dv-pipecat-ai 0.0.75.dev840__py3-none-any.whl → 0.0.82.dev776__py3-none-any.whl

{dv_pipecat_ai-0.0.75.dev840.dist-info → dv_pipecat_ai-0.0.82.dev776.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dv-pipecat-ai
-Version: 0.0.75.dev840
+Version: 0.0.82.dev776
 Summary: An open source framework for voice (and multimodal) assistants
 License-Expression: BSD-2-Clause
 Project-URL: Source, https://github.com/pipecat-ai/pipecat

{dv_pipecat_ai-0.0.75.dev840.dist-info → dv_pipecat_ai-0.0.82.dev776.dist-info}/RECORD

@@ -1,4 +1,4 @@
-dv_pipecat_ai-0.0.75.dev840.dist-info/licenses/LICENSE,sha256=DWY2QGf2eMCFhuu2ChairtT6CB7BEFffNVhXWc4Od08,1301
+dv_pipecat_ai-0.0.82.dev776.dist-info/licenses/LICENSE,sha256=DWY2QGf2eMCFhuu2ChairtT6CB7BEFffNVhXWc4Od08,1301
 pipecat/__init__.py,sha256=j0Xm6adxHhd7D06dIyyPV_GlBYLlBnTAERVvD_jAARQ,861
 pipecat/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pipecat/adapters/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -93,7 +93,7 @@ pipecat/processors/aggregators/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5
 pipecat/processors/aggregators/dtmf_aggregator.py,sha256=x2Q8hSFeh_O0B7D7umSV8CDMNduZG2jjBxa6miR-yiU,5308
 pipecat/processors/aggregators/gated.py,sha256=tii0sRrBkRW6y9Xq5iTWPnqlOEejU4VqPIPtdOa61pc,3073
 pipecat/processors/aggregators/gated_openai_llm_context.py,sha256=cr6MT8J6SpPzZbppKPOKe3_pt_5qXC9g6a4wvZDyrec,3005
-pipecat/processors/aggregators/llm_response.py,sha256=SA6_ec2276ij66Kb9Am5XvQ9lcbVHB7ThMLr9wpkqNg,46224
+pipecat/processors/aggregators/llm_response.py,sha256=Ki_xWxPda2N0HCg7eC0Z9Apa6sqxm97Jixc_y8fHw1c,46321
 pipecat/processors/aggregators/openai_llm_context.py,sha256=82q67TsjoAPSESAjzHI5jE9Ffq7yiB3MRtxy71V2RGg,12984
 pipecat/processors/aggregators/sentence.py,sha256=E7e3knfQl6HEGpYMKPklF1aO_gOn-rr7SnynErwfkQk,2235
 pipecat/processors/aggregators/user_response.py,sha256=Jw_54IVZ47S_GU3P_SSU4L2l5J7AiehzU1L5JwiaRJo,1784
@@ -126,6 +126,7 @@ pipecat/serializers/__init__.py,sha256=OV61GQX5ZVU7l7Dt7UTBdv2wUF7ZvtbCoXryo7nno
 pipecat/serializers/base_serializer.py,sha256=OyBUZccs2ZT9mfkBbq2tGsUJMvci6o-j90Cl1sicPaI,2030
 pipecat/serializers/convox.py,sha256=MXCLhV6GMnoP8bI6-EVrObhrftEyTGOmzVeIU5ywmPo,9536
 pipecat/serializers/exotel.py,sha256=LB4wYoXDjPmtkydrZ0G4H4u-SXpQw9KjyRzBZCYloEE,5907
+pipecat/serializers/genesys.py,sha256=5g6_F-OIWSNmStgc6-bDT5mDQkCHHKxcOWSb-F4s2-A,3564
 pipecat/serializers/livekit.py,sha256=caVZlVJGV-SmEXE_H7i3DRo1RvC9FgGCVqi8IYGrpEo,2552
 pipecat/serializers/plivo.py,sha256=EXZZgwxQzhO61spRU98qveMskVnELuHCQg5piBO6tq0,9210
 pipecat/serializers/protobuf.py,sha256=h0UgVvIa3LXxtpbeQUq0tCGicGbDHxjiY6EdxXJO0_s,5162
@@ -135,7 +136,7 @@ pipecat/services/__init__.py,sha256=B0B4BXpPNgYTf0orYxQvdhSyvtZwNj9Whqndgav4r4E,
 pipecat/services/ai_service.py,sha256=mck03zv_-NZ39jhHR3hT_Qu5s6s_JzQ88lpiCtRV87w,5980
 pipecat/services/ai_services.py,sha256=_RrDWfM8adV17atzY9RxK0nXRVM5kbUkKrvN90GAWYM,795
 pipecat/services/image_service.py,sha256=tqJun4nYeyN_PaWqTdF_CFsOiqBf3XX7R4et5Y07mEU,2357
-pipecat/services/llm_service.py,sha256=ybvMa4iqOhdNtlSCFKZJSKug6Jx8GhucsQ_7a9MXBf0,23595
+pipecat/services/llm_service.py,sha256=VUzdf9mP8P9hdKwi2P544vwZOJHzB8ExfTAaKYKcmm8,23704
 pipecat/services/mcp_service.py,sha256=OYftGfdfGlDmjsWbF2b3CuMhPw8B1jcgaZUUYZPIA_o,14298
 pipecat/services/openai.py,sha256=fg5-MIvwqgKTN6i5Kp7GD6XUvMRo3nlughuNt9QqLGA,27546
 pipecat/services/stt_service.py,sha256=tShjVEl374j1Sc3qsdhTuWaT-8NJsAn-3yFw0XLRm4A,11163
@@ -200,6 +201,7 @@ pipecat/services/google/llm_openai.py,sha256=p_aQYpX1e_ffO63oo0cDyj8ZYWb2CO3N-Ii
 pipecat/services/google/llm_vertex.py,sha256=yqs8pqUCTgRj5wvQFHPJbGduoIaXjaqPym5x-lh5LhI,5032
 pipecat/services/google/rtvi.py,sha256=PZb1yVny5YG7_XmJRXPzs3iYapeQ4XHreFN1v6KwTGM,3014
 pipecat/services/google/stt.py,sha256=1vKZNEKZ-KLKp_7lA_VijznSqTwYRFYK1sDn2qteKtI,32814
+pipecat/services/google/test-google-chirp.py,sha256=ji6ta7WDgKMu9yeKovuIVRlcMuk8S6XIyzIokHQY80E,1437
 pipecat/services/google/tts.py,sha256=S_JSPqzLABfuyHLRppNiDmq2g9OFcnJOrfysVg3OHbY,32038
 pipecat/services/grok/__init__.py,sha256=PyaTSnqwxd8jdF5aFTe3lWM-TBhfDyUu9ahRl6nPS-4,251
 pipecat/services/grok/llm.py,sha256=xsJWXqJApfQgEt6z_8U44qUCQJMcpgEdpOHN-u0tNAQ,7330
@@ -332,7 +334,7 @@ pipecat/utils/tracing/service_decorators.py,sha256=HwDCqLGijhYD3F8nxDuQmEw-YkRw0
 pipecat/utils/tracing/setup.py,sha256=7TEgPNpq6M8lww8OQvf0P9FzYc5A30xICGklVA-fua0,2892
 pipecat/utils/tracing/turn_context_provider.py,sha256=ikon3plFOx0XbMrH6DdeHttNpb-U0gzMZIm3bWLc9eI,2485
 pipecat/utils/tracing/turn_trace_observer.py,sha256=dma16SBJpYSOE58YDWy89QzHyQFc_9gQZszKeWixuwc,9725
-dv_pipecat_ai-0.0.75.dev840.dist-info/METADATA,sha256=6BnxCiDkrqjYv7q2PmXwWBwL33GrUm4nrTu0em3yFlY,32457
-dv_pipecat_ai-0.0.75.dev840.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dv_pipecat_ai-0.0.75.dev840.dist-info/top_level.txt,sha256=kQzG20CxGf-nSsHmtXHx3hY2-8zHA3jYg8jk0TajqXc,8
-dv_pipecat_ai-0.0.75.dev840.dist-info/RECORD,,
+dv_pipecat_ai-0.0.82.dev776.dist-info/METADATA,sha256=VJAth6kEBgJT2SJHJ5KnMorgpHZvF6ZMg6Uqc65CL-Q,32457
+dv_pipecat_ai-0.0.82.dev776.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dv_pipecat_ai-0.0.82.dev776.dist-info/top_level.txt,sha256=kQzG20CxGf-nSsHmtXHx3hY2-8zHA3jYg8jk0TajqXc,8
+dv_pipecat_ai-0.0.82.dev776.dist-info/RECORD,,

pipecat/processors/aggregators/llm_response.py

@@ -541,7 +541,8 @@ class LLMUserContextAggregator(LLMContextResponseAggregator):
                     self.logger.debug(
                         "Triggering interruption - pushing BotInterruptionFrame and aggregation"
                     )
-                    await self.push_frame(BotInterruptionFrame(), FrameDirection.UPSTREAM)
+                    # await self.push_frame(BotInterruptionFrame(), FrameDirection.UPSTREAM)
+                    await self.push_frame(StartInterruptionFrame(), FrameDirection.DOWNSTREAM)
                     self.logger.debug("Pushed BotInterruptionFrame")
                 # No interruption config - normal behavior (always push aggregation)
                 await self._process_aggregation()

pipecat/serializers/genesys.py

@@ -0,0 +1,95 @@
+import base64
+import json
+from typing import Optional
+
+from pydantic import BaseModel
+
+from pipecat.audio.utils import create_default_resampler, pcm_to_ulaw, ulaw_to_pcm
+from pipecat.frames.frames import (
+    AudioRawFrame,
+    Frame,
+    InputAudioRawFrame,
+    InputDTMFFrame,
+    KeypadEntry,
+    StartFrame,
+    StartInterruptionFrame,
+    TransportMessageFrame,
+    TransportMessageUrgentFrame,
+)
+from pipecat.serializers.base_serializer import FrameSerializer, FrameSerializerType
+
+
+class GenesysFrameSerializer(FrameSerializer):
+    class InputParams(BaseModel):
+        genesys_sample_rate: int = 8000  # Default Genesys rate (8kHz)
+        sample_rate: Optional[int] = None  # Pipeline input rate
+
+    def __init__(self, session_id: str, params: InputParams = InputParams()):
+        self._session_id = session_id
+        self._params = params
+        self._genesys_sample_rate = self._params.genesys_sample_rate
+        self._sample_rate = 0  # Pipeline input rate
+        self._resampler = create_default_resampler()
+        self._seq = 1  # Sequence number for outgoing messages
+
+    @property
+    def type(self) -> FrameSerializerType:
+        return FrameSerializerType.TEXT
+
+    async def setup(self, frame: StartFrame):
+        self._sample_rate = self._params.sample_rate or frame.audio_in_sample_rate
+
+    async def serialize(self, frame: Frame) -> str | bytes | None:
+        if isinstance(frame, StartInterruptionFrame):
+            answer = {
+                "version": "2",
+                "type": "clearAudio",  # Or appropriate event for interruption
+                "seq": self._seq,
+                "id": self._session_id,
+            }
+            self._seq += 1
+            return json.dumps(answer)
+        elif isinstance(frame, AudioRawFrame):
+            data = frame.audio
+            # Convert PCM to 8kHz μ-law for Genesys
+            serialized_data = await pcm_to_ulaw(
+                data, frame.sample_rate, self._genesys_sample_rate, self._resampler
+            )
+            payload = base64.b64encode(serialized_data).decode("utf-8")
+            answer = {
+                "version": "2",
+                "type": "audio",
+                "seq": self._seq,
+                "id": self._session_id,
+                "media": {
+                    "payload": payload,
+                    "format": "PCMU",
+                    "rate": self._genesys_sample_rate,
+                },
+            }
+            self._seq += 1
+            return json.dumps(answer)
+        elif isinstance(frame, (TransportMessageFrame, TransportMessageUrgentFrame)):
+            return json.dumps(frame.message)
+
+    async def deserialize(self, data: str | bytes) -> Frame | None:
+        message = json.loads(data)
+        if message.get("type") == "audio":
+            payload_base64 = message["media"]["payload"]
+            payload = base64.b64decode(payload_base64)
+            # Convert Genesys 8kHz μ-law to PCM at pipeline input rate
+            deserialized_data = await ulaw_to_pcm(
+                payload, self._genesys_sample_rate, self._sample_rate, self._resampler
+            )
+            audio_frame = InputAudioRawFrame(
+                audio=deserialized_data, num_channels=1, sample_rate=self._sample_rate
+            )
+            return audio_frame
+        elif message.get("type") == "dtmf":
+            digit = message.get("dtmf", {}).get("digit")
+            try:
+                return InputDTMFFrame(KeypadEntry(digit))
+            except ValueError:
+                return None
+        else:
+            return None

pipecat/services/google/test-google-chirp.py

@@ -0,0 +1,45 @@
+import asyncio
+import os
+
+from pipecat.frames.frames import TTSAudioRawFrame
+from pipecat.services.google.tts import GoogleTTSService
+
+
+async def test_chirp_tts():
+    # Get credentials from environment variable
+    credentials_path = (
+        "/Users/kalicharanvemuru/Documents/Code/pipecat/examples/ringg-chatbot/creds.json"
+    )
+
+    if not credentials_path or not os.path.exists(credentials_path):
+        raise ValueError(
+            "Please set GOOGLE_APPLICATION_CREDENTIALS environment variable to your service account key file"
+        )
+
+    # Initialize the TTS service with Chirp voice
+    tts = GoogleTTSService(
+        credentials_path=credentials_path,
+        voice_id="en-US-Chirp3-HD-Charon",  # Using Chirp3 HD Charon voice
+        sample_rate=24000,
+    )
+
+    # Test text
+    test_text = "Hello, this is a test of the Google TTS service with Chirp voice."
+
+    print(f"Testing TTS with text: {test_text}")
+
+    # Generate speech
+    try:
+        async for frame in tts.run_tts(test_text):
+            if isinstance(frame, TTSAudioRawFrame):
+                print(f"Received audio chunk of size: {len(frame.audio)} bytes")
+            else:
+                print(f"Received frame: {frame.__class__.__name__}")
+
+        print("TTS generation completed successfully!")
+    except Exception as e:
+        print(f"Error during TTS generation: {str(e)}")
+
+
+if __name__ == "__main__":
+    asyncio.run(test_chirp_tts())

pipecat/services/llm_service.py

@@ -254,9 +254,11 @@ class LLMService(AIService):
             await self._handle_interruptions(frame)
 
     async def _handle_interruptions(self, _: StartInterruptionFrame):
+        # logger.info("In LLM Handling interruptions")
         for function_name, entry in self._functions.items():
             if entry.cancel_on_interruption:
                 await self._cancel_function_call(function_name)
+        # logger.info("in LLM Interruptions handled")
 
     def register_function(
         self,