[BLD] Python & misc lint fixes (chroma-core#2046)

Author: codetheweb

Diff for: .github/workflows/chroma-lint.yml

@@ -13,5 +13,15 @@ jobs:
       - name: Install pre-commit
         run: python -m pip install -r requirements_dev.txt
       - name: Run pre-commit
-        # todo: remove || true once lint issues are resolved
-        run: pre-commit run --all-files || true
+        run: |
+          pre-commit run --all-files trailing-whitespace
+          pre-commit run --all-files mixed-line-ending
+          pre-commit run --all-files end-of-file-fixer
+          pre-commit run --all-files requirements-txt-fixer
+          pre-commit run --all-files check-xml
+          pre-commit run --all-files check-merge-conflict
+          pre-commit run --all-files check-case-conflict
+          pre-commit run --all-files check-docstring-first
+          pre-commit run --all-files black
+          pre-commit run --all-files flake8
+          pre-commit run --all-files prettier

Diff for: .github/workflows/release-helm-chart.yml

@@ -27,4 +27,4 @@ jobs:
             workflow_id: 'copy-oss-helm.yaml',
             ref: 'main'
           })
-          console.log(result)
+          console.log(result)

Diff for: .pre-commit-config.yaml

@@ -1,11 +1,12 @@
-exclude: 'chromadb/proto/(chroma_pb2|coordinator_pb2)\.(py|pyi|py_grpc\.py)' # Generated files
+exclude: 'chromadb/proto/(chroma_pb2|coordinator_pb2|logservice_pb2)\.(py|pyi|py_grpc\.py)' # Generated files
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.5.0
     hooks:
       - id: trailing-whitespace
       - id: mixed-line-ending
       - id: end-of-file-fixer
+        exclude: "go/migrations"
       - id: requirements-txt-fixer
       - id: check-yaml
         args: ["--allow-multiple-documents"]
@@ -32,9 +33,26 @@ repos:
     rev: "v1.2.0"
     hooks:
       - id: mypy
-        args: [--strict, --ignore-missing-imports, --follow-imports=silent, --disable-error-code=type-abstract, --config-file=./pyproject.toml]
-        additional_dependencies: ["types-requests", "pydantic", "overrides", "hypothesis", "pytest", "pypika", "numpy", "types-protobuf", "kubernetes"]
-
+        args:
+          [
+            --strict,
+            --ignore-missing-imports,
+            --follow-imports=silent,
+            --disable-error-code=type-abstract,
+            --config-file=./pyproject.toml,
+          ]
+        additional_dependencies:
+          [
+            "types-requests",
+            "pydantic",
+            "overrides",
+            "hypothesis",
+            "pytest",
+            "pypika",
+            "numpy",
+            "types-protobuf",
+            "kubernetes",
+          ]
 
   - repo: https://github.com/pre-commit/mirrors-prettier
     rev: "v3.1.0"

Diff for: .vscode/settings.json

@@ -132,4 +132,4 @@
     "unordered_set": "cpp",
     "algorithm": "cpp"
   },
-}
+}

Diff for: Dockerfile

@@ -38,4 +38,4 @@ ENV CHROMA_TIMEOUT_KEEP_ALIVE 30
 EXPOSE 8000
 
 ENTRYPOINT ["/docker_entrypoint.sh"]
-CMD [ "--workers ${CHROMA_WORKERS} --host ${CHROMA_HOST_ADDR} --port ${CHROMA_HOST_PORT} --proxy-headers --log-config ${CHROMA_LOG_CONFIG} --timeout-keep-alive ${CHROMA_TIMEOUT_KEEP_ALIVE}"]
+CMD [ "--workers ${CHROMA_WORKERS} --host ${CHROMA_HOST_ADDR} --port ${CHROMA_HOST_PORT} --proxy-headers --log-config ${CHROMA_LOG_CONFIG} --timeout-keep-alive ${CHROMA_TIMEOUT_KEEP_ALIVE}"]

Diff for: chromadb/__init__.py

@@ -246,7 +246,9 @@ def CloudClient(
     # Always use SSL for cloud
     settings.chroma_server_ssl_enabled = enable_ssl
 
-    settings.chroma_client_auth_provider = "chromadb.auth.token_authn.TokenAuthClientProvider"
+    settings.chroma_client_auth_provider = (
+        "chromadb.auth.token_authn.TokenAuthClientProvider"
+    )
     settings.chroma_client_auth_credentials = api_key
     settings.chroma_auth_token_transport_header = (
         TokenTransportHeader.X_CHROMA_TOKEN.name

Diff for: chromadb/api/models/Collection.py

@@ -382,7 +382,8 @@ def modify(
             validate_metadata(metadata)
             if "hnsw:space" in metadata:
                 raise ValueError(
-                    "Changing the distance function of a collection once it is created is not supported currently.")
+                    "Changing the distance function of a collection once it is created is not supported currently."
+                )
 
         self._client._modify(id=self.id, new_name=name, new_metadata=metadata)
         if name:

Diff for: chromadb/auth/__init__.py

@@ -33,6 +33,7 @@ class ClientAuthProvider(Component):
     client requests. Client implementations (in our case, just the FastAPI
     client) must inject these headers into their requests.
     """
+
     def __init__(self, system: System) -> None:
         super().__init__(system)
 
@@ -52,6 +53,7 @@ class UserIdentity:
     _all_ information known about the user, and the AuthorizationProvider is
     responsible for making decisions based on that information.
     """
+
     user_id: str
     tenant: Optional[str] = None
     databases: Optional[List[str]] = None
@@ -71,20 +73,18 @@ class ServerAuthenticationProvider(Component):
     The ServerAuthenticationProvider should return a UserIdentity object if the
     request is authenticated for use by the ServerAuthorizationProvider.
     """
+
     def __init__(self, system: System) -> None:
         super().__init__(system)
         self._ignore_auth_paths: Dict[
             str, List[str]
         ] = system.settings.chroma_server_auth_ignore_paths
         self.overwrite_singleton_tenant_database_access_from_auth = (
-            system.settings.
-            chroma_overwrite_singleton_tenant_database_access_from_auth
+            system.settings.chroma_overwrite_singleton_tenant_database_access_from_auth
         )
 
     @abstractmethod
-    def authenticate_or_raise(
-        self, headers: Headers
-    ) -> UserIdentity:
+    def authenticate_or_raise(self, headers: Headers) -> UserIdentity:
         pass
 
     def ignore_operation(self, verb: str, path: str) -> bool:
@@ -100,13 +100,11 @@ def read_creds_or_creds_file(self) -> List[str]:
         _creds = None
 
         if self._system.settings.chroma_server_authn_credentials_file:
-            _creds_file = str(self._system.settings[
-                "chroma_server_authn_credentials_file"
-            ])
+            _creds_file = str(
+                self._system.settings["chroma_server_authn_credentials_file"]
+            )
         if self._system.settings.chroma_server_authn_credentials:
-            _creds = str(self._system.settings[
-                "chroma_server_authn_credentials"
-            ])
+            _creds = str(self._system.settings["chroma_server_authn_credentials"])
         if not _creds_file and not _creds:
             raise ValueError(
                 "No credentials file or credentials found in "
@@ -122,9 +120,7 @@ def read_creds_or_creds_file(self) -> List[str]:
         elif _creds_file:
             with open(_creds_file, "r") as f:
                 return f.readlines()
-        raise ValueError(
-            "Should never happen"
-        )
+        raise ValueError("Should never happen")
 
     def singleton_tenant_database_if_applicable(
         self, user: Optional[UserIdentity]
@@ -144,15 +140,13 @@ def singleton_tenant_database_if_applicable(
         - If the user has access to multiple tenants and/or databases this
           function will return None for the corresponding value(s).
         """
-        if (not self.overwrite_singleton_tenant_database_access_from_auth or
-                not user):
+        if not self.overwrite_singleton_tenant_database_access_from_auth or not user:
             return None, None
         tenant = None
         database = None
         if user.tenant and user.tenant != "*":
             tenant = user.tenant
-        if (user.databases and len(user.databases) == 1 and
-                user.databases[0] != "*"):
+        if user.databases and len(user.databases) == 1 and user.databases[0] != "*":
             database = user.databases[0]
         return tenant, database
 
@@ -161,6 +155,7 @@ class AuthzAction(str, Enum):
     """
     The set of actions that can be authorized by the authorization provider.
     """
+
     RESET = "system:reset"
     CREATE_TENANT = "tenant:create_tenant"
     GET_TENANT = "tenant:get_tenant"
@@ -187,6 +182,7 @@ class AuthzResource:
     """
     The resource being accessed in an authorization request.
     """
+
     tenant: Optional[str]
     database: Optional[str]
     collection: Optional[str]
@@ -202,23 +198,21 @@ class ServerAuthorizationProvider(Component):
     ServerAuthorizationProvider should raise an exception if the request is not
     authorized.
     """
+
     def __init__(self, system: System) -> None:
         super().__init__(system)
 
     @abstractmethod
-    def authorize_or_raise(self,
-                           user: UserIdentity,
-                           action: AuthzAction,
-                           resource: AuthzResource) -> None:
+    def authorize_or_raise(
+        self, user: UserIdentity, action: AuthzAction, resource: AuthzResource
+    ) -> None:
         pass
 
     def read_config_or_config_file(self) -> List[str]:
         _config_file = None
         _config = None
         if self._system.settings.chroma_server_authz_config_file:
-            _config_file = self._system.settings[
-                "chroma_server_authz_config_file"
-            ]
+            _config_file = self._system.settings["chroma_server_authz_config_file"]
         if self._system.settings.chroma_server_authz_config:
             _config = str(self._system.settings["chroma_server_authz_config"])
         if not _config_file and not _config:
@@ -231,10 +225,8 @@ def read_config_or_config_file(self) -> List[str]:
                 "Please provide only one."
             )
         if _config:
-            return [c for c in _config.split('\n') if c]
+            return [c for c in _config.split("\n") if c]
         elif _config_file:
             with open(_config_file, "r") as f:
                 return f.readlines()
-        raise ValueError(
-            "Should never happen"
-        )
+        raise ValueError("Should never happen")

Diff for: chromadb/auth/basic_authn/__init__.py

@@ -1,6 +1,5 @@
 import base64
 import bcrypt
-import importlib
 import logging
 
 from fastapi import HTTPException
@@ -31,25 +30,20 @@ class BasicAuthClientProvider(ClientAuthProvider):
     Client auth provider for basic auth. The credentials are passed as a
     base64-encoded string in the Authorization header prepended with "Basic ".
     """
+
     def __init__(self, system: System) -> None:
         super().__init__(system)
         self._settings = system.settings
         system.settings.require("chroma_client_auth_credentials")
-        self._creds = SecretStr(
-            str(system.settings.chroma_client_auth_credentials)
-        )
+        self._creds = SecretStr(str(system.settings.chroma_client_auth_credentials))
 
     @override
     def authenticate(self) -> ClientAuthHeaders:
         encoded = base64.b64encode(
             f"{self._creds.get_secret_value()}".encode("utf-8")
-        ).decode(
-            "utf-8"
-        )
+        ).decode("utf-8")
         return {
-            "Authorization": SecretStr(
-                f"Basic {encoded}"
-            ),
+            "Authorization": SecretStr(f"Basic {encoded}"),
         }
 
 
@@ -62,6 +56,7 @@ class BasicAuthenticationServerProvider(ServerAuthenticationProvider):
     Expects tokens to be passed as a base64-encoded string in the Authorization
     header prepended with "Basic".
     """
+
     def __init__(self, system: System) -> None:
         super().__init__(system)
         self._settings = system.settings
@@ -73,8 +68,12 @@ def __init__(self, system: System) -> None:
             if not line.strip():
                 continue
             _raw_creds = [v for v in line.strip().split(":")]
-            if (_raw_creds and _raw_creds[0] and
-                    len(_raw_creds) != 2 or not all(_raw_creds)):
+            if (
+                _raw_creds
+                and _raw_creds[0]
+                and len(_raw_creds) != 2
+                or not all(_raw_creds)
+            ):
                 raise ValueError(
                     f"Invalid htpasswd credentials found: {_raw_creds}. "
                     "Lines must be exactly <username>:<bcrypt passwd>."
@@ -89,12 +88,11 @@ def __init__(self, system: System) -> None:
                 )
             self._creds[username] = SecretStr(password)
 
-    @trace_method("BasicAuthenticationServerProvider.authenticate",
-                  OpenTelemetryGranularity.ALL)
+    @trace_method(
+        "BasicAuthenticationServerProvider.authenticate", OpenTelemetryGranularity.ALL
+    )
     @override
-    def authenticate_or_raise(
-        self, headers: Headers
-    ) -> UserIdentity:
+    def authenticate_or_raise(self, headers: Headers) -> UserIdentity:
         try:
             _auth_header = headers["Authorization"]
             _auth_header = _auth_header.replace("Basic ", "")
@@ -115,7 +113,6 @@ def authenticate_or_raise(
 
         except Exception as e:
             logger.error(
-                "BasicAuthenticationServerProvider.authenticate "
-                f"failed: {repr(e)}"
+                "BasicAuthenticationServerProvider.authenticate " f"failed: {repr(e)}"
             )
         raise HTTPException(status_code=403, detail="Forbidden")

Diff for: chromadb/auth/simple_rbac_authz/__init__.py

@@ -17,6 +17,7 @@
 )
 
 from hypothesis import Phase, settings
+
 settings.register_profile("ci", phases=[Phase.generate, Phase.target])
 
 
@@ -33,12 +34,11 @@ class SimpleRBACAuthorizationProvider(ServerAuthorizationProvider):
     For an example of an RBAC configuration file, see
     examples/basic_functionality/authz/authz.yaml.
     """
+
     def __init__(self, system: System) -> None:
         super().__init__(system)
         self._settings = system.settings
-        self._config = yaml.safe_load(
-            '\n'.join(self.read_config_or_config_file())
-        )
+        self._config = yaml.safe_load("\n".join(self.read_config_or_config_file()))
 
         # We favor preprocessing here to avoid having to parse the config file
         # on every request. This AuthorizationProvider does not support
@@ -51,23 +51,22 @@ def __init__(self, system: System) -> None:
             _actions = self._config["roles_mapping"][user["role"]]["actions"]
             self._permissions[user["id"]] = set(_actions)
         logger.info(
-            "Authorization Provider SimpleRBACAuthorizationProvider "
-            "initialized"
+            "Authorization Provider SimpleRBACAuthorizationProvider " "initialized"
         )
 
     @trace_method(
         "SimpleRBACAuthorizationProvider.authorize",
         OpenTelemetryGranularity.ALL,
     )
     @override
-    def authorize_or_raise(self,
-                           user: UserIdentity,
-                           action: AuthzAction,
-                           resource: AuthzResource) -> None:
-
+    def authorize_or_raise(
+        self, user: UserIdentity, action: AuthzAction, resource: AuthzResource
+    ) -> None:
         policy_decision = False
-        if (user.user_id in self._permissions and
-                action in self._permissions[user.user_id]):
+        if (
+            user.user_id in self._permissions
+            and action in self._permissions[user.user_id]
+        ):
             policy_decision = True
 
         logger.debug(