[CHORE] clean up typos across the code

.github/workflows/pr.yml

@@ -194,6 +194,18 @@ jobs:
     uses: ./.github/workflows/_go-tests.yml
     secrets: inherit
 
+  typo-check:
+    name: Check for typos
+    runs-on: blacksmith-4vcpu-ubuntu-2404
+    steps:
+    - name: Checkout chroma-core/chroma
+      uses: actions/checkout@v4
+
+    - name: Run typo check
+      uses: crate-ci/[email protected]
+      with:
+        config: typos.toml
+
   lint:
     name: Lint
     runs-on: blacksmith-4vcpu-ubuntu-2404

.github/workflows/release-dev-javascript-client.yml

@@ -25,7 +25,7 @@ jobs:
             echo "Push to main branch, releasing dev version to GH packages"
             echo "NPM_SCRIPT=release_dev" >> "$GITHUB_ENV"
           else
-            echo "The ref does not point to main, exiting workflow" # we alredy make the check above but this is a good practice
+            echo "The ref does not point to main, exiting workflow" # we already make the check above but this is a good practice
             exit 1
           fi
       - name: Checkout

bin/test.py

@@ -1,5 +1,5 @@
 # Sanity check script to ensure that the Chroma client can connect
-# and is capable of recieving data.
+# and is capable of receiving data.
 import chromadb
 
 # run in in-memory mode

chromadb/__init__.py

@@ -148,7 +148,7 @@ def EphemeralClient(
         settings = Settings()
     settings.is_persistent = False
 
-    # Make sure paramaters are the correct types -- users can pass anything.
+    # Make sure parameters are the correct types -- users can pass anything.
     tenant = str(tenant)
     database = str(database)
 
@@ -175,7 +175,7 @@ def PersistentClient(
     settings.persist_directory = str(path)
     settings.is_persistent = True
 
-    # Make sure paramaters are the correct types -- users can pass anything.
+    # Make sure parameters are the correct types -- users can pass anything.
     tenant = str(tenant)
     database = str(database)
 
@@ -189,7 +189,7 @@ def RustClient(
     database: str = DEFAULT_DATABASE,
 ) -> ClientAPI:
     """
-    Creates an ephemeral or persistance instance of Chroma that saves to disk.
+    Creates an ephemeral or persistent instance of Chroma that saves to disk.
     This is useful for testing and development, but not recommended for production use.
 
     Args:
@@ -204,7 +204,7 @@ def RustClient(
     settings.is_persistent = path is not None
     settings.persist_directory = path or ""
 
-    # Make sure paramaters are the correct types -- users can pass anything.
+    # Make sure parameters are the correct types -- users can pass anything.
     tenant = str(tenant)
     database = str(database)
 
@@ -353,7 +353,7 @@ def CloudClient(
     if settings is None:
         settings = Settings()
 
-    # Make sure paramaters are the correct types -- users can pass anything.
+    # Make sure parameters are the correct types -- users can pass anything.
     tenant = tenant or os.environ.get("CHROMA_TENANT")
     if tenant is not None:
         tenant = str(tenant)
@@ -392,7 +392,7 @@ def Client(
     database: The database to use for this client. Defaults to the default database.
     """
 
-    # Make sure paramaters are the correct types -- users can pass anything.
+    # Make sure parameters are the correct types -- users can pass anything.
     tenant = str(tenant)
     database = str(database)
 

chromadb/api/models/AsyncCollection.py

@@ -464,7 +464,7 @@ async def delete(
 
         Args:
             ids: The ids of the embeddings to delete
-            where: A Where type dict used to filter the delection by. E.g. `{"$and": [{"color" : "red"}, {"price": {"$gte": 4.20}}]}`. Optional.
+            where: A Where type dict used to filter the deletion by. E.g. `{"$and": [{"color" : "red"}, {"price": {"$gte": 4.20}}]}`. Optional.
             where_document: A WhereDocument type dict used to filter the deletion by the document content. E.g. `{"$contains": "hello"}`. Optional.
 
         Returns:

chromadb/api/models/Collection.py

@@ -469,7 +469,7 @@ def delete(
 
         Args:
             ids: The ids of the embeddings to delete
-            where: A Where type dict used to filter the delection by. E.g. `{"$and": [{"color" : "red"}, {"price": {"$gte": 4.20}]}}`. Optional.
+            where: A Where type dict used to filter the deletion by. E.g. `{"$and": [{"color" : "red"}, {"price": {"$gte": 4.20}]}}`. Optional.
             where_document: A WhereDocument type dict used to filter the deletion by the document content. E.g. `{"$contains": "hello"}`. Optional.
 
         Returns:

chromadb/api/models/CollectionCommon.py

@@ -251,7 +251,7 @@ def _validate_and_prepare_get_request(
             validate_ids(ids=unpacked_ids)
 
         validate_filter_set(filter_set=filters)
-        validate_include(include=include, dissalowed=["distances"])
+        validate_include(include=include, disallowed=["distances"])
 
         if "data" in include and self._data_loader is None:
             raise ValueError(
@@ -260,7 +260,7 @@ def _validate_and_prepare_get_request(
 
         # Prepare
         request_include = include
-        # We need to include uris in the result from the API to load datas
+        # We need to include uris in the result from the API to load data
         if "data" in include and "uris" not in include:
             request_include.append("uris")
 
@@ -322,7 +322,7 @@ def _validate_and_prepare_query_request(
         request_where = filters["where"]
         request_where_document = filters["where_document"]
 
-        # We need to manually include uris in the result from the API to load datas
+        # We need to manually include uris in the result from the API to load data
         request_include = include
         if "data" in request_include and "uris" not in request_include:
             request_include.append("uris")

chromadb/api/rust.py

@@ -86,7 +86,7 @@ def __init__(self, system: System):
     @override
     def start(self) -> None:
         # Construct the SqliteConfig
-        # TOOD: We should add a "config converter"
+        # TODO: We should add a "config converter"
         if self._system.settings.require("is_persistent"):
             persist_path = self._system.settings.require("persist_directory")
             sqlite_persist_path = persist_path + "/chroma.sqlite3"

chromadb/api/segment.py

@@ -428,7 +428,7 @@ def _search(
         database: str = DEFAULT_DATABASE,
     ) -> SearchResult:
         raise NotImplementedError(
-            "Seach is not implemented for SegmentAPI"
+            "Search is not implemented for SegmentAPI"
         )
 
     @trace_method("SegmentAPI.delete_collection", OpenTelemetryGranularity.OPERATION)

chromadb/api/types.py

@@ -1029,7 +1029,7 @@ def validate_where_document(where_document: WhereDocument) -> None:
             )
 
 
-def validate_include(include: Include, dissalowed: Optional[Include] = None) -> None:
+def validate_include(include: Include, disallowed: Optional[Include] = None) -> None:
     """Validates include to ensure it is a list of strings. Since get does not allow distances, allow_distances is used
     to control if distances is allowed"""
 
@@ -1046,9 +1046,9 @@ def validate_include(include: Include, dissalowed: Optional[Include] = None) ->
                 f"Expected include item to be one of {', '.join(valid_items)}, got {item}"
             )
 
-        if dissalowed is not None and any(item == e for e in dissalowed):
+        if disallowed is not None and any(item == e for e in disallowed):
             raise ValueError(
-                f"Include item cannot be one of {', '.join(dissalowed)}, got {item}"
+                f"Include item cannot be one of {', '.join(disallowed)}, got {item}"
             )
 
 

chromadb/auth/token_authn/__init__.py

@@ -39,7 +39,7 @@
 
 class TokenTransportHeader(str, Enum):
     """
-    Accceptable token transport headers.
+    Acceptable token transport headers.
     """
 
     # I don't love having this enum here -- it's weird to have an enum

chromadb/config.py

@@ -491,7 +491,7 @@ def reset_state(self) -> None:
 
 
 def get_class(fqn: str, type: Type[C]) -> Type[C]:
-    """Given a fully qualifed class name, import the module and return the class"""
+    """Given a fully qualified class name, import the module and return the class"""
     module_name, class_name = fqn.rsplit(".", 1)
     module = importlib.import_module(module_name)
     cls = getattr(module, class_name)

chromadb/db/base.py

@@ -111,7 +111,7 @@ def param(self, idx: int) -> pypika.Parameter:
 
 class ParameterValue(pypika.Parameter):  # type: ignore
     """
-    Wrapper class for PyPika paramters that allows the values for Parameters
+    Wrapper class for PyPika parameters that allows the values for Parameters
     to be expressed inline while building a query. See get_sql() for
     detailed usage information.
     """

chromadb/db/migrations.py

@@ -75,7 +75,7 @@ class MigratableDB(SqlDB):
     importlib_resources.
 
     All migrations in the same directory are assumed to be dependent on previous
-    migrations in the same directory, where "previous" is defined on lexographical
+    migrations in the same directory, where "previous" is defined on lexicographical
     ordering of filenames.
 
     Migrations have a ascending numeric version number and a hash of the file contents.

chromadb/db/mixins/sysdb.py

@@ -857,7 +857,7 @@ def _insert_metadata(
     ) -> None:
         # It would be cleaner to use something like ON CONFLICT UPDATE here But that is
         # very difficult to do in a portable way (e.g sqlite and postgres have
-        # completely different sytnax)
+        # completely different syntax)
         add_attributes_to_current_span(
             {
                 "num_keys": len(metadata),