dv-pipecat-ai 0.0.82.dev857__py3-none-any.whl → 0.0.85.dev837__py3-none-any.whl

pipecat/services/aws_nova_sonic/context.py

@@ -8,360 +8,14 @@
 
 This module provides specialized context aggregators and message handling for AWS Nova Sonic,
 including conversation history management and role-specific message processing.
-"""
-
-import copy
-from dataclasses import dataclass, field
-from enum import Enum
-
-from loguru import logger
-
-from pipecat.frames.frames import (
-    BotStoppedSpeakingFrame,
-    DataFrame,
-    Frame,
-    FunctionCallResultFrame,
-    LLMFullResponseEndFrame,
-    LLMFullResponseStartFrame,
-    LLMMessagesAppendFrame,
-    LLMMessagesUpdateFrame,
-    LLMSetToolChoiceFrame,
-    LLMSetToolsFrame,
-    StartInterruptionFrame,
-    TextFrame,
-    UserImageRawFrame,
-)
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.processors.frame_processor import FrameDirection
-from pipecat.services.aws_nova_sonic.frames import AWSNovaSonicFunctionCallResultFrame
-from pipecat.services.openai.llm import (
-    OpenAIAssistantContextAggregator,
-    OpenAIUserContextAggregator,
-)
-
-
-class Role(Enum):
-    """Roles supported in AWS Nova Sonic conversations.
-
-    Parameters:
-        SYSTEM: System-level messages (not used in conversation history).
-        USER: Messages sent by the user.
-        ASSISTANT: Messages sent by the assistant.
-        TOOL: Messages sent by tools (not used in conversation history).
-    """
-
-    SYSTEM = "SYSTEM"
-    USER = "USER"
-    ASSISTANT = "ASSISTANT"
-    TOOL = "TOOL"
-
-
-@dataclass
-class AWSNovaSonicConversationHistoryMessage:
-    """A single message in AWS Nova Sonic conversation history.
-
-    Parameters:
-        role: The role of the message sender (USER or ASSISTANT only).
-        text: The text content of the message.
-    """
-
-    role: Role  # only USER and ASSISTANT
-    text: str
-
-
-@dataclass
-class AWSNovaSonicConversationHistory:
-    """Complete conversation history for AWS Nova Sonic initialization.
-
-    Parameters:
-        system_instruction: System-level instruction for the conversation.
-        messages: List of conversation messages between user and assistant.
-    """
-
-    system_instruction: str = None
-    messages: list[AWSNovaSonicConversationHistoryMessage] = field(default_factory=list)
-
-
-class AWSNovaSonicLLMContext(OpenAILLMContext):
-    """Specialized LLM context for AWS Nova Sonic service.
-
-    Extends OpenAI context with Nova Sonic-specific message handling,
-    conversation history management, and text buffering capabilities.
-    """
-
-    def __init__(self, messages=None, tools=None, **kwargs):
-        """Initialize AWS Nova Sonic LLM context.
-
-        Args:
-            messages: Initial messages for the context.
-            tools: Available tools for the context.
-            **kwargs: Additional arguments passed to parent class.
-        """
-        super().__init__(messages=messages, tools=tools, **kwargs)
-        self.__setup_local()
-
-    def __setup_local(self, system_instruction: str = ""):
-        self._assistant_text = ""
-        self._user_text = ""
-        self._system_instruction = system_instruction
-
-    @staticmethod
-    def upgrade_to_nova_sonic(
-        obj: OpenAILLMContext, system_instruction: str
-    ) -> "AWSNovaSonicLLMContext":
-        """Upgrade an OpenAI context to AWS Nova Sonic context.
-
-        Args:
-            obj: The OpenAI context to upgrade.
-            system_instruction: System instruction for the context.
-
-        Returns:
-            The upgraded AWS Nova Sonic context.
-        """
-        if isinstance(obj, OpenAILLMContext) and not isinstance(obj, AWSNovaSonicLLMContext):
-            obj.__class__ = AWSNovaSonicLLMContext
-            obj.__setup_local(system_instruction)
-        return obj
-
-    # NOTE: this method has the side-effect of updating _system_instruction from messages
-    def get_messages_for_initializing_history(self) -> AWSNovaSonicConversationHistory:
-        """Get conversation history for initializing AWS Nova Sonic session.
-
-        Processes stored messages and extracts system instruction and conversation
-        history in the format expected by AWS Nova Sonic.
-
-        Returns:
-            Formatted conversation history with system instruction and messages.
-        """
-        history = AWSNovaSonicConversationHistory(system_instruction=self._system_instruction)
-
-        # Bail if there are no messages
-        if not self.messages:
-            return history
-
-        messages = copy.deepcopy(self.messages)
-
-        # If we have a "system" message as our first message, let's pull that out into "instruction"
-        if messages[0].get("role") == "system":
-            system = messages.pop(0)
-            content = system.get("content")
-            if isinstance(content, str):
-                history.system_instruction = content
-            elif isinstance(content, list):
-                history.system_instruction = content[0].get("text")
-            if history.system_instruction:
-                self._system_instruction = history.system_instruction
-
-        # Process remaining messages to fill out conversation history.
-        # Nova Sonic supports "user" and "assistant" messages in history.
-        for message in messages:
-            history_message = self.from_standard_message(message)
-            if history_message:
-                history.messages.append(history_message)
-
-        return history
-
-    def get_messages_for_persistent_storage(self):
-        """Get messages formatted for persistent storage.
-
-        Returns:
-            List of messages including system instruction if present.
-        """
-        messages = super().get_messages_for_persistent_storage()
-        # If we have a system instruction and messages doesn't already contain it, add it
-        if self._system_instruction and not (messages and messages[0].get("role") == "system"):
-            messages.insert(0, {"role": "system", "content": self._system_instruction})
-        return messages
 
-    def from_standard_message(self, message) -> AWSNovaSonicConversationHistoryMessage:
-        """Convert standard message format to Nova Sonic format.
+.. deprecated:: 0.0.91
+    AWS Nova Sonic no longer uses types from this module under the hood.
+    It now uses `LLMContext` and `LLMContextAggregatorPair`.
+    Using the new patterns should allow you to not need types from this module.
 
-        Args:
-            message: Standard message dictionary to convert.
-
-        Returns:
-            Nova Sonic conversation history message, or None if not convertible.
-        """
-        role = message.get("role")
-        if message.get("role") == "user" or message.get("role") == "assistant":
-            content = message.get("content")
-            if isinstance(message.get("content"), list):
-                content = ""
-                for c in message.get("content"):
-                    if c.get("type") == "text":
-                        content += " " + c.get("text")
-                    else:
-                        logger.error(
-                            f"Unhandled content type in context message: {c.get('type')} - {message}"
-                        )
-            # There won't be content if this is an assistant tool call entry.
-            # We're ignoring those since they can't be loaded into AWS Nova Sonic conversation
-            # history
-            if content:
-                return AWSNovaSonicConversationHistoryMessage(role=Role[role.upper()], text=content)
-        # NOTE: we're ignoring messages with role "tool" since they can't be loaded into AWS Nova
-        # Sonic conversation history
-
-    def buffer_user_text(self, text):
-        """Buffer user text for later flushing to context.
-
-        Args:
-            text: User text to buffer.
-        """
-        self._user_text += f" {text}" if self._user_text else text
-        # logger.debug(f"User text buffered: {self._user_text}")
-
-    def flush_aggregated_user_text(self) -> str:
-        """Flush buffered user text to context as a complete message.
-
-        Returns:
-            The flushed user text, or empty string if no text was buffered.
-        """
-        if not self._user_text:
-            return ""
-        user_text = self._user_text
-        message = {
-            "role": "user",
-            "content": [{"type": "text", "text": user_text}],
-        }
-        self._user_text = ""
-        self.add_message(message)
-        # logger.debug(f"Context updated (user): {self.get_messages_for_logging()}")
-        return user_text
-
-    def buffer_assistant_text(self, text):
-        """Buffer assistant text for later flushing to context.
-
-        Args:
-            text: Assistant text to buffer.
-        """
-        self._assistant_text += text
-        # logger.debug(f"Assistant text buffered: {self._assistant_text}")
-
-    def flush_aggregated_assistant_text(self):
-        """Flush buffered assistant text to context as a complete message."""
-        if not self._assistant_text:
-            return
-        message = {
-            "role": "assistant",
-            "content": [{"type": "text", "text": self._assistant_text}],
-        }
-        self._assistant_text = ""
-        self.add_message(message)
-        # logger.debug(f"Context updated (assistant): {self.get_messages_for_logging()}")
-
-
-@dataclass
-class AWSNovaSonicMessagesUpdateFrame(DataFrame):
-    """Frame containing updated AWS Nova Sonic context.
-
-    Parameters:
-        context: The updated AWS Nova Sonic LLM context.
-    """
-
-    context: AWSNovaSonicLLMContext
-
-
-class AWSNovaSonicUserContextAggregator(OpenAIUserContextAggregator):
-    """Context aggregator for user messages in AWS Nova Sonic conversations.
-
-    Extends the OpenAI user context aggregator to emit Nova Sonic-specific
-    context update frames.
-    """
-
-    async def process_frame(
-        self, frame: Frame, direction: FrameDirection = FrameDirection.DOWNSTREAM
-    ):
-        """Process frames and emit Nova Sonic-specific context updates.
-
-        Args:
-            frame: The frame to process.
-            direction: The direction the frame is traveling.
-        """
-        await super().process_frame(frame, direction)
-
-        # Parent does not push LLMMessagesUpdateFrame
-        if isinstance(frame, LLMMessagesUpdateFrame):
-            await self.push_frame(AWSNovaSonicMessagesUpdateFrame(context=self._context))
-
-
-class AWSNovaSonicAssistantContextAggregator(OpenAIAssistantContextAggregator):
-    """Context aggregator for assistant messages in AWS Nova Sonic conversations.
-
-    Provides specialized handling for assistant responses and function calls
-    in AWS Nova Sonic context, with custom frame processing logic.
-    """
-
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        """Process frames with Nova Sonic-specific logic.
-
-        Args:
-            frame: The frame to process.
-            direction: The direction the frame is traveling.
-        """
-        # HACK: For now, disable the context aggregator by making it just pass through all frames
-        # that the parent handles (except the function call stuff, which we still need).
-        # For an explanation of this hack, see
-        # AWSNovaSonicLLMService._report_assistant_response_text_added.
-        if isinstance(
-            frame,
-            (
-                StartInterruptionFrame,
-                LLMFullResponseStartFrame,
-                LLMFullResponseEndFrame,
-                TextFrame,
-                LLMMessagesAppendFrame,
-                LLMMessagesUpdateFrame,
-                LLMSetToolsFrame,
-                LLMSetToolChoiceFrame,
-                UserImageRawFrame,
-                BotStoppedSpeakingFrame,
-            ),
-        ):
-            await self.push_frame(frame, direction)
-        else:
-            await super().process_frame(frame, direction)
-
-    async def handle_function_call_result(self, frame: FunctionCallResultFrame):
-        """Handle function call results for AWS Nova Sonic.
-
-        Args:
-            frame: The function call result frame to handle.
-        """
-        await super().handle_function_call_result(frame)
-
-        # The standard function callback code path pushes the FunctionCallResultFrame from the LLM
-        # itself, so we didn't have a chance to add the result to the AWS Nova Sonic server-side
-        # context. Let's push a special frame to do that.
-        await self.push_frame(
-            AWSNovaSonicFunctionCallResultFrame(result_frame=frame), FrameDirection.UPSTREAM
-        )
-
-
-@dataclass
-class AWSNovaSonicContextAggregatorPair:
-    """Pair of user and assistant context aggregators for AWS Nova Sonic.
-
-    Parameters:
-        _user: The user context aggregator.
-        _assistant: The assistant context aggregator.
-    """
-
-    _user: AWSNovaSonicUserContextAggregator
-    _assistant: AWSNovaSonicAssistantContextAggregator
-
-    def user(self) -> AWSNovaSonicUserContextAggregator:
-        """Get the user context aggregator.
-
-        Returns:
-            The user context aggregator instance.
-        """
-        return self._user
-
-    def assistant(self) -> AWSNovaSonicAssistantContextAggregator:
-        """Get the assistant context aggregator.
+    See deprecation warning in pipecat.services.aws.nova_sonic.context for more
+    details.
+"""
 
-        Returns:
-            The assistant context aggregator instance.
-        """
-        return self._assistant
+from pipecat.services.aws.nova_sonic.context import *

pipecat/services/aws_nova_sonic/frames.py

@@ -6,20 +6,16 @@
 
 """Custom frames for AWS Nova Sonic LLM service."""
 
-from dataclasses import dataclass
-
-from pipecat.frames.frames import DataFrame, FunctionCallResultFrame
-
-
-@dataclass
-class AWSNovaSonicFunctionCallResultFrame(DataFrame):
-    """Frame containing function call result for AWS Nova Sonic processing.
-
-    This frame wraps a standard function call result frame to enable
-    AWS Nova Sonic-specific handling and context updates.
-
-    Parameters:
-        result_frame: The underlying function call result frame.
-    """
-
-    result_frame: FunctionCallResultFrame
+import warnings
+
+from pipecat.services.aws.nova_sonic.frames import *
+
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Types in pipecat.services.aws_nova_sonic.frames are deprecated. "
+        "Please use the equivalent types from "
+        "pipecat.services.aws.nova_sonic.frames instead.",
+        DeprecationWarning,
+        stacklevel=2,
+    )

pipecat/services/azure/llm.py

@@ -1,4 +1,3 @@
-#
 # Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
@@ -6,9 +5,12 @@
 
 """Azure OpenAI service implementation for the Pipecat AI framework."""
 
+from typing import Optional
+
 from loguru import logger
 from openai import AsyncAzureOpenAI
 
+from pipecat.adapters.services.open_ai_adapter import OpenAILLMInvocationParams
 from pipecat.services.openai.llm import OpenAILLMService
 
 
@@ -17,6 +19,16 @@ class AzureLLMService(OpenAILLMService):
 
     This service extends OpenAILLMService to connect to Azure's OpenAI endpoint while
     maintaining full compatibility with OpenAI's interface and functionality.
+
+
+    Args:
+        api_key: The API key for accessing Azure OpenAI.
+        endpoint: The Azure endpoint URL.
+        model: The model identifier to use.
+        api_version: Azure API version. Defaults to "2024-09-01-preview".
+        reasoning_effort: If provided for reasoning models, sets the effort (e.g. "minimal").
+        **kwargs: Additional keyword arguments passed to OpenAILLMService.
+
     """
 
     def __init__(
@@ -26,6 +38,7 @@ class AzureLLMService(OpenAILLMService):
         endpoint: str,
         model: str,
         api_version: str = "2024-09-01-preview",
+        reasoning_effort: Optional[str] = None,
         **kwargs,
     ):
         """Initialize the Azure LLM service.
@@ -41,6 +54,7 @@ class AzureLLMService(OpenAILLMService):
         # will call create_client() and we need those values there.
         self._endpoint = endpoint
         self._api_version = api_version
+        self._reasoning_effort = reasoning_effort
         super().__init__(api_key=api_key, model=model, **kwargs)
 
     def create_client(self, api_key=None, base_url=None, **kwargs):
@@ -62,3 +76,39 @@ class AzureLLMService(OpenAILLMService):
             api_version=self._api_version,
             azure_deployment=azure_deployment,
         )
+
+    def _is_reasoning_model(self) -> bool:
+        """Check if the current model supports reasoning parameters.
+
+        Based on search results:
+        - GPT-5, GPT-5-mini, and GPT-5-nano are reasoning models
+        - GPT-5-chat is a standard chat model that doesn't use reasoning by default
+
+        Returns:
+            True if model supports reasoning parameters.
+        """
+        model_name_lower = self.model_name.lower()
+
+        # Reasoning-capable models
+        reasoning_models = {"gpt-5-nano", "gpt-5", "gpt-5-mini"}
+        return model_name_lower in reasoning_models
+
+    def build_chat_completion_params(self, params_from_context: OpenAILLMInvocationParams) -> dict:
+        # include base params
+        params = super().build_chat_completion_params(params_from_context)
+
+        if self._is_reasoning_model():
+            # not required for reasoning models
+            for k in ("frequency_penalty", "presence_penalty", "temperature", "top_p"):
+                if k in params:
+                    params.pop(k, None)
+            if self._reasoning_effort:
+                params["reasoning_effort"] = self._reasoning_effort
+            seed = self._settings.get("seed")
+            if seed is not None:
+                params["seed"] = seed
+        else:
+            # Standard models are fine with the defaults from the base class
+            pass
+
+        return params

pipecat/services/azure/realtime/llm.py

@@ -0,0 +1,65 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Azure OpenAI Realtime LLM service implementation."""
+
+from loguru import logger
+
+from pipecat.services.openai.realtime.llm import OpenAIRealtimeLLMService
+
+try:
+    from websockets.asyncio.client import connect as websocket_connect
+except ModuleNotFoundError as e:
+    logger.error(f"Exception: {e}")
+    logger.error("In order to use Azure Realtime, you need to `pip install pipecat-ai[openai]`.")
+    raise Exception(f"Missing module: {e}")
+
+
+class AzureRealtimeLLMService(OpenAIRealtimeLLMService):
+    """Azure OpenAI Realtime LLM service with Azure-specific authentication.
+
+    Extends the OpenAI Realtime service to work with Azure OpenAI endpoints,
+    using Azure's authentication headers and endpoint format. Provides the same
+    real-time audio and text communication capabilities as the base OpenAI service.
+    """
+
+    def __init__(
+        self,
+        *,
+        api_key: str,
+        base_url: str,
+        **kwargs,
+    ):
+        """Initialize Azure Realtime LLM service.
+
+        Args:
+            api_key: The API key for the Azure OpenAI service.
+            base_url: The full Azure WebSocket endpoint URL including api-version and deployment.
+                Example: "wss://my-project.openai.azure.com/openai/realtime?api-version=2024-10-01-preview&deployment=my-realtime-deployment"
+            **kwargs: Additional arguments passed to parent OpenAIRealtimeLLMService.
+        """
+        super().__init__(base_url=base_url, api_key=api_key, **kwargs)
+        self.api_key = api_key
+        self.base_url = base_url
+
+    async def _connect(self):
+        try:
+            if self._websocket:
+                # Here we assume that if we have a websocket, we are connected. We
+                # handle disconnections in the send/recv code paths.
+                return
+
+            logger.info(f"Connecting to {self.base_url}, api key: {self.api_key}")
+            self._websocket = await websocket_connect(
+                uri=self.base_url,
+                additional_headers={
+                    "api-key": self.api_key,
+                },
+            )
+            self._receive_task = self.create_task(self._receive_task_handler())
+        except Exception as e:
+            logger.error(f"{self} initialization error: {e}")
+            self._websocket = None

pipecat/services/azure/stt.py

@@ -19,6 +19,7 @@ from pipecat.frames.frames import (
     CancelFrame,
     EndFrame,
     Frame,
+    InterimTranscriptionFrame,
     StartFrame,
     TranscriptionFrame,
 )
@@ -184,7 +185,9 @@ class AzureSTTService(STTService):
         self._apply_phrase_list(self._speech_recognizer)
 
         # Attach event handler for recognized speech
+        # self._speech_recognizer.recognizing.connect(self._on_handle_recognizing)
         self._speech_recognizer.recognized.connect(self._on_handle_recognized)
+
         self._speech_recognizer.start_continuous_recognition_async()
 
     async def stop(self, frame: EndFrame):
@@ -248,6 +251,18 @@ class AzureSTTService(STTService):
             )
             asyncio.run_coroutine_threadsafe(self.push_frame(frame), self.get_event_loop())
 
+    def _on_handle_recognizing(self, event):
+        if event.result.reason == ResultReason.RecognizingSpeech and len(event.result.text) > 0:
+            language = getattr(event.result, "language", None) or self._settings.get("language")
+            frame = InterimTranscriptionFrame(
+                event.result.text,
+                self._user_id,
+                time_now_iso8601(),
+                language,
+                result=event,
+            )
+            asyncio.run_coroutine_threadsafe(self.push_frame(frame), self.get_event_loop())
+
     def _apply_phrase_list(self, recognizer: SpeechRecognizer):
         """Applies the configured vocabulary as a phrase list to the recognizer."""
         if self._vocab and recognizer: