, combine expressions accordingly
+        # if there's an operator, combine expressions accordingly
         if self._operator:
             if not isinstance(self._left, FilterExpression) or not isinstance(
                 self._right, FilterExpression

redisvl/utils/vectorize/text/custom.py

@@ -41,7 +41,7 @@ class CustomTextVectorizer(BaseVectorizer):
     This vectorizer is designed to accept a provided callable text vectorizer and
     provides a class definition to allow for compatibility with RedisVL.
     The vectorizer may support both synchronous and asynchronous operations which
-    allows for batch processing of texts, but at a minimum only syncronous embedding
+    allows for batch processing of texts, but at a minimum only synchronous embedding
     is required to satisfy the 'embed()' method.
 
     You can optionally enable caching to improve performance when generating
@@ -94,8 +94,8 @@ def __init__(
         Args:
             embed (Callable): a Callable function that accepts a string object and returns a list of floats.
             embed_many (Optional[Callable]): a Callable function that accepts a list of string objects and returns a list containing lists of floats. Defaults to None.
-            aembed (Optional[Callable]): an asyncronous Callable function that accepts a string object and returns a lists of floats. Defaults to None.
-            aembed_many (Optional[Callable]): an asyncronous Callable function that accepts a list of string objects and returns a list containing lists of floats. Defaults to None.
+            aembed (Optional[Callable]): an asynchronous Callable function that accepts a string object and returns a lists of floats. Defaults to None.
+            aembed_many (Optional[Callable]): an asynchronous Callable function that accepts a list of string objects and returns a list containing lists of floats. Defaults to None.
             dtype (str): the default datatype to use when embedding text as byte arrays.
                 Used when setting `as_buffer=True` in calls to embed() and embed_many().
                 Defaults to 'float32'.

tests/integration/test_llmcache.py

@@ -744,7 +744,7 @@ def test_cache_filtering(cache_with_filters):
     )
     assert len(results) == 4
 
-    # test no results are returned if we pass a nonexistant tag
+    # test no results are returned if we pass a nonexistent tag
     bad_filter = Tag("label") == "bad tag"
     results = cache_with_filters.check(
         "test prompt 1", filter_expression=bad_filter, num_results=5

tests/unit/test_aggregation_types.py

@@ -26,7 +26,7 @@ def test_aggregate_hybrid_query():
 
     assert isinstance(hybrid_query, AggregateRequest)
 
-    # Check defaut properties
+    # Check default properties
     assert hybrid_query._text == sample_text
     assert hybrid_query._text_field == text_field_name
     assert hybrid_query._vector == sample_vector

tests/unit/test_filter.py

@@ -38,7 +38,7 @@
         (
             "==",
             ["hypen-tag", "under_score", "dot.tag"],
-            "@tag_field:{hypen\\-tag|under_score|dot\\.tag}",
+            "@tag_field:{hyphen\\-tag|under_score|dot\\.tag}",
         ),
         # ...additional unique cases as desired...
     ],

tests/unit/test_query_types.py

@@ -367,9 +367,9 @@ def test_string_filter_expressions(query):
     assert query.query_string().__contains__("hello world")
 
     # Optional flag
-    query.set_filter("~(@desciption:(hello | world))")
-    assert query._filter_expression == "~(@desciption:(hello | world))"
-    assert query.query_string().__contains__("~(@desciption:(hello | world))")
+    query.set_filter("~(@description:(hello | world))")
+    assert query._filter_expression == "~(@description:(hello | world))"
+    assert query.query_string().__contains__("~(@description:(hello | world))")
 
 
 def test_vector_query_hybrid_policy():