dv-pipecat-ai 0.0.85.dev7__py3-none-any.whl → 0.0.85.dev698__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.

This version of dv-pipecat-ai might be problematic. Click here for more details.

Files changed (156) hide show
  1. {dv_pipecat_ai-0.0.85.dev7.dist-info → dv_pipecat_ai-0.0.85.dev698.dist-info}/METADATA +78 -117
  2. {dv_pipecat_ai-0.0.85.dev7.dist-info → dv_pipecat_ai-0.0.85.dev698.dist-info}/RECORD +156 -122
  3. pipecat/adapters/base_llm_adapter.py +38 -1
  4. pipecat/adapters/services/anthropic_adapter.py +9 -14
  5. pipecat/adapters/services/aws_nova_sonic_adapter.py +5 -0
  6. pipecat/adapters/services/bedrock_adapter.py +236 -13
  7. pipecat/adapters/services/gemini_adapter.py +12 -8
  8. pipecat/adapters/services/open_ai_adapter.py +19 -7
  9. pipecat/adapters/services/open_ai_realtime_adapter.py +5 -0
  10. pipecat/audio/filters/krisp_viva_filter.py +193 -0
  11. pipecat/audio/filters/noisereduce_filter.py +15 -0
  12. pipecat/audio/turn/base_turn_analyzer.py +9 -1
  13. pipecat/audio/turn/smart_turn/base_smart_turn.py +14 -8
  14. pipecat/audio/turn/smart_turn/data/__init__.py +0 -0
  15. pipecat/audio/turn/smart_turn/data/smart-turn-v3.0.onnx +0 -0
  16. pipecat/audio/turn/smart_turn/http_smart_turn.py +6 -2
  17. pipecat/audio/turn/smart_turn/local_smart_turn.py +1 -1
  18. pipecat/audio/turn/smart_turn/local_smart_turn_v2.py +1 -1
  19. pipecat/audio/turn/smart_turn/local_smart_turn_v3.py +124 -0
  20. pipecat/audio/vad/data/README.md +10 -0
  21. pipecat/audio/vad/vad_analyzer.py +13 -1
  22. pipecat/extensions/voicemail/voicemail_detector.py +5 -5
  23. pipecat/frames/frames.py +120 -87
  24. pipecat/observers/loggers/debug_log_observer.py +3 -3
  25. pipecat/observers/loggers/llm_log_observer.py +7 -3
  26. pipecat/observers/loggers/user_bot_latency_log_observer.py +22 -10
  27. pipecat/pipeline/runner.py +12 -4
  28. pipecat/pipeline/service_switcher.py +64 -36
  29. pipecat/pipeline/task.py +85 -24
  30. pipecat/processors/aggregators/dtmf_aggregator.py +28 -22
  31. pipecat/processors/aggregators/{gated_openai_llm_context.py → gated_llm_context.py} +9 -9
  32. pipecat/processors/aggregators/gated_open_ai_llm_context.py +12 -0
  33. pipecat/processors/aggregators/llm_response.py +6 -7
  34. pipecat/processors/aggregators/llm_response_universal.py +19 -15
  35. pipecat/processors/aggregators/user_response.py +6 -6
  36. pipecat/processors/aggregators/vision_image_frame.py +24 -2
  37. pipecat/processors/audio/audio_buffer_processor.py +43 -8
  38. pipecat/processors/filters/stt_mute_filter.py +2 -0
  39. pipecat/processors/frame_processor.py +103 -17
  40. pipecat/processors/frameworks/langchain.py +8 -2
  41. pipecat/processors/frameworks/rtvi.py +209 -68
  42. pipecat/processors/frameworks/strands_agents.py +170 -0
  43. pipecat/processors/logger.py +2 -2
  44. pipecat/processors/transcript_processor.py +4 -4
  45. pipecat/processors/user_idle_processor.py +3 -6
  46. pipecat/runner/run.py +270 -50
  47. pipecat/runner/types.py +2 -0
  48. pipecat/runner/utils.py +51 -10
  49. pipecat/serializers/exotel.py +5 -5
  50. pipecat/serializers/livekit.py +20 -0
  51. pipecat/serializers/plivo.py +6 -9
  52. pipecat/serializers/protobuf.py +6 -5
  53. pipecat/serializers/telnyx.py +2 -2
  54. pipecat/serializers/twilio.py +43 -23
  55. pipecat/services/ai_service.py +2 -6
  56. pipecat/services/anthropic/llm.py +2 -25
  57. pipecat/services/asyncai/tts.py +2 -3
  58. pipecat/services/aws/__init__.py +1 -0
  59. pipecat/services/aws/llm.py +122 -97
  60. pipecat/services/aws/nova_sonic/__init__.py +0 -0
  61. pipecat/services/aws/nova_sonic/context.py +367 -0
  62. pipecat/services/aws/nova_sonic/frames.py +25 -0
  63. pipecat/services/aws/nova_sonic/llm.py +1155 -0
  64. pipecat/services/aws/stt.py +1 -3
  65. pipecat/services/aws_nova_sonic/__init__.py +19 -1
  66. pipecat/services/aws_nova_sonic/aws.py +11 -1151
  67. pipecat/services/aws_nova_sonic/context.py +13 -355
  68. pipecat/services/aws_nova_sonic/frames.py +13 -17
  69. pipecat/services/azure/realtime/__init__.py +0 -0
  70. pipecat/services/azure/realtime/llm.py +65 -0
  71. pipecat/services/azure/stt.py +15 -0
  72. pipecat/services/cartesia/tts.py +2 -2
  73. pipecat/services/deepgram/__init__.py +1 -0
  74. pipecat/services/deepgram/flux/__init__.py +0 -0
  75. pipecat/services/deepgram/flux/stt.py +636 -0
  76. pipecat/services/elevenlabs/__init__.py +2 -1
  77. pipecat/services/elevenlabs/stt.py +254 -276
  78. pipecat/services/elevenlabs/tts.py +5 -5
  79. pipecat/services/fish/tts.py +2 -2
  80. pipecat/services/gemini_multimodal_live/events.py +38 -524
  81. pipecat/services/gemini_multimodal_live/file_api.py +23 -173
  82. pipecat/services/gemini_multimodal_live/gemini.py +41 -1403
  83. pipecat/services/gladia/stt.py +56 -72
  84. pipecat/services/google/__init__.py +1 -0
  85. pipecat/services/google/gemini_live/__init__.py +3 -0
  86. pipecat/services/google/gemini_live/file_api.py +189 -0
  87. pipecat/services/google/gemini_live/llm.py +1582 -0
  88. pipecat/services/google/gemini_live/llm_vertex.py +184 -0
  89. pipecat/services/google/llm.py +15 -11
  90. pipecat/services/google/llm_openai.py +3 -3
  91. pipecat/services/google/llm_vertex.py +86 -16
  92. pipecat/services/google/tts.py +7 -3
  93. pipecat/services/heygen/api.py +2 -0
  94. pipecat/services/heygen/client.py +8 -4
  95. pipecat/services/heygen/video.py +2 -0
  96. pipecat/services/hume/__init__.py +5 -0
  97. pipecat/services/hume/tts.py +220 -0
  98. pipecat/services/inworld/tts.py +6 -6
  99. pipecat/services/llm_service.py +15 -5
  100. pipecat/services/lmnt/tts.py +2 -2
  101. pipecat/services/mcp_service.py +4 -2
  102. pipecat/services/mem0/memory.py +6 -5
  103. pipecat/services/mistral/llm.py +29 -8
  104. pipecat/services/moondream/vision.py +42 -16
  105. pipecat/services/neuphonic/tts.py +2 -2
  106. pipecat/services/openai/__init__.py +1 -0
  107. pipecat/services/openai/base_llm.py +27 -20
  108. pipecat/services/openai/realtime/__init__.py +0 -0
  109. pipecat/services/openai/realtime/context.py +272 -0
  110. pipecat/services/openai/realtime/events.py +1106 -0
  111. pipecat/services/openai/realtime/frames.py +37 -0
  112. pipecat/services/openai/realtime/llm.py +829 -0
  113. pipecat/services/openai/tts.py +16 -8
  114. pipecat/services/openai_realtime/__init__.py +27 -0
  115. pipecat/services/openai_realtime/azure.py +21 -0
  116. pipecat/services/openai_realtime/context.py +21 -0
  117. pipecat/services/openai_realtime/events.py +21 -0
  118. pipecat/services/openai_realtime/frames.py +21 -0
  119. pipecat/services/openai_realtime_beta/azure.py +16 -0
  120. pipecat/services/openai_realtime_beta/openai.py +17 -5
  121. pipecat/services/playht/tts.py +31 -4
  122. pipecat/services/rime/tts.py +3 -4
  123. pipecat/services/sarvam/tts.py +2 -6
  124. pipecat/services/simli/video.py +2 -2
  125. pipecat/services/speechmatics/stt.py +1 -7
  126. pipecat/services/stt_service.py +34 -0
  127. pipecat/services/tavus/video.py +2 -2
  128. pipecat/services/tts_service.py +9 -9
  129. pipecat/services/vision_service.py +7 -6
  130. pipecat/tests/utils.py +4 -4
  131. pipecat/transcriptions/language.py +41 -1
  132. pipecat/transports/base_input.py +17 -42
  133. pipecat/transports/base_output.py +42 -26
  134. pipecat/transports/daily/transport.py +199 -26
  135. pipecat/transports/heygen/__init__.py +0 -0
  136. pipecat/transports/heygen/transport.py +381 -0
  137. pipecat/transports/livekit/transport.py +228 -63
  138. pipecat/transports/local/audio.py +6 -1
  139. pipecat/transports/local/tk.py +11 -2
  140. pipecat/transports/network/fastapi_websocket.py +1 -1
  141. pipecat/transports/smallwebrtc/connection.py +98 -19
  142. pipecat/transports/smallwebrtc/request_handler.py +204 -0
  143. pipecat/transports/smallwebrtc/transport.py +65 -23
  144. pipecat/transports/tavus/transport.py +23 -12
  145. pipecat/transports/websocket/client.py +41 -5
  146. pipecat/transports/websocket/fastapi.py +21 -11
  147. pipecat/transports/websocket/server.py +14 -7
  148. pipecat/transports/whatsapp/api.py +8 -0
  149. pipecat/transports/whatsapp/client.py +47 -0
  150. pipecat/utils/base_object.py +54 -22
  151. pipecat/utils/string.py +12 -1
  152. pipecat/utils/tracing/service_decorators.py +21 -21
  153. {dv_pipecat_ai-0.0.85.dev7.dist-info → dv_pipecat_ai-0.0.85.dev698.dist-info}/WHEEL +0 -0
  154. {dv_pipecat_ai-0.0.85.dev7.dist-info → dv_pipecat_ai-0.0.85.dev698.dist-info}/licenses/LICENSE +0 -0
  155. {dv_pipecat_ai-0.0.85.dev7.dist-info → dv_pipecat_ai-0.0.85.dev698.dist-info}/top_level.txt +0 -0
  156. /pipecat/services/{aws_nova_sonic → aws/nova_sonic}/ready.wav +0 -0
pipecat/utils/tracing/service_decorators.py CHANGED
@@ -651,9 +651,9 @@ def traced_gemini_live(operation: str) -> Callable:
651
651
 
652
652
  elif operation == "llm_tool_call" and args:
653
653
  # Extract tool call information
654
- evt = args[0] if args else None
655
- if evt and hasattr(evt, "toolCall") and evt.toolCall.functionCalls:
656
- function_calls = evt.toolCall.functionCalls
654
+ msg = args[0] if args else None
655
+ if msg and hasattr(msg, "tool_call") and msg.tool_call.function_calls:
656
+ function_calls = msg.tool_call.function_calls
657
657
  if function_calls:
658
658
  # Add information about the first function call
659
659
  call = function_calls[0]
@@ -722,19 +722,19 @@ def traced_gemini_live(operation: str) -> Callable:
722
722
 
723
723
  elif operation == "llm_response" and args:
724
724
  # Extract usage and response metadata from turn complete event
725
- evt = args[0] if args else None
726
- if evt and hasattr(evt, "usageMetadata") and evt.usageMetadata:
727
- usage = evt.usageMetadata
725
+ msg = args[0] if args else None
726
+ if msg and hasattr(msg, "usage_metadata") and msg.usage_metadata:
727
+ usage = msg.usage_metadata
728
728
 
729
729
  # Token usage - basic attributes for span visibility
730
- if hasattr(usage, "promptTokenCount"):
731
- operation_attrs["tokens.prompt"] = usage.promptTokenCount or 0
732
- if hasattr(usage, "responseTokenCount"):
730
+ if hasattr(usage, "prompt_token_count"):
731
+ operation_attrs["tokens.prompt"] = usage.prompt_token_count or 0
732
+ if hasattr(usage, "response_token_count"):
733
733
  operation_attrs["tokens.completion"] = (
734
- usage.responseTokenCount or 0
734
+ usage.response_token_count or 0
735
735
  )
736
- if hasattr(usage, "totalTokenCount"):
737
- operation_attrs["tokens.total"] = usage.totalTokenCount or 0
736
+ if hasattr(usage, "total_token_count"):
737
+ operation_attrs["tokens.total"] = usage.total_token_count or 0
738
738
 
739
739
  # Get output text and modality from service state
740
740
  text = getattr(self, "_bot_text_buffer", "")
@@ -751,9 +751,9 @@ def traced_gemini_live(operation: str) -> Callable:
751
751
 
752
752
  # Add turn completion status
753
753
  if (
754
- evt
755
- and hasattr(evt, "serverContent")
756
- and evt.serverContent.turnComplete
754
+ msg
755
+ and hasattr(msg, "server_content")
756
+ and msg.server_content.turn_complete
757
757
  ):
758
758
  operation_attrs["turn_complete"] = True
759
759
 
@@ -772,16 +772,16 @@ def traced_gemini_live(operation: str) -> Callable:
772
772
 
773
773
  # For llm_response operation, also handle token usage metrics
774
774
  if operation == "llm_response" and hasattr(self, "start_llm_usage_metrics"):
775
- evt = args[0] if args else None
776
- if evt and hasattr(evt, "usageMetadata") and evt.usageMetadata:
777
- usage = evt.usageMetadata
775
+ msg = args[0] if args else None
776
+ if msg and hasattr(msg, "usage_metadata") and msg.usage_metadata:
777
+ usage = msg.usage_metadata
778
778
  # Create LLMTokenUsage object
779
779
  from pipecat.metrics.metrics import LLMTokenUsage
780
780
 
781
781
  tokens = LLMTokenUsage(
782
- prompt_tokens=usage.promptTokenCount or 0,
783
- completion_tokens=usage.responseTokenCount or 0,
784
- total_tokens=usage.totalTokenCount or 0,
782
+ prompt_tokens=usage.prompt_token_count or 0,
783
+ completion_tokens=usage.response_token_count or 0,
784
+ total_tokens=usage.total_token_count or 0,
785
785
  )
786
786
  _add_token_usage_to_span(current_span, tokens)
787
787