mistralai 1.0.0rc1__py3-none-any.whl → 1.0.1__py3-none-any.whl

mistralai/chat.py

@@ -1,21 +1,20 @@
 """Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
 
 from .basesdk import BaseSDK
-from mistralai import models
+from mistralai import models, utils
 from mistralai._hooks import HookContext
-from mistralai.types import OptionalNullable, UNSET
-import mistralai.utils as utils
-from mistralai.utils import eventstreaming
+from mistralai.types import Nullable, OptionalNullable, UNSET
+from mistralai.utils import eventstreaming, get_security_from_env
 from typing import Any, AsyncGenerator, Generator, List, Optional, Union
 
 class Chat(BaseSDK):
     r"""Chat Completion API."""
     
     
-    def create(
+    def complete(
         self, *,
+        model: Nullable[str],
         messages: Union[List[models.Messages], List[models.MessagesTypedDict]],
-        model: OptionalNullable[str] = UNSET,
         temperature: Optional[float] = 0.7,
         top_p: Optional[float] = 1,
         max_tokens: OptionalNullable[int] = UNSET,
@@ -25,18 +24,16 @@ class Chat(BaseSDK):
         random_seed: OptionalNullable[int] = UNSET,
         response_format: Optional[Union[models.ResponseFormat, models.ResponseFormatTypedDict]] = None,
         tools: OptionalNullable[Union[List[models.Tool], List[models.ToolTypedDict]]] = UNSET,
-        safe_prompt: Optional[bool] = False,
         tool_choice: Optional[models.ToolChoice] = "auto",
+        safe_prompt: Optional[bool] = False,
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
     ) -> Optional[models.ChatCompletionResponse]:
         r"""Chat Completion
 
-        Chat Completion
-
-        :param messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content.
         :param model: ID of the model to use. You can use the [List Available Models](/api#operation/listModels) API to see all of your available models, or see our [Model overview](/models) for model descriptions.
+        :param messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content.
         :param temperature: What sampling temperature to use, between 0.0 and 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
         :param top_p: Nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.
         :param max_tokens: The maximum number of tokens to generate in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length.
@@ -46,8 +43,8 @@ class Chat(BaseSDK):
         :param random_seed: The seed to use for random sampling. If set, different calls will generate deterministic results.
         :param response_format: 
         :param tools: 
-        :param safe_prompt: Whether to inject a safety prompt before all conversations.
         :param tool_choice: 
+        :param safe_prompt: Whether to inject a safety prompt before all conversations.
         :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
@@ -72,8 +69,8 @@ class Chat(BaseSDK):
             messages=utils.get_pydantic_model(messages, List[models.Messages]),
             response_format=utils.get_pydantic_model(response_format, Optional[models.ResponseFormat]),
             tools=utils.get_pydantic_model(tools, OptionalNullable[List[models.Tool]]),
-            safe_prompt=safe_prompt,
             tool_choice=tool_choice,
+            safe_prompt=safe_prompt,
         )
         
         req = self.build_request(
@@ -107,7 +104,7 @@ class Chat(BaseSDK):
             ])                
         
         http_res = self.do_request(
-            hook_ctx=HookContext(operation_id="chat_completion_v1_chat_completions_post", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="chat_completion_v1_chat_completions_post", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["422","4XX","5XX"],
             retry_config=retry_config
@@ -127,10 +124,10 @@ class Chat(BaseSDK):
 
     
     
-    async def create_async(
+    async def complete_async(
         self, *,
+        model: Nullable[str],
         messages: Union[List[models.Messages], List[models.MessagesTypedDict]],
-        model: OptionalNullable[str] = UNSET,
         temperature: Optional[float] = 0.7,
         top_p: Optional[float] = 1,
         max_tokens: OptionalNullable[int] = UNSET,
@@ -140,18 +137,16 @@ class Chat(BaseSDK):
         random_seed: OptionalNullable[int] = UNSET,
         response_format: Optional[Union[models.ResponseFormat, models.ResponseFormatTypedDict]] = None,
         tools: OptionalNullable[Union[List[models.Tool], List[models.ToolTypedDict]]] = UNSET,
-        safe_prompt: Optional[bool] = False,
         tool_choice: Optional[models.ToolChoice] = "auto",
+        safe_prompt: Optional[bool] = False,
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
     ) -> Optional[models.ChatCompletionResponse]:
         r"""Chat Completion
 
-        Chat Completion
-
-        :param messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content.
         :param model: ID of the model to use. You can use the [List Available Models](/api#operation/listModels) API to see all of your available models, or see our [Model overview](/models) for model descriptions.
+        :param messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content.
         :param temperature: What sampling temperature to use, between 0.0 and 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
         :param top_p: Nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.
         :param max_tokens: The maximum number of tokens to generate in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length.
@@ -161,8 +156,8 @@ class Chat(BaseSDK):
         :param random_seed: The seed to use for random sampling. If set, different calls will generate deterministic results.
         :param response_format: 
         :param tools: 
-        :param safe_prompt: Whether to inject a safety prompt before all conversations.
         :param tool_choice: 
+        :param safe_prompt: Whether to inject a safety prompt before all conversations.
         :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
@@ -187,8 +182,8 @@ class Chat(BaseSDK):
             messages=utils.get_pydantic_model(messages, List[models.Messages]),
             response_format=utils.get_pydantic_model(response_format, Optional[models.ResponseFormat]),
             tools=utils.get_pydantic_model(tools, OptionalNullable[List[models.Tool]]),
-            safe_prompt=safe_prompt,
             tool_choice=tool_choice,
+            safe_prompt=safe_prompt,
         )
         
         req = self.build_request(
@@ -222,7 +217,7 @@ class Chat(BaseSDK):
             ])                
         
         http_res = await self.do_request_async(
-            hook_ctx=HookContext(operation_id="chat_completion_v1_chat_completions_post", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="chat_completion_v1_chat_completions_post", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["422","4XX","5XX"],
             retry_config=retry_config
@@ -244,8 +239,8 @@ class Chat(BaseSDK):
     
     def stream(
         self, *,
+        model: Nullable[str],
         messages: Union[List[models.ChatCompletionStreamRequestMessages], List[models.ChatCompletionStreamRequestMessagesTypedDict]],
-        model: OptionalNullable[str] = UNSET,
         temperature: Optional[float] = 0.7,
         top_p: Optional[float] = 1,
         max_tokens: OptionalNullable[int] = UNSET,
@@ -255,8 +250,8 @@ class Chat(BaseSDK):
         random_seed: OptionalNullable[int] = UNSET,
         response_format: Optional[Union[models.ResponseFormat, models.ResponseFormatTypedDict]] = None,
         tools: OptionalNullable[Union[List[models.Tool], List[models.ToolTypedDict]]] = UNSET,
-        safe_prompt: Optional[bool] = False,
         tool_choice: Optional[models.ChatCompletionStreamRequestToolChoice] = "auto",
+        safe_prompt: Optional[bool] = False,
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
@@ -265,8 +260,8 @@ class Chat(BaseSDK):
 
         Mistral AI provides the ability to stream responses back to a client in order to allow partial results for certain requests. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Otherwise, the server will hold the request open until the timeout or until completion, with the response containing the full result as JSON.
 
-        :param messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content.
         :param model: ID of the model to use. You can use the [List Available Models](/api#operation/listModels) API to see all of your available models, or see our [Model overview](/models) for model descriptions.
+        :param messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content.
         :param temperature: What sampling temperature to use, between 0.0 and 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
         :param top_p: Nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.
         :param max_tokens: The maximum number of tokens to generate in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length.
@@ -276,8 +271,8 @@ class Chat(BaseSDK):
         :param random_seed: The seed to use for random sampling. If set, different calls will generate deterministic results.
         :param response_format: 
         :param tools: 
-        :param safe_prompt: Whether to inject a safety prompt before all conversations.
         :param tool_choice: 
+        :param safe_prompt: Whether to inject a safety prompt before all conversations.
         :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
@@ -302,8 +297,8 @@ class Chat(BaseSDK):
             messages=utils.get_pydantic_model(messages, List[models.ChatCompletionStreamRequestMessages]),
             response_format=utils.get_pydantic_model(response_format, Optional[models.ResponseFormat]),
             tools=utils.get_pydantic_model(tools, OptionalNullable[List[models.Tool]]),
-            safe_prompt=safe_prompt,
             tool_choice=tool_choice,
+            safe_prompt=safe_prompt,
         )
         
         req = self.build_request(
@@ -337,7 +332,7 @@ class Chat(BaseSDK):
             ])                
         
         http_res = self.do_request(
-            hook_ctx=HookContext(operation_id="stream_chat", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="stream_chat", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["422","4XX","5XX"],
             stream=True,
@@ -360,8 +355,8 @@ class Chat(BaseSDK):
     
     async def stream_async(
         self, *,
+        model: Nullable[str],
         messages: Union[List[models.ChatCompletionStreamRequestMessages], List[models.ChatCompletionStreamRequestMessagesTypedDict]],
-        model: OptionalNullable[str] = UNSET,
         temperature: Optional[float] = 0.7,
         top_p: Optional[float] = 1,
         max_tokens: OptionalNullable[int] = UNSET,
@@ -371,8 +366,8 @@ class Chat(BaseSDK):
         random_seed: OptionalNullable[int] = UNSET,
         response_format: Optional[Union[models.ResponseFormat, models.ResponseFormatTypedDict]] = None,
         tools: OptionalNullable[Union[List[models.Tool], List[models.ToolTypedDict]]] = UNSET,
-        safe_prompt: Optional[bool] = False,
         tool_choice: Optional[models.ChatCompletionStreamRequestToolChoice] = "auto",
+        safe_prompt: Optional[bool] = False,
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
@@ -381,8 +376,8 @@ class Chat(BaseSDK):
 
         Mistral AI provides the ability to stream responses back to a client in order to allow partial results for certain requests. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Otherwise, the server will hold the request open until the timeout or until completion, with the response containing the full result as JSON.
 
-        :param messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content.
         :param model: ID of the model to use. You can use the [List Available Models](/api#operation/listModels) API to see all of your available models, or see our [Model overview](/models) for model descriptions.
+        :param messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content.
         :param temperature: What sampling temperature to use, between 0.0 and 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
         :param top_p: Nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.
         :param max_tokens: The maximum number of tokens to generate in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length.
@@ -392,8 +387,8 @@ class Chat(BaseSDK):
         :param random_seed: The seed to use for random sampling. If set, different calls will generate deterministic results.
         :param response_format: 
         :param tools: 
-        :param safe_prompt: Whether to inject a safety prompt before all conversations.
         :param tool_choice: 
+        :param safe_prompt: Whether to inject a safety prompt before all conversations.
         :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
@@ -418,8 +413,8 @@ class Chat(BaseSDK):
             messages=utils.get_pydantic_model(messages, List[models.ChatCompletionStreamRequestMessages]),
             response_format=utils.get_pydantic_model(response_format, Optional[models.ResponseFormat]),
             tools=utils.get_pydantic_model(tools, OptionalNullable[List[models.Tool]]),
-            safe_prompt=safe_prompt,
             tool_choice=tool_choice,
+            safe_prompt=safe_prompt,
         )
         
         req = self.build_request(
@@ -453,7 +448,7 @@ class Chat(BaseSDK):
             ])                
         
         http_res = await self.do_request_async(
-            hook_ctx=HookContext(operation_id="stream_chat", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="stream_chat", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["422","4XX","5XX"],
             stream=True,

mistralai/client.py

@@ -1,6 +1,6 @@
 from typing import Optional
 
-MIGRATION_MESSAGE = "This client is deprecated starting v1.0.0, pin your version to 0.4.2. Or migrate by following this documentation: TODO add link"
+MIGRATION_MESSAGE = "This client is deprecated. To migrate to the new client, please refer to this guide: https://github.com/mistralai/client-python/blob/main/MIGRATION.md. If you need to use this client anyway, pin your version to 0.4.2."
 
 
 class MistralClient:

mistralai/embeddings.py

@@ -1,10 +1,10 @@
 """Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
 
 from .basesdk import BaseSDK
-from mistralai import models
+from mistralai import models, utils
 from mistralai._hooks import HookContext
 from mistralai.types import OptionalNullable, UNSET
-import mistralai.utils as utils
+from mistralai.utils import get_security_from_env
 from typing import Any, Optional, Union
 
 class Embeddings(BaseSDK):
@@ -76,7 +76,7 @@ class Embeddings(BaseSDK):
             ])                
         
         http_res = self.do_request(
-            hook_ctx=HookContext(operation_id="embeddings_v1_embeddings_post", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="embeddings_v1_embeddings_post", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["422","4XX","5XX"],
             retry_config=retry_config
@@ -161,7 +161,7 @@ class Embeddings(BaseSDK):
             ])                
         
         http_res = await self.do_request_async(
-            hook_ctx=HookContext(operation_id="embeddings_v1_embeddings_post", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="embeddings_v1_embeddings_post", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["422","4XX","5XX"],
             retry_config=retry_config

mistralai/files.py

@@ -1,10 +1,10 @@
 """Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
 
 from .basesdk import BaseSDK
-from mistralai import models
+from mistralai import models, utils
 from mistralai._hooks import HookContext
 from mistralai.types import OptionalNullable, UNSET
-import mistralai.utils as utils
+from mistralai.utils import get_security_from_env
 from typing import Optional, Union
 
 class Files(BaseSDK):
@@ -74,7 +74,7 @@ class Files(BaseSDK):
             ])                
         
         http_res = self.do_request(
-            hook_ctx=HookContext(operation_id="files_api_routes_upload_file", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="files_api_routes_upload_file", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["4XX","5XX"],
             retry_config=retry_config
@@ -153,7 +153,7 @@ class Files(BaseSDK):
             ])                
         
         http_res = await self.do_request_async(
-            hook_ctx=HookContext(operation_id="files_api_routes_upload_file", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="files_api_routes_upload_file", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["4XX","5XX"],
             retry_config=retry_config
@@ -220,7 +220,7 @@ class Files(BaseSDK):
             ])                
         
         http_res = self.do_request(
-            hook_ctx=HookContext(operation_id="files_api_routes_list_files", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="files_api_routes_list_files", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["4XX","5XX"],
             retry_config=retry_config
@@ -287,7 +287,7 @@ class Files(BaseSDK):
             ])                
         
         http_res = await self.do_request_async(
-            hook_ctx=HookContext(operation_id="files_api_routes_list_files", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="files_api_routes_list_files", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["4XX","5XX"],
             retry_config=retry_config
@@ -361,7 +361,7 @@ class Files(BaseSDK):
             ])                
         
         http_res = self.do_request(
-            hook_ctx=HookContext(operation_id="files_api_routes_retrieve_file", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="files_api_routes_retrieve_file", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["4XX","5XX"],
             retry_config=retry_config
@@ -435,7 +435,7 @@ class Files(BaseSDK):
             ])                
         
         http_res = await self.do_request_async(
-            hook_ctx=HookContext(operation_id="files_api_routes_retrieve_file", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="files_api_routes_retrieve_file", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["4XX","5XX"],
             retry_config=retry_config
@@ -509,7 +509,7 @@ class Files(BaseSDK):
             ])                
         
         http_res = self.do_request(
-            hook_ctx=HookContext(operation_id="files_api_routes_delete_file", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="files_api_routes_delete_file", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["4XX","5XX"],
             retry_config=retry_config
@@ -583,7 +583,7 @@ class Files(BaseSDK):
             ])                
         
         http_res = await self.do_request_async(
-            hook_ctx=HookContext(operation_id="files_api_routes_delete_file", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="files_api_routes_delete_file", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["4XX","5XX"],
             retry_config=retry_config

mistralai/fim.py

@@ -1,21 +1,20 @@
 """Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
 
 from .basesdk import BaseSDK
-from mistralai import models
+from mistralai import models, utils
 from mistralai._hooks import HookContext
-from mistralai.types import OptionalNullable, UNSET
-import mistralai.utils as utils
-from mistralai.utils import eventstreaming
+from mistralai.types import Nullable, OptionalNullable, UNSET
+from mistralai.utils import eventstreaming, get_security_from_env
 from typing import Any, AsyncGenerator, Generator, Optional, Union
 
 class Fim(BaseSDK):
     r"""Fill-in-the-middle API."""
     
     
-    def create(
+    def complete(
         self, *,
+        model: Nullable[str],
         prompt: str,
-        model: OptionalNullable[str] = UNSET,
         temperature: Optional[float] = 0.7,
         top_p: Optional[float] = 1,
         max_tokens: OptionalNullable[int] = UNSET,
@@ -32,8 +31,8 @@ class Fim(BaseSDK):
 
         FIM completion.
 
-        :param prompt: The text/code to complete.
         :param model: ID of the model to use. Only compatible for now with:   - `codestral-2405`   - `codestral-latest`
+        :param prompt: The text/code to complete.
         :param temperature: What sampling temperature to use, between 0.0 and 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
         :param top_p: Nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.
         :param max_tokens: The maximum number of tokens to generate in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length.
@@ -98,7 +97,7 @@ class Fim(BaseSDK):
             ])                
         
         http_res = self.do_request(
-            hook_ctx=HookContext(operation_id="fim_completion_v1_fim_completions_post", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="fim_completion_v1_fim_completions_post", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["422","4XX","5XX"],
             retry_config=retry_config
@@ -118,10 +117,10 @@ class Fim(BaseSDK):
 
     
     
-    async def create_async(
+    async def complete_async(
         self, *,
+        model: Nullable[str],
         prompt: str,
-        model: OptionalNullable[str] = UNSET,
         temperature: Optional[float] = 0.7,
         top_p: Optional[float] = 1,
         max_tokens: OptionalNullable[int] = UNSET,
@@ -138,8 +137,8 @@ class Fim(BaseSDK):
 
         FIM completion.
 
-        :param prompt: The text/code to complete.
         :param model: ID of the model to use. Only compatible for now with:   - `codestral-2405`   - `codestral-latest`
+        :param prompt: The text/code to complete.
         :param temperature: What sampling temperature to use, between 0.0 and 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
         :param top_p: Nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.
         :param max_tokens: The maximum number of tokens to generate in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length.
@@ -204,7 +203,7 @@ class Fim(BaseSDK):
             ])                
         
         http_res = await self.do_request_async(
-            hook_ctx=HookContext(operation_id="fim_completion_v1_fim_completions_post", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="fim_completion_v1_fim_completions_post", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["422","4XX","5XX"],
             retry_config=retry_config
@@ -226,8 +225,8 @@ class Fim(BaseSDK):
     
     def stream(
         self, *,
+        model: Nullable[str],
         prompt: str,
-        model: OptionalNullable[str] = UNSET,
         temperature: Optional[float] = 0.7,
         top_p: Optional[float] = 1,
         max_tokens: OptionalNullable[int] = UNSET,
@@ -244,8 +243,8 @@ class Fim(BaseSDK):
 
         Mistral AI provides the ability to stream responses back to a client in order to allow partial results for certain requests. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Otherwise, the server will hold the request open until the timeout or until completion, with the response containing the full result as JSON.
 
-        :param prompt: The text/code to complete.
         :param model: ID of the model to use. Only compatible for now with:   - `codestral-2405`   - `codestral-latest`
+        :param prompt: The text/code to complete.
         :param temperature: What sampling temperature to use, between 0.0 and 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
         :param top_p: Nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.
         :param max_tokens: The maximum number of tokens to generate in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length.
@@ -310,7 +309,7 @@ class Fim(BaseSDK):
             ])                
         
         http_res = self.do_request(
-            hook_ctx=HookContext(operation_id="stream_fim", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="stream_fim", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["422","4XX","5XX"],
             stream=True,
@@ -333,8 +332,8 @@ class Fim(BaseSDK):
     
     async def stream_async(
         self, *,
+        model: Nullable[str],
         prompt: str,
-        model: OptionalNullable[str] = UNSET,
         temperature: Optional[float] = 0.7,
         top_p: Optional[float] = 1,
         max_tokens: OptionalNullable[int] = UNSET,
@@ -351,8 +350,8 @@ class Fim(BaseSDK):
 
         Mistral AI provides the ability to stream responses back to a client in order to allow partial results for certain requests. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Otherwise, the server will hold the request open until the timeout or until completion, with the response containing the full result as JSON.
 
-        :param prompt: The text/code to complete.
         :param model: ID of the model to use. Only compatible for now with:   - `codestral-2405`   - `codestral-latest`
+        :param prompt: The text/code to complete.
         :param temperature: What sampling temperature to use, between 0.0 and 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
         :param top_p: Nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.
         :param max_tokens: The maximum number of tokens to generate in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length.
@@ -417,7 +416,7 @@ class Fim(BaseSDK):
             ])                
         
         http_res = await self.do_request_async(
-            hook_ctx=HookContext(operation_id="stream_fim", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            hook_ctx=HookContext(operation_id="stream_fim", oauth2_scopes=[], security_source=get_security_from_env(self.sdk_configuration.security, models.Security)),
             request=req,
             error_status_codes=["422","4XX","5XX"],
             stream=True,