c63a5cfe-b235-4fbe-8bbb-82a9e02a482a-python 0.1.0a7__py3-none-any.whl → 0.1.0a9__py3-none-any.whl

gradientai/types/agents/chat/agent_chat_completion_chunk.py

@@ -0,0 +1,93 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import List, Optional
+from typing_extensions import Literal
+
+from ...._models import BaseModel
+from ...shared.chat_completion_token_logprob import ChatCompletionTokenLogprob
+
+__all__ = ["AgentChatCompletionChunk", "Choice", "ChoiceDelta", "ChoiceLogprobs", "Usage"]
+
+
+class ChoiceDelta(BaseModel):
+    content: Optional[str] = None
+    """The contents of the chunk message."""
+
+    refusal: Optional[str] = None
+    """The refusal message generated by the model."""
+
+    role: Optional[Literal["developer", "user", "assistant"]] = None
+    """The role of the author of this message."""
+
+
+class ChoiceLogprobs(BaseModel):
+    content: Optional[List[ChatCompletionTokenLogprob]] = None
+    """A list of message content tokens with log probability information."""
+
+    refusal: Optional[List[ChatCompletionTokenLogprob]] = None
+    """A list of message refusal tokens with log probability information."""
+
+
+class Choice(BaseModel):
+    delta: ChoiceDelta
+    """A chat completion delta generated by streamed model responses."""
+
+    finish_reason: Optional[Literal["stop", "length"]] = None
+    """The reason the model stopped generating tokens.
+
+    This will be `stop` if the model hit a natural stop point or a provided stop
+    sequence, or `length` if the maximum number of tokens specified in the request
+    was reached
+    """
+
+    index: int
+    """The index of the choice in the list of choices."""
+
+    logprobs: Optional[ChoiceLogprobs] = None
+    """Log probability information for the choice."""
+
+
+class Usage(BaseModel):
+    completion_tokens: int
+    """Number of tokens in the generated completion."""
+
+    prompt_tokens: int
+    """Number of tokens in the prompt."""
+
+    total_tokens: int
+    """Total number of tokens used in the request (prompt + completion)."""
+
+
+class AgentChatCompletionChunk(BaseModel):
+    id: str
+    """A unique identifier for the chat completion. Each chunk has the same ID."""
+
+    choices: List[Choice]
+    """A list of chat completion choices.
+
+    Can contain more than one elements if `n` is greater than 1. Can also be empty
+    for the last chunk if you set `stream_options: {"include_usage": true}`.
+    """
+
+    created: int
+    """The Unix timestamp (in seconds) of when the chat completion was created.
+
+    Each chunk has the same timestamp.
+    """
+
+    model: str
+    """The model to generate the completion."""
+
+    object: Literal["chat.completion.chunk"]
+    """The object type, which is always `chat.completion.chunk`."""
+
+    usage: Optional[Usage] = None
+    """
+    An optional field that will only be present when you set
+    `stream_options: {"include_usage": true}` in your request. When present, it
+    contains a null value **except for the last chunk** which contains the token
+    usage statistics for the entire request.
+
+    **NOTE:** If the stream is interrupted or cancelled, you may not receive the
+    final usage chunk which contains the total token usage for the request.
+    """

gradientai/types/agents/chat/completion_create_params.py

@@ -6,17 +6,19 @@ from typing import Dict, List, Union, Iterable, Optional
 from typing_extensions import Literal, Required, TypeAlias, TypedDict
 
 __all__ = [
-    "CompletionCreateParams",
+    "CompletionCreateParamsBase",
     "Message",
     "MessageChatCompletionRequestSystemMessage",
     "MessageChatCompletionRequestDeveloperMessage",
     "MessageChatCompletionRequestUserMessage",
     "MessageChatCompletionRequestAssistantMessage",
     "StreamOptions",
+    "CompletionCreateParamsNonStreaming",
+    "CompletionCreateParamsStreaming",
 ]
 
 
-class CompletionCreateParams(TypedDict, total=False):
+class CompletionCreateParamsBase(TypedDict, total=False):
     messages: Required[Iterable[Message]]
     """A list of messages comprising the conversation so far."""
 
@@ -92,12 +94,6 @@ class CompletionCreateParams(TypedDict, total=False):
     The returned text will not contain the stop sequence.
     """
 
-    stream: Optional[bool]
-    """
-    If set to true, the model response data will be streamed to the client as it is
-    generated using server-sent events.
-    """
-
     stream_options: Optional[StreamOptions]
     """Options for streaming response. Only set this when you set `stream: true`."""
 
@@ -183,3 +179,22 @@ class StreamOptions(TypedDict, total=False):
     **NOTE:** If the stream is interrupted, you may not receive the final usage
     chunk which contains the total token usage for the request.
     """
+
+
+class CompletionCreateParamsNonStreaming(CompletionCreateParamsBase, total=False):
+    stream: Optional[Literal[False]]
+    """
+    If set to true, the model response data will be streamed to the client as it is
+    generated using server-sent events.
+    """
+
+
+class CompletionCreateParamsStreaming(CompletionCreateParamsBase):
+    stream: Required[Literal[True]]
+    """
+    If set to true, the model response data will be streamed to the client as it is
+    generated using server-sent events.
+    """
+
+
+CompletionCreateParams = Union[CompletionCreateParamsNonStreaming, CompletionCreateParamsStreaming]

gradientai/types/chat/__init__.py

@@ -2,5 +2,6 @@
 
 from __future__ import annotations
 
+from .chat_completion_chunk import ChatCompletionChunk as ChatCompletionChunk
 from .completion_create_params import CompletionCreateParams as CompletionCreateParams
 from .completion_create_response import CompletionCreateResponse as CompletionCreateResponse

gradientai/types/chat/chat_completion_chunk.py

@@ -0,0 +1,93 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import List, Optional
+from typing_extensions import Literal
+
+from ..._models import BaseModel
+from ..shared.chat_completion_token_logprob import ChatCompletionTokenLogprob
+
+__all__ = ["ChatCompletionChunk", "Choice", "ChoiceDelta", "ChoiceLogprobs", "Usage"]
+
+
+class ChoiceDelta(BaseModel):
+    content: Optional[str] = None
+    """The contents of the chunk message."""
+
+    refusal: Optional[str] = None
+    """The refusal message generated by the model."""
+
+    role: Optional[Literal["developer", "user", "assistant"]] = None
+    """The role of the author of this message."""
+
+
+class ChoiceLogprobs(BaseModel):
+    content: Optional[List[ChatCompletionTokenLogprob]] = None
+    """A list of message content tokens with log probability information."""
+
+    refusal: Optional[List[ChatCompletionTokenLogprob]] = None
+    """A list of message refusal tokens with log probability information."""
+
+
+class Choice(BaseModel):
+    delta: ChoiceDelta
+    """A chat completion delta generated by streamed model responses."""
+
+    finish_reason: Optional[Literal["stop", "length"]] = None
+    """The reason the model stopped generating tokens.
+
+    This will be `stop` if the model hit a natural stop point or a provided stop
+    sequence, or `length` if the maximum number of tokens specified in the request
+    was reached
+    """
+
+    index: int
+    """The index of the choice in the list of choices."""
+
+    logprobs: Optional[ChoiceLogprobs] = None
+    """Log probability information for the choice."""
+
+
+class Usage(BaseModel):
+    completion_tokens: int
+    """Number of tokens in the generated completion."""
+
+    prompt_tokens: int
+    """Number of tokens in the prompt."""
+
+    total_tokens: int
+    """Total number of tokens used in the request (prompt + completion)."""
+
+
+class ChatCompletionChunk(BaseModel):
+    id: str
+    """A unique identifier for the chat completion. Each chunk has the same ID."""
+
+    choices: List[Choice]
+    """A list of chat completion choices.
+
+    Can contain more than one elements if `n` is greater than 1. Can also be empty
+    for the last chunk if you set `stream_options: {"include_usage": true}`.
+    """
+
+    created: int
+    """The Unix timestamp (in seconds) of when the chat completion was created.
+
+    Each chunk has the same timestamp.
+    """
+
+    model: str
+    """The model to generate the completion."""
+
+    object: Literal["chat.completion.chunk"]
+    """The object type, which is always `chat.completion.chunk`."""
+
+    usage: Optional[Usage] = None
+    """
+    An optional field that will only be present when you set
+    `stream_options: {"include_usage": true}` in your request. When present, it
+    contains a null value **except for the last chunk** which contains the token
+    usage statistics for the entire request.
+
+    **NOTE:** If the stream is interrupted or cancelled, you may not receive the
+    final usage chunk which contains the total token usage for the request.
+    """

gradientai/types/chat/completion_create_params.py

@@ -6,17 +6,19 @@ from typing import Dict, List, Union, Iterable, Optional
 from typing_extensions import Literal, Required, TypeAlias, TypedDict
 
 __all__ = [
-    "CompletionCreateParams",
+    "CompletionCreateParamsBase",
     "Message",
     "MessageChatCompletionRequestSystemMessage",
     "MessageChatCompletionRequestDeveloperMessage",
     "MessageChatCompletionRequestUserMessage",
     "MessageChatCompletionRequestAssistantMessage",
     "StreamOptions",
+    "CompletionCreateParamsNonStreaming",
+    "CompletionCreateParamsStreaming",
 ]
 
 
-class CompletionCreateParams(TypedDict, total=False):
+class CompletionCreateParamsBase(TypedDict, total=False):
     messages: Required[Iterable[Message]]
     """A list of messages comprising the conversation so far."""
 
@@ -92,12 +94,6 @@ class CompletionCreateParams(TypedDict, total=False):
     The returned text will not contain the stop sequence.
     """
 
-    stream: Optional[bool]
-    """
-    If set to true, the model response data will be streamed to the client as it is
-    generated using server-sent events.
-    """
-
     stream_options: Optional[StreamOptions]
     """Options for streaming response. Only set this when you set `stream: true`."""
 
@@ -183,3 +179,22 @@ class StreamOptions(TypedDict, total=False):
     **NOTE:** If the stream is interrupted, you may not receive the final usage
     chunk which contains the total token usage for the request.
     """
+
+
+class CompletionCreateParamsNonStreaming(CompletionCreateParamsBase, total=False):
+    stream: Optional[Literal[False]]
+    """
+    If set to true, the model response data will be streamed to the client as it is
+    generated using server-sent events.
+    """
+
+
+class CompletionCreateParamsStreaming(CompletionCreateParamsBase):
+    stream: Required[Literal[True]]
+    """
+    If set to true, the model response data will be streamed to the client as it is
+    generated using server-sent events.
+    """
+
+
+CompletionCreateParams = Union[CompletionCreateParamsNonStreaming, CompletionCreateParamsStreaming]