mistralai 1.2.5__py3-none-any.whl → 1.3.0__py3-none-any.whl

mistralai/_version.py

@@ -3,7 +3,7 @@
 import importlib.metadata
 
 __title__: str = "mistralai"
-__version__: str = "1.2.5"
+__version__: str = "1.3.0"
 
 try:
     if __package__ is not None:

mistralai/agents.py

@@ -5,7 +5,7 @@ from mistralai import models, utils
 from mistralai._hooks import HookContext
 from mistralai.types import OptionalNullable, UNSET
 from mistralai.utils import eventstreaming, get_security_from_env
-from typing import Any, List, Optional, Union
+from typing import Any, List, Mapping, Optional, Union
 
 
 class Agents(BaseSDK):
@@ -46,6 +46,7 @@ class Agents(BaseSDK):
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
     ) -> Optional[models.ChatCompletionResponse]:
         r"""Agents Completion
 
@@ -64,6 +65,7 @@ class Agents(BaseSDK):
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
         :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        :param http_headers: Additional headers to set or replace on requests.
         """
         base_url = None
         url_variables = None
@@ -94,7 +96,7 @@ class Agents(BaseSDK):
             agent_id=agent_id,
         )
 
-        req = self.build_request(
+        req = self._build_request(
             method="POST",
             path="/v1/agents/completions",
             base_url=base_url,
@@ -105,6 +107,7 @@ class Agents(BaseSDK):
             request_has_query_params=True,
             user_agent_header="user-agent",
             accept_header_value="application/json",
+            http_headers=http_headers,
             security=self.sdk_configuration.security,
             get_serialized_body=lambda: utils.serialize_request_body(
                 request, False, False, "json", models.AgentsCompletionRequest
@@ -191,6 +194,7 @@ class Agents(BaseSDK):
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
     ) -> Optional[models.ChatCompletionResponse]:
         r"""Agents Completion
 
@@ -209,6 +213,7 @@ class Agents(BaseSDK):
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
         :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        :param http_headers: Additional headers to set or replace on requests.
         """
         base_url = None
         url_variables = None
@@ -239,7 +244,7 @@ class Agents(BaseSDK):
             agent_id=agent_id,
         )
 
-        req = self.build_request_async(
+        req = self._build_request_async(
             method="POST",
             path="/v1/agents/completions",
             base_url=base_url,
@@ -250,6 +255,7 @@ class Agents(BaseSDK):
             request_has_query_params=True,
             user_agent_header="user-agent",
             accept_header_value="application/json",
+            http_headers=http_headers,
             security=self.sdk_configuration.security,
             get_serialized_body=lambda: utils.serialize_request_body(
                 request, False, False, "json", models.AgentsCompletionRequest
@@ -336,6 +342,7 @@ class Agents(BaseSDK):
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
     ) -> Optional[eventstreaming.EventStream[models.CompletionEvent]]:
         r"""Stream Agents completion
 
@@ -356,6 +363,7 @@ class Agents(BaseSDK):
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
         :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        :param http_headers: Additional headers to set or replace on requests.
         """
         base_url = None
         url_variables = None
@@ -386,7 +394,7 @@ class Agents(BaseSDK):
             agent_id=agent_id,
         )
 
-        req = self.build_request(
+        req = self._build_request(
             method="POST",
             path="/v1/agents/completions#stream",
             base_url=base_url,
@@ -397,6 +405,7 @@ class Agents(BaseSDK):
             request_has_query_params=True,
             user_agent_header="user-agent",
             accept_header_value="text/event-stream",
+            http_headers=http_headers,
             security=self.sdk_configuration.security,
             get_serialized_body=lambda: utils.serialize_request_body(
                 request, False, False, "json", models.AgentsCompletionStreamRequest
@@ -487,6 +496,7 @@ class Agents(BaseSDK):
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
     ) -> Optional[eventstreaming.EventStreamAsync[models.CompletionEvent]]:
         r"""Stream Agents completion
 
@@ -507,6 +517,7 @@ class Agents(BaseSDK):
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
         :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        :param http_headers: Additional headers to set or replace on requests.
         """
         base_url = None
         url_variables = None
@@ -537,7 +548,7 @@ class Agents(BaseSDK):
             agent_id=agent_id,
         )
 
-        req = self.build_request_async(
+        req = self._build_request_async(
             method="POST",
             path="/v1/agents/completions#stream",
             base_url=base_url,
@@ -548,6 +559,7 @@ class Agents(BaseSDK):
             request_has_query_params=True,
             user_agent_header="user-agent",
             accept_header_value="text/event-stream",
+            http_headers=http_headers,
             security=self.sdk_configuration.security,
             get_serialized_body=lambda: utils.serialize_request_body(
                 request, False, False, "json", models.AgentsCompletionStreamRequest

mistralai/basesdk.py

@@ -9,7 +9,8 @@ from mistralai._hooks import (
     BeforeRequestContext,
 )
 from mistralai.utils import RetryConfig, SerializedRequestBody, get_body_content
-from typing import Callable, List, Optional, Tuple
+from typing import Callable, List, Mapping, Optional, Tuple
+from urllib.parse import parse_qs, urlparse
 
 
 class BaseSDK:
@@ -18,7 +19,7 @@ class BaseSDK:
     def __init__(self, sdk_config: SDKConfiguration) -> None:
         self.sdk_configuration = sdk_config
 
-    def get_url(self, base_url, url_variables):
+    def _get_url(self, base_url, url_variables):
         sdk_url, sdk_variables = self.sdk_configuration.get_server_details()
 
         if base_url is None:
@@ -29,7 +30,7 @@ class BaseSDK:
 
         return utils.template_url(base_url, url_variables)
 
-    def build_request_async(
+    def _build_request_async(
         self,
         method,
         path,
@@ -48,9 +49,10 @@ class BaseSDK:
             Callable[[], Optional[SerializedRequestBody]]
         ] = None,
         url_override: Optional[str] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
     ) -> httpx.Request:
         client = self.sdk_configuration.async_client
-        return self.build_request_with_client(
+        return self._build_request_with_client(
             client,
             method,
             path,
@@ -67,9 +69,10 @@ class BaseSDK:
             timeout_ms,
             get_serialized_body,
             url_override,
+            http_headers,
         )
 
-    def build_request(
+    def _build_request(
         self,
         method,
         path,
@@ -88,9 +91,10 @@ class BaseSDK:
             Callable[[], Optional[SerializedRequestBody]]
         ] = None,
         url_override: Optional[str] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
     ) -> httpx.Request:
         client = self.sdk_configuration.client
-        return self.build_request_with_client(
+        return self._build_request_with_client(
             client,
             method,
             path,
@@ -107,9 +111,10 @@ class BaseSDK:
             timeout_ms,
             get_serialized_body,
             url_override,
+            http_headers,
         )
 
-    def build_request_with_client(
+    def _build_request_with_client(
         self,
         client,
         method,
@@ -129,13 +134,14 @@ class BaseSDK:
             Callable[[], Optional[SerializedRequestBody]]
         ] = None,
         url_override: Optional[str] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
     ) -> httpx.Request:
         query_params = {}
 
         url = url_override
         if url is None:
             url = utils.generate_url(
-                self.get_url(base_url, url_variables),
+                self._get_url(base_url, url_variables),
                 path,
                 request if request_has_path_params else None,
                 _globals if request_has_path_params else None,
@@ -145,6 +151,12 @@ class BaseSDK:
                 request if request_has_query_params else None,
                 _globals if request_has_query_params else None,
             )
+        else:
+            # Pick up the query parameter from the override so they can be
+            # preserved when building the request later on (necessary as of
+            # httpx 0.28).
+            parsed_override = urlparse(str(url_override))
+            query_params = parse_qs(parsed_override.query, keep_blank_values=True)
 
         headers = utils.get_headers(request, _globals)
         headers["Accept"] = accept_header_value
@@ -159,7 +171,7 @@ class BaseSDK:
             headers = {**headers, **security_headers}
             query_params = {**query_params, **security_query_params}
 
-        serialized_request_body = SerializedRequestBody("application/octet-stream")
+        serialized_request_body = SerializedRequestBody()
         if get_serialized_body is not None:
             rb = get_serialized_body()
             if request_body_required and rb is None:
@@ -178,6 +190,10 @@ class BaseSDK:
         ):
             headers["content-type"] = serialized_request_body.media_type
 
+        if http_headers is not None:
+            for header, value in http_headers.items():
+                headers[header] = value
+
         timeout = timeout_ms / 1000 if timeout_ms is not None else None
 
         return client.build_request(

mistralai/chat.py

@@ -5,7 +5,7 @@ from mistralai import models, utils
 from mistralai._hooks import HookContext
 from mistralai.types import Nullable, OptionalNullable, UNSET
 from mistralai.utils import eventstreaming, get_security_from_env
-from typing import Any, List, Optional, Union
+from typing import Any, List, Mapping, Optional, Union
 
 
 class Chat(BaseSDK):
@@ -17,7 +17,7 @@ class Chat(BaseSDK):
         model: Nullable[str],
         messages: Union[List[models.Messages], List[models.MessagesTypedDict]],
         temperature: OptionalNullable[float] = UNSET,
-        top_p: Optional[float] = 1,
+        top_p: Optional[float] = None,
         max_tokens: OptionalNullable[int] = UNSET,
         stream: Optional[bool] = False,
         stop: Optional[Union[models.Stop, models.StopTypedDict]] = None,
@@ -37,10 +37,11 @@ class Chat(BaseSDK):
         presence_penalty: Optional[float] = None,
         frequency_penalty: Optional[float] = None,
         n: OptionalNullable[int] = UNSET,
-        safe_prompt: Optional[bool] = False,
+        safe_prompt: Optional[bool] = None,
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
     ) -> Optional[models.ChatCompletionResponse]:
         r"""Chat Completion
 
@@ -62,6 +63,7 @@ class Chat(BaseSDK):
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
         :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        :param http_headers: Additional headers to set or replace on requests.
         """
         base_url = None
         url_variables = None
@@ -93,7 +95,7 @@ class Chat(BaseSDK):
             safe_prompt=safe_prompt,
         )
 
-        req = self.build_request(
+        req = self._build_request(
             method="POST",
             path="/v1/chat/completions",
             base_url=base_url,
@@ -104,6 +106,7 @@ class Chat(BaseSDK):
             request_has_query_params=True,
             user_agent_header="user-agent",
             accept_header_value="application/json",
+            http_headers=http_headers,
             security=self.sdk_configuration.security,
             get_serialized_body=lambda: utils.serialize_request_body(
                 request, False, False, "json", models.ChatCompletionRequest
@@ -161,7 +164,7 @@ class Chat(BaseSDK):
         model: Nullable[str],
         messages: Union[List[models.Messages], List[models.MessagesTypedDict]],
         temperature: OptionalNullable[float] = UNSET,
-        top_p: Optional[float] = 1,
+        top_p: Optional[float] = None,
         max_tokens: OptionalNullable[int] = UNSET,
         stream: Optional[bool] = False,
         stop: Optional[Union[models.Stop, models.StopTypedDict]] = None,
@@ -181,10 +184,11 @@ class Chat(BaseSDK):
         presence_penalty: Optional[float] = None,
         frequency_penalty: Optional[float] = None,
         n: OptionalNullable[int] = UNSET,
-        safe_prompt: Optional[bool] = False,
+        safe_prompt: Optional[bool] = None,
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
     ) -> Optional[models.ChatCompletionResponse]:
         r"""Chat Completion
 
@@ -206,6 +210,7 @@ class Chat(BaseSDK):
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
         :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        :param http_headers: Additional headers to set or replace on requests.
         """
         base_url = None
         url_variables = None
@@ -237,7 +242,7 @@ class Chat(BaseSDK):
             safe_prompt=safe_prompt,
         )
 
-        req = self.build_request_async(
+        req = self._build_request_async(
             method="POST",
             path="/v1/chat/completions",
             base_url=base_url,
@@ -248,6 +253,7 @@ class Chat(BaseSDK):
             request_has_query_params=True,
             user_agent_header="user-agent",
             accept_header_value="application/json",
+            http_headers=http_headers,
             security=self.sdk_configuration.security,
             get_serialized_body=lambda: utils.serialize_request_body(
                 request, False, False, "json", models.ChatCompletionRequest
@@ -308,7 +314,7 @@ class Chat(BaseSDK):
             List[models.ChatCompletionStreamRequestMessagesTypedDict],
         ],
         temperature: OptionalNullable[float] = UNSET,
-        top_p: Optional[float] = 1,
+        top_p: Optional[float] = None,
         max_tokens: OptionalNullable[int] = UNSET,
         stream: Optional[bool] = True,
         stop: Optional[
@@ -333,10 +339,11 @@ class Chat(BaseSDK):
         presence_penalty: Optional[float] = None,
         frequency_penalty: Optional[float] = None,
         n: OptionalNullable[int] = UNSET,
-        safe_prompt: Optional[bool] = False,
+        safe_prompt: Optional[bool] = None,
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
     ) -> Optional[eventstreaming.EventStream[models.CompletionEvent]]:
         r"""Stream chat completion
 
@@ -360,6 +367,7 @@ class Chat(BaseSDK):
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
         :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        :param http_headers: Additional headers to set or replace on requests.
         """
         base_url = None
         url_variables = None
@@ -393,7 +401,7 @@ class Chat(BaseSDK):
             safe_prompt=safe_prompt,
         )
 
-        req = self.build_request(
+        req = self._build_request(
             method="POST",
             path="/v1/chat/completions#stream",
             base_url=base_url,
@@ -404,6 +412,7 @@ class Chat(BaseSDK):
             request_has_query_params=True,
             user_agent_header="user-agent",
             accept_header_value="text/event-stream",
+            http_headers=http_headers,
             security=self.sdk_configuration.security,
             get_serialized_body=lambda: utils.serialize_request_body(
                 request, False, False, "json", models.ChatCompletionStreamRequest
@@ -468,7 +477,7 @@ class Chat(BaseSDK):
             List[models.ChatCompletionStreamRequestMessagesTypedDict],
         ],
         temperature: OptionalNullable[float] = UNSET,
-        top_p: Optional[float] = 1,
+        top_p: Optional[float] = None,
         max_tokens: OptionalNullable[int] = UNSET,
         stream: Optional[bool] = True,
         stop: Optional[
@@ -493,10 +502,11 @@ class Chat(BaseSDK):
         presence_penalty: Optional[float] = None,
         frequency_penalty: Optional[float] = None,
         n: OptionalNullable[int] = UNSET,
-        safe_prompt: Optional[bool] = False,
+        safe_prompt: Optional[bool] = None,
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
     ) -> Optional[eventstreaming.EventStreamAsync[models.CompletionEvent]]:
         r"""Stream chat completion
 
@@ -520,6 +530,7 @@ class Chat(BaseSDK):
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
         :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        :param http_headers: Additional headers to set or replace on requests.
         """
         base_url = None
         url_variables = None
@@ -553,7 +564,7 @@ class Chat(BaseSDK):
             safe_prompt=safe_prompt,
         )
 
-        req = self.build_request_async(
+        req = self._build_request_async(
             method="POST",
             path="/v1/chat/completions#stream",
             base_url=base_url,
@@ -564,6 +575,7 @@ class Chat(BaseSDK):
             request_has_query_params=True,
             user_agent_header="user-agent",
             accept_header_value="text/event-stream",
+            http_headers=http_headers,
             security=self.sdk_configuration.security,
             get_serialized_body=lambda: utils.serialize_request_body(
                 request, False, False, "json", models.ChatCompletionStreamRequest

mistralai/classifiers.py

@@ -5,7 +5,7 @@ from mistralai import models, utils
 from mistralai._hooks import HookContext
 from mistralai.types import Nullable, OptionalNullable, UNSET
 from mistralai.utils import get_security_from_env
-from typing import Any, Optional, Union
+from typing import Any, Mapping, Optional, Union
 
 
 class Classifiers(BaseSDK):
@@ -22,6 +22,7 @@ class Classifiers(BaseSDK):
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
     ) -> Optional[models.ClassificationResponse]:
         r"""Moderations
 
@@ -30,6 +31,7 @@ class Classifiers(BaseSDK):
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
         :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        :param http_headers: Additional headers to set or replace on requests.
         """
         base_url = None
         url_variables = None
@@ -44,7 +46,7 @@ class Classifiers(BaseSDK):
             model=model,
         )
 
-        req = self.build_request(
+        req = self._build_request(
             method="POST",
             path="/v1/moderations",
             base_url=base_url,
@@ -55,6 +57,7 @@ class Classifiers(BaseSDK):
             request_has_query_params=True,
             user_agent_header="user-agent",
             accept_header_value="application/json",
+            http_headers=http_headers,
             security=self.sdk_configuration.security,
             get_serialized_body=lambda: utils.serialize_request_body(
                 request, False, False, "json", models.ClassificationRequest
@@ -117,6 +120,7 @@ class Classifiers(BaseSDK):
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
     ) -> Optional[models.ClassificationResponse]:
         r"""Moderations
 
@@ -125,6 +129,7 @@ class Classifiers(BaseSDK):
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
         :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        :param http_headers: Additional headers to set or replace on requests.
         """
         base_url = None
         url_variables = None
@@ -139,7 +144,7 @@ class Classifiers(BaseSDK):
             model=model,
         )
 
-        req = self.build_request_async(
+        req = self._build_request_async(
             method="POST",
             path="/v1/moderations",
             base_url=base_url,
@@ -150,6 +155,7 @@ class Classifiers(BaseSDK):
             request_has_query_params=True,
             user_agent_header="user-agent",
             accept_header_value="application/json",
+            http_headers=http_headers,
             security=self.sdk_configuration.security,
             get_serialized_body=lambda: utils.serialize_request_body(
                 request, False, False, "json", models.ClassificationRequest
@@ -212,6 +218,7 @@ class Classifiers(BaseSDK):
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
     ) -> Optional[models.ClassificationResponse]:
         r"""Moderations Chat
 
@@ -220,6 +227,7 @@ class Classifiers(BaseSDK):
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
         :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        :param http_headers: Additional headers to set or replace on requests.
         """
         base_url = None
         url_variables = None
@@ -236,7 +244,7 @@ class Classifiers(BaseSDK):
             model=model,
         )
 
-        req = self.build_request(
+        req = self._build_request(
             method="POST",
             path="/v1/chat/moderations",
             base_url=base_url,
@@ -247,6 +255,7 @@ class Classifiers(BaseSDK):
             request_has_query_params=True,
             user_agent_header="user-agent",
             accept_header_value="application/json",
+            http_headers=http_headers,
             security=self.sdk_configuration.security,
             get_serialized_body=lambda: utils.serialize_request_body(
                 request, False, False, "json", models.ChatClassificationRequest
@@ -309,6 +318,7 @@ class Classifiers(BaseSDK):
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
     ) -> Optional[models.ClassificationResponse]:
         r"""Moderations Chat
 
@@ -317,6 +327,7 @@ class Classifiers(BaseSDK):
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
         :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        :param http_headers: Additional headers to set or replace on requests.
         """
         base_url = None
         url_variables = None
@@ -333,7 +344,7 @@ class Classifiers(BaseSDK):
             model=model,
         )
 
-        req = self.build_request_async(
+        req = self._build_request_async(
             method="POST",
             path="/v1/chat/moderations",
             base_url=base_url,
@@ -344,6 +355,7 @@ class Classifiers(BaseSDK):
             request_has_query_params=True,
             user_agent_header="user-agent",
             accept_header_value="application/json",
+            http_headers=http_headers,
             security=self.sdk_configuration.security,
             get_serialized_body=lambda: utils.serialize_request_body(
                 request, False, False, "json", models.ChatClassificationRequest

mistralai/embeddings.py

@@ -5,7 +5,7 @@ from mistralai import models, utils
 from mistralai._hooks import HookContext
 from mistralai.types import OptionalNullable, UNSET
 from mistralai.utils import get_security_from_env
-from typing import Any, Optional, Union
+from typing import Any, Mapping, Optional, Union
 
 
 class Embeddings(BaseSDK):
@@ -20,6 +20,7 @@ class Embeddings(BaseSDK):
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
     ) -> Optional[models.EmbeddingResponse]:
         r"""Embeddings
 
@@ -31,6 +32,7 @@ class Embeddings(BaseSDK):
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
         :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        :param http_headers: Additional headers to set or replace on requests.
         """
         base_url = None
         url_variables = None
@@ -46,7 +48,7 @@ class Embeddings(BaseSDK):
             encoding_format=encoding_format,
         )
 
-        req = self.build_request(
+        req = self._build_request(
             method="POST",
             path="/v1/embeddings",
             base_url=base_url,
@@ -57,6 +59,7 @@ class Embeddings(BaseSDK):
             request_has_query_params=True,
             user_agent_header="user-agent",
             accept_header_value="application/json",
+            http_headers=http_headers,
             security=self.sdk_configuration.security,
             get_serialized_body=lambda: utils.serialize_request_body(
                 request, False, False, "json", models.EmbeddingRequest
@@ -117,6 +120,7 @@ class Embeddings(BaseSDK):
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
+        http_headers: Optional[Mapping[str, str]] = None,
     ) -> Optional[models.EmbeddingResponse]:
         r"""Embeddings
 
@@ -128,6 +132,7 @@ class Embeddings(BaseSDK):
         :param retries: Override the default retry configuration for this method
         :param server_url: Override the default server URL for this method
         :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        :param http_headers: Additional headers to set or replace on requests.
         """
         base_url = None
         url_variables = None
@@ -143,7 +148,7 @@ class Embeddings(BaseSDK):
             encoding_format=encoding_format,
         )
 
-        req = self.build_request_async(
+        req = self._build_request_async(
             method="POST",
             path="/v1/embeddings",
             base_url=base_url,
@@ -154,6 +159,7 @@ class Embeddings(BaseSDK):
             request_has_query_params=True,
             user_agent_header="user-agent",
             accept_header_value="application/json",
+            http_headers=http_headers,
             security=self.sdk_configuration.security,
             get_serialized_body=lambda: utils.serialize_request_body(
                 request, False, False, "json", models.EmbeddingRequest