Skip to content

mirascope.core.azure.stream

The AzureStream class for convenience around streaming LLM calls.

Usage Documentation

Streams

AzureStream 

AzureStream(
    *,
    stream: (
        Generator[
            tuple[
                _BaseCallResponseChunkT, _BaseToolT | None
            ],
            None,
            None,
        ]
        | AsyncGenerator[
            tuple[
                _BaseCallResponseChunkT, _BaseToolT | None
            ],
            None,
        ]
    ),
    metadata: Metadata,
    tool_types: list[type[_BaseToolT]] | None,
    call_response_type: type[_BaseCallResponseT],
    model: str,
    prompt_template: str | None,
    fn_args: dict[str, Any],
    dynamic_config: _BaseDynamicConfigT,
    messages: list[_MessageParamT],
    call_params: _BaseCallParamsT,
    call_kwargs: BaseCallKwargs[_ToolSchemaT]
)

Bases: BaseStream[AzureCallResponse, AzureCallResponseChunk, UserMessage, AssistantMessage, ToolMessage, ChatRequestMessage, AzureTool, ChatCompletionsToolDefinition, AsyncAzureDynamicConfig | AzureDynamicConfig, AzureCallParams, CompletionsFinishReason]

A class for convenience around streaming Azure LLM calls.

Example:

from mirascope.core import prompt_template
from mirascope.core.azure import azure_call


@azure_call("gpt-4o-mini", stream=True)
def recommend_book(genre: str) -> str:
    return f"Recommend a {genre} book"


stream = recommend_book("fantasy")  # returns `AzureStream` instance
for chunk, _ in stream:
    print(chunk.content, end="", flush=True)
Source code in mirascope/core/base/stream.py 
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
def __init__(
    self,
    *,
    stream: Generator[tuple[_BaseCallResponseChunkT, _BaseToolT | None], None, None]
    | AsyncGenerator[
        tuple[_BaseCallResponseChunkT, _BaseToolT | None],
        None,
    ],
    metadata: Metadata,
    tool_types: list[type[_BaseToolT]] | None,
    call_response_type: type[_BaseCallResponseT],
    model: str,
    prompt_template: str | None,
    fn_args: dict[str, Any],
    dynamic_config: _BaseDynamicConfigT,
    messages: list[_MessageParamT],
    call_params: _BaseCallParamsT,
    call_kwargs: BaseCallKwargs[_ToolSchemaT],
) -> None:
    """Initializes an instance of `BaseStream`."""
    self.content = ""
    self.stream = stream
    self.metadata = metadata
    self.tool_types = tool_types
    self.call_response_type = call_response_type
    self.model = model
    self.prompt_template = prompt_template
    self.fn_args = fn_args
    self.dynamic_config = dynamic_config
    self.messages = messages
    self.call_params = call_params
    self.call_kwargs = call_kwargs
    self.user_message_param = get_possible_user_message_param(messages)  # pyright: ignore [reportAttributeAccessIssue]

cost property 

cost: float | None

Returns the cost of the call.

construct_call_response 

construct_call_response() -> AzureCallResponse

Constructs the call response from a consumed AzureStream.

Raises:

Type Description
ValueError

if the stream has not yet been consumed.
Source code in mirascope/core/azure/stream.py 
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
def construct_call_response(self) -> AzureCallResponse:
    """Constructs the call response from a consumed AzureStream.

    Raises:
        ValueError: if the stream has not yet been consumed.
    """
    if not hasattr(self, "message_param"):
        raise ValueError(
            "No stream response, check if the stream has been consumed."
        )
    message = ChatResponseMessage(
        role=self.message_param["role"],
        content=self.message_param.get("content", ""),
        tool_calls=self.message_param.get("tool_calls", []),
    )
    if not self.input_tokens and not self.output_tokens:
        usage = CompletionsUsage(
            completion_tokens=0, prompt_tokens=0, total_tokens=0
        )
    else:
        usage = CompletionsUsage(
            prompt_tokens=int(self.input_tokens or 0),
            completion_tokens=int(self.output_tokens or 0),
            total_tokens=int(self.input_tokens or 0) + int(self.output_tokens or 0),
        )
    completion = ChatCompletions(
        id=self.id if self.id else "",
        model=self.model,
        choices=[
            ChatChoice(
                finish_reason=self.finish_reasons[0]
                if self.finish_reasons
                else "stop",
                index=0,
                message=message,
            )
        ],
        created=datetime.datetime.now(),
        usage=usage,
    )
    return AzureCallResponse(
        metadata=self.metadata,
        response=completion,
        tool_types=self.tool_types,
        prompt_template=self.prompt_template,
        fn_args=self.fn_args if self.fn_args else {},
        dynamic_config=self.dynamic_config,
        messages=self.messages,
        call_params=self.call_params,
        call_kwargs=self.call_kwargs,
        user_message_param=self.user_message_param,
        start_time=self.start_time,
        end_time=self.end_time,
    )