dv-pipecat-ai 0.0.85.dev699__py3-none-any.whl → 0.0.85.dev814__py3-none-any.whl

pipecat/runner/run.py

@@ -70,16 +70,19 @@ import asyncio
 import mimetypes
 import os
 import sys
+import uuid
 from contextlib import asynccontextmanager
+from http import HTTPMethod
 from pathlib import Path
-from typing import Optional
+from typing import Any, Dict, List, Optional, TypedDict
 
 import aiohttp
-from fastapi.responses import FileResponse
+from fastapi.responses import FileResponse, Response
 from loguru import logger
 
 from pipecat.runner.types import (
     DailyRunnerArguments,
+    RunnerArguments,
     SmallWebRTCRunnerArguments,
     WebSocketRunnerArguments,
 )
@@ -166,6 +169,7 @@ def _create_server_app(
     host: str = "localhost",
     proxy: str,
     esp32_mode: bool = False,
+    whatsapp_enabled: bool = False,
     folder: Optional[str] = None,
 ):
     """Create FastAPI app with transport-specific routes."""
@@ -182,7 +186,8 @@ def _create_server_app(
     # Set up transport-specific routes
     if transport_type == "webrtc":
         _setup_webrtc_routes(app, esp32_mode=esp32_mode, host=host, folder=folder)
-        _setup_whatsapp_routes(app)
+        if whatsapp_enabled:
+            _setup_whatsapp_routes(app)
     elif transport_type == "daily":
         _setup_daily_routes(app)
     elif transport_type in TELEPHONY_TRANSPORTS:
@@ -200,8 +205,10 @@ def _setup_webrtc_routes(
     try:
         from pipecat_ai_small_webrtc_prebuilt.frontend import SmallWebRTCPrebuiltUI
 
-        from pipecat.transports.smallwebrtc.connection import SmallWebRTCConnection
+        from pipecat.transports.smallwebrtc.connection import IceServer, SmallWebRTCConnection
         from pipecat.transports.smallwebrtc.request_handler import (
+            IceCandidate,
+            SmallWebRTCPatchRequest,
             SmallWebRTCRequest,
             SmallWebRTCRequestHandler,
         )
@@ -209,6 +216,16 @@ def _setup_webrtc_routes(
         logger.error(f"WebRTC transport dependencies not installed: {e}")
         return
 
+    class IceConfig(TypedDict):
+        iceServers: List[IceServer]
+
+    class StartBotResult(TypedDict, total=False):
+        sessionId: str
+        iceConfig: Optional[IceConfig]
+
+    # In-memory store of active sessions: session_id -> session info
+    active_sessions: Dict[str, Dict[str, Any]] = {}
+
     # Mount the frontend
     app.mount("/client", SmallWebRTCPrebuiltUI)
 
@@ -217,7 +234,7 @@ def _setup_webrtc_routes(
         """Redirect root requests to client interface."""
         return RedirectResponse(url="/client/")
 
-    @app.get("/files/{filename}")
+    @app.get("/files/{filename:path}")
     async def download_file(filename: str):
         """Handle file downloads."""
         if not folder:
@@ -254,6 +271,74 @@ def _setup_webrtc_routes(
         )
         return answer
 
+    @app.patch("/api/offer")
+    async def ice_candidate(request: SmallWebRTCPatchRequest):
+        """Handle WebRTC new ice candidate requests."""
+        logger.debug(f"Received patch request: {request}")
+        await small_webrtc_handler.handle_patch_request(request)
+        return {"status": "success"}
+
+    @app.post("/start")
+    async def rtvi_start(request: Request):
+        """Mimic Pipecat Cloud's /start endpoint."""
+        # Parse the request body
+        try:
+            request_data = await request.json()
+            logger.debug(f"Received request: {request_data}")
+        except Exception as e:
+            logger.error(f"Failed to parse request body: {e}")
+            request_data = {}
+
+        # Store session info immediately in memory, replicate the behavior expected on Pipecat Cloud
+        session_id = str(uuid.uuid4())
+        active_sessions[session_id] = request_data
+
+        result: StartBotResult = {"sessionId": session_id}
+        if request_data.get("enableDefaultIceServers"):
+            result["iceConfig"] = IceConfig(
+                iceServers=[IceServer(urls="stun:stun.l.google.com:19302")]
+            )
+
+        return result
+
+    @app.api_route(
+        "/sessions/{session_id}/{path:path}",
+        methods=["GET", "POST", "PUT", "PATCH", "DELETE"],
+    )
+    async def proxy_request(
+        session_id: str, path: str, request: Request, background_tasks: BackgroundTasks
+    ):
+        """Mimic Pipecat Cloud's proxy."""
+        active_session = active_sessions.get(session_id)
+        if active_session is None:
+            return Response(content="Invalid or not-yet-ready session_id", status_code=404)
+
+        if path.endswith("api/offer"):
+            # Parse the request body and convert to SmallWebRTCRequest
+            try:
+                request_data = await request.json()
+                if request.method == HTTPMethod.POST.value:
+                    webrtc_request = SmallWebRTCRequest(
+                        sdp=request_data["sdp"],
+                        type=request_data["type"],
+                        pc_id=request_data.get("pc_id"),
+                        restart_pc=request_data.get("restart_pc"),
+                        request_data=request_data,
+                    )
+                    return await offer(webrtc_request, background_tasks)
+                elif request.method == HTTPMethod.PATCH.value:
+                    patch_request = SmallWebRTCPatchRequest(
+                        pc_id=request_data["pc_id"],
+                        candidates=[IceCandidate(**c) for c in request_data.get("candidates", [])],
+                    )
+                    return await ice_candidate(patch_request)
+            except Exception as e:
+                logger.error(f"Failed to parse WebRTC request: {e}")
+                return Response(content="Invalid WebRTC request", status_code=400)
+
+        logger.info(f"Received request for path: {path}")
+        return Response(status_code=200)
+
     @asynccontextmanager
     async def smallwebrtc_lifespan(app: FastAPI):
         """Manage FastAPI application lifecycle and cleanup connections."""
@@ -289,6 +374,29 @@ def _add_lifespan_to_app(app: FastAPI, new_lifespan):
 
 def _setup_whatsapp_routes(app: FastAPI):
     """Set up WebRTC-specific routes."""
+    WHATSAPP_APP_SECRET = os.getenv("WHATSAPP_APP_SECRET")
+    WHATSAPP_PHONE_NUMBER_ID = os.getenv("WHATSAPP_PHONE_NUMBER_ID")
+    WHATSAPP_TOKEN = os.getenv("WHATSAPP_TOKEN")
+    WHATSAPP_WEBHOOK_VERIFICATION_TOKEN = os.getenv("WHATSAPP_WEBHOOK_VERIFICATION_TOKEN")
+
+    if not all(
+        [
+            WHATSAPP_APP_SECRET,
+            WHATSAPP_PHONE_NUMBER_ID,
+            WHATSAPP_TOKEN,
+            WHATSAPP_WEBHOOK_VERIFICATION_TOKEN,
+        ]
+    ):
+        logger.error(
+            """Missing required environment variables for WhatsApp transport:
+    WHATSAPP_APP_SECRET
+    WHATSAPP_PHONE_NUMBER_ID
+    WHATSAPP_TOKEN
+    WHATSAPP_WEBHOOK_VERIFICATION_TOKEN
+            """
+        )
+        return
+
     try:
         from pipecat_ai_small_webrtc_prebuilt.frontend import SmallWebRTCPrebuiltUI
 
@@ -300,24 +408,7 @@ def _setup_whatsapp_routes(app: FastAPI):
         from pipecat.transports.whatsapp.api import WhatsAppWebhookRequest
         from pipecat.transports.whatsapp.client import WhatsAppClient
     except ImportError as e:
-        logger.error(f"WebRTC transport dependencies not installed: {e}")
-        return
-
-    WHATSAPP_TOKEN = os.getenv("WHATSAPP_TOKEN")
-    WHATSAPP_PHONE_NUMBER_ID = os.getenv("WHATSAPP_PHONE_NUMBER_ID")
-    WHATSAPP_WEBHOOK_VERIFICATION_TOKEN = os.getenv("WHATSAPP_WEBHOOK_VERIFICATION_TOKEN")
-    WHATSAPP_APP_SECRET = os.getenv("WHATSAPP_APP_SECRET")
-
-    if not all(
-        [
-            WHATSAPP_TOKEN,
-            WHATSAPP_PHONE_NUMBER_ID,
-            WHATSAPP_WEBHOOK_VERIFICATION_TOKEN,
-        ]
-    ):
-        logger.debug(
-            "Missing required environment variables for WhatsApp transport. Keeping it disabled."
-        )
+        logger.error(f"WhatsApp transport dependencies not installed: {e}")
         return
 
     # Global WhatsApp client instance
@@ -439,9 +530,9 @@ def _setup_daily_routes(app: FastAPI):
     """Set up Daily-specific routes."""
 
     @app.get("/")
-    async def start_agent():
+    async def create_room_and_start_agent():
         """Launch a Daily bot and redirect to room."""
-        print("Starting bot with Daily transport")
+        print("Starting bot with Daily transport and redirecting to Daily room")
 
         import aiohttp
 
@@ -456,11 +547,11 @@ def _setup_daily_routes(app: FastAPI):
             asyncio.create_task(bot_module.bot(runner_args))
             return RedirectResponse(room_url)
 
-    async def _handle_rtvi_request(request: Request):
-        """Common handler for both /start and /connect endpoints.
+    @app.post("/start")
+    async def start_agent(request: Request):
+        """Handler for /start endpoints.
 
         Expects POST body like::
-
             {
                 "createDailyRoom": true,
                 "dailyRoomProperties": { "start_video_off": true },
@@ -477,47 +568,32 @@ def _setup_daily_routes(app: FastAPI):
             logger.error(f"Failed to parse request body: {e}")
             request_data = {}
 
-        # Extract the body data that should be passed to the bot
-        # This mimics Pipecat Cloud's behavior
-        bot_body = request_data.get("body", {})
-
-        # Log the extracted body data for debugging
-        if bot_body:
-            logger.info(f"Extracted body data for bot: {bot_body}")
-        else:
-            logger.debug("No body data provided in request")
+        create_daily_room = request_data.get("createDailyRoom", False)
+        body = request_data.get("body", {})
 
-        import aiohttp
-
-        from pipecat.runner.daily import configure
+        bot_module = _get_bot_module()
 
-        async with aiohttp.ClientSession() as session:
-            room_url, token = await configure(session)
+        result = None
+        if create_daily_room:
+            import aiohttp
 
-            # Start the bot in the background with extracted body data
-            bot_module = _get_bot_module()
-            runner_args = DailyRunnerArguments(room_url=room_url, token=token, body=bot_body)
-            asyncio.create_task(bot_module.bot(runner_args))
-            # Match PCC /start endpoint response format:
-            return {"dailyRoom": room_url, "dailyToken": token}
+            from pipecat.runner.daily import configure
 
-    @app.post("/start")
-    async def rtvi_start(request: Request):
-        """Launch a Daily bot and return connection info for RTVI clients."""
-        return await _handle_rtvi_request(request)
+            async with aiohttp.ClientSession() as session:
+                room_url, token = await configure(session)
+                runner_args = DailyRunnerArguments(room_url=room_url, token=token, body=body)
+                result = {
+                    "dailyRoom": room_url,
+                    "dailyToken": token,
+                    "sessionId": str(uuid.uuid4()),
+                }
+        else:
+            runner_args = RunnerArguments(body=body)
 
-    @app.post("/connect")
-    async def rtvi_connect(request: Request):
-        """Launch a Daily bot and return connection info for RTVI clients.
+        # Start the bot in the background
+        asyncio.create_task(bot_module.bot(runner_args))
 
-        .. deprecated:: 0.0.78
-            Use /start instead. This endpoint will be removed in a future version.
-        """
-        logger.warning(
-            "DEPRECATED: /connect endpoint is deprecated. Please use /start instead. "
-            "This endpoint will be removed in a future version."
-        )
-        return await _handle_rtvi_request(request)
+        return result
 
 
 def _setup_telephony_routes(app: FastAPI, *, transport_type: str, proxy: str):
@@ -576,8 +652,6 @@ def _setup_telephony_routes(app: FastAPI, *, transport_type: str, proxy: str):
 async def _run_daily_direct():
     """Run Daily bot with direct connection (no FastAPI server)."""
     try:
-        import aiohttp
-
         from pipecat.runner.daily import configure
     except ImportError as e:
         logger.error("Daily transport dependencies not installed.")
@@ -689,6 +763,12 @@ def main():
     parser.add_argument(
         "--verbose", "-v", action="count", default=0, help="Increase logging verbosity"
     )
+    parser.add_argument(
+        "--whatsapp",
+        action="store_true",
+        default=False,
+        help="Ensure requried WhatsApp environment variables are present",
+    )
 
     args = parser.parse_args()
 
@@ -731,10 +811,11 @@ def main():
         print()
         if args.esp32:
             print(f"🚀 Bot ready! (ESP32 mode)")
-            print(f"   → Open http://{args.host}:{args.port}/client in your browser")
+        elif args.whatsapp:
+            print(f"🚀 Bot ready! (WhatsApp)")
         else:
             print(f"🚀 Bot ready!")
-            print(f"   → Open http://{args.host}:{args.port}/client in your browser")
+        print(f"   → Open http://{args.host}:{args.port}/client in your browser")
         print()
     elif args.transport == "daily":
         print()
@@ -752,6 +833,7 @@ def main():
         host=args.host,
         proxy=args.proxy,
         esp32_mode=args.esp32,
+        whatsapp_enabled=args.whatsapp,
         folder=args.folder,
     )
 

pipecat/runner/types.py

@@ -20,9 +20,11 @@ from fastapi import WebSocket
 class RunnerArguments:
     """Base class for runner session arguments."""
 
-    handle_sigint: bool = field(init=False)
-    handle_sigterm: bool = field(init=False)
-    pipeline_idle_timeout_secs: int = field(init=False)
+    # Use kw_only so subclasses don't need to worry about ordering.
+    handle_sigint: bool = field(init=False, kw_only=True)
+    handle_sigterm: bool = field(init=False, kw_only=True)
+    pipeline_idle_timeout_secs: int = field(init=False, kw_only=True)
+    body: Optional[Any] = field(default_factory=dict, kw_only=True)
 
     def __post_init__(self):
         self.handle_sigint = False
@@ -42,7 +44,6 @@ class DailyRunnerArguments(RunnerArguments):
 
     room_url: str
     token: Optional[str] = None
-    body: Optional[Any] = field(default_factory=dict)
 
 
 @dataclass
@@ -55,7 +56,6 @@ class WebSocketRunnerArguments(RunnerArguments):
     """
 
     websocket: WebSocket
-    body: Optional[Any] = field(default_factory=dict)
 
 
 @dataclass

pipecat/services/assemblyai/models.py

@@ -108,6 +108,8 @@ class AssemblyAIConnectionParams(BaseModel):
         end_of_turn_confidence_threshold: Confidence threshold for end-of-turn detection.
         min_end_of_turn_silence_when_confident: Minimum silence duration when confident about end-of-turn.
         max_turn_silence: Maximum silence duration before forcing end-of-turn.
+        keyterms_prompt: List of key terms to guide transcription. Will be JSON serialized before sending.
+        speech_model: Select between English and multilingual models. Defaults to "universal-streaming-english".
     """
 
     sample_rate: int = 16000
@@ -117,3 +119,7 @@ class AssemblyAIConnectionParams(BaseModel):
     end_of_turn_confidence_threshold: Optional[float] = None
     min_end_of_turn_silence_when_confident: Optional[int] = None
     max_turn_silence: Optional[int] = None
+    keyterms_prompt: Optional[List[str]] = None
+    speech_model: Literal["universal-streaming-english", "universal-streaming-multilingual"] = (
+        "universal-streaming-english"
+    )

pipecat/services/assemblyai/stt.py

@@ -174,11 +174,16 @@ class AssemblyAISTTService(STTService):
 
     def _build_ws_url(self) -> str:
         """Build WebSocket URL with query parameters using urllib.parse.urlencode."""
-        params = {
-            k: str(v).lower() if isinstance(v, bool) else v
-            for k, v in self._connection_params.model_dump().items()
-            if v is not None
-        }
+        params = {}
+        for k, v in self._connection_params.model_dump().items():
+            if v is not None:
+                if k == "keyterms_prompt":
+                    params[k] = json.dumps(v)
+                elif isinstance(v, bool):
+                    params[k] = str(v).lower()
+                else:
+                    params[k] = v
+
         if params:
             query_string = urlencode(params)
             return f"{self._api_endpoint_base_url}?{query_string}"
@@ -197,6 +202,8 @@ class AssemblyAISTTService(STTService):
             )
             self._connected = True
             self._receive_task = self.create_task(self._receive_task_handler())
+
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"Failed to connect to AssemblyAI: {e}")
             self._connected = False
@@ -238,6 +245,7 @@ class AssemblyAISTTService(STTService):
             self._websocket = None
             self._connected = False
             self._receive_task = None
+            await self._call_event_handler("on_disconnected")
 
     async def _receive_task_handler(self):
         """Handle incoming WebSocket messages."""

pipecat/services/asyncai/tts.py

@@ -235,6 +235,8 @@ class AsyncAITTSService(InterruptibleTTSService):
             }
 
             await self._get_websocket().send(json.dumps(init_msg))
+
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"{self} initialization error: {e}")
             self._websocket = None
@@ -252,6 +254,7 @@ class AsyncAITTSService(InterruptibleTTSService):
         finally:
             self._websocket = None
             self._started = False
+            await self._call_event_handler("on_disconnected")
 
     def _get_websocket(self):
         if self._websocket:

pipecat/services/aws/llm.py

@@ -720,11 +720,11 @@ class AWSBedrockLLMService(LLMService):
             additional_model_request_fields: Additional model-specific parameters.
         """
 
-        max_tokens: Optional[int] = Field(default_factory=lambda: 4096, ge=1)
-        temperature: Optional[float] = Field(default_factory=lambda: 0.7, ge=0.0, le=1.0)
-        top_p: Optional[float] = Field(default_factory=lambda: 0.999, ge=0.0, le=1.0)
+        max_tokens: Optional[int] = Field(default=None, ge=1)
+        temperature: Optional[float] = Field(default=None, ge=0.0, le=1.0)
+        top_p: Optional[float] = Field(default=None, ge=0.0, le=1.0)
         stop_sequences: Optional[List[str]] = Field(default_factory=lambda: [])
-        latency: Optional[str] = Field(default_factory=lambda: "standard")
+        latency: Optional[str] = Field(default=None)
         additional_model_request_fields: Optional[Dict[str, Any]] = Field(default_factory=dict)
 
     def __init__(
@@ -801,6 +801,24 @@ class AWSBedrockLLMService(LLMService):
         """
         return True
 
+    def _build_inference_config(self) -> Dict[str, Any]:
+        """Build inference config with only the parameters that are set.
+
+        This prevents conflicts with models (e.g., Claude Sonnet 4.5) that don't
+        allow certain parameter combinations like temperature and top_p together.
+
+        Returns:
+            Dictionary containing only the inference parameters that are not None.
+        """
+        inference_config = {}
+        if self._settings["max_tokens"] is not None:
+            inference_config["maxTokens"] = self._settings["max_tokens"]
+        if self._settings["temperature"] is not None:
+            inference_config["temperature"] = self._settings["temperature"]
+        if self._settings["top_p"] is not None:
+            inference_config["topP"] = self._settings["top_p"]
+        return inference_config
+
     async def run_inference(self, context: LLMContext | OpenAILLMContext) -> Optional[str]:
         """Run a one-shot, out-of-band (i.e. out-of-pipeline) inference with the given LLM context.
 
@@ -826,16 +844,16 @@ class AWSBedrockLLMService(LLMService):
         model_id = self.model_name
 
         # Prepare request parameters
+        inference_config = self._build_inference_config()
+
         request_params = {
             "modelId": model_id,
             "messages": messages,
-            "inferenceConfig": {
-                "maxTokens": 8192,
-                "temperature": 0.7,
-                "topP": 0.9,
-            },
         }
 
+        if inference_config:
+            request_params["inferenceConfig"] = inference_config
+
         if system:
             request_params["system"] = system
 
@@ -974,21 +992,20 @@ class AWSBedrockLLMService(LLMService):
             tools = params_from_context["tools"]
             tool_choice = params_from_context["tool_choice"]
 
-            # Set up inference config
-            inference_config = {
-                "maxTokens": self._settings["max_tokens"],
-                "temperature": self._settings["temperature"],
-                "topP": self._settings["top_p"],
-            }
+            # Set up inference config - only include parameters that are set
+            inference_config = self._build_inference_config()
 
             # Prepare request parameters
             request_params = {
                 "modelId": self.model_name,
                 "messages": messages,
-                "inferenceConfig": inference_config,
                 "additionalModelRequestFields": self._settings["additional_model_request_fields"],
             }
 
+            # Only add inference config if it has parameters
+            if inference_config:
+                request_params["inferenceConfig"] = inference_config
+
             # Add system message
             if system:
                 request_params["system"] = system

pipecat/services/aws/nova_sonic/context.py

@@ -8,8 +8,77 @@
 
 This module provides specialized context aggregators and message handling for AWS Nova Sonic,
 including conversation history management and role-specific message processing.
+
+.. 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.
+
+    BEFORE:
+    ```
+    # Setup
+    context = OpenAILLMContext(messages, tools)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    # Context frame type
+    frame: OpenAILLMContextFrame
+
+    # Context type
+    context: AWSNovaSonicLLMContext
+    # or
+    context: OpenAILLMContext
+    ```
+
+    AFTER:
+    ```
+    # Setup
+    context = LLMContext(messages, tools)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    # Context frame type
+    frame: LLMContextFrame
+
+    # Context type
+    context: LLMContext
+    ```
 """
 
+import warnings
+
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Types in pipecat.services.aws.nova_sonic.context (or "
+        "pipecat.services.aws_nova_sonic.context) are deprecated. \n"
+        "AWS Nova Sonic no longer uses types from this module under the hood. \n"
+        "It now uses `LLMContext` and `LLMContextAggregatorPair`. \n"
+        "Using the new patterns should allow you to not need types from this module.\n\n"
+        "BEFORE:\n"
+        "```\n"
+        "# Setup\n"
+        "context = OpenAILLMContext(messages, tools)\n"
+        "context_aggregator = llm.create_context_aggregator(context)\n\n"
+        "# Context frame type\n"
+        "frame: OpenAILLMContextFrame\n\n"
+        "# Context type\n"
+        "context: AWSNovaSonicLLMContext\n"
+        "# or\n"
+        "context: OpenAILLMContext\n\n"
+        "```\n\n"
+        "AFTER:\n"
+        "```\n"
+        "# Setup\n"
+        "context = LLMContext(messages, tools)\n"
+        "context_aggregator = LLMContextAggregatorPair(context)\n\n"
+        "# Context frame type\n"
+        "frame: LLMContextFrame\n\n"
+        "# Context type\n"
+        "context: LLMContext\n\n"
+        "```",
+        DeprecationWarning,
+        stacklevel=2,
+    )
+
 import copy
 from dataclasses import dataclass, field
 from enum import Enum