diff --git a/CHANGELOG.md b/CHANGELOG.md index 2fc5abde4..41d1b6236 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,7 +5,18 @@ All notable changes to **Pipecat** will be documented in this file. The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). -## [Unreleased] +## [0.0.71] - 2025-06-10 + +### Added + +- Adds a parameter called `additional_span_attributes` to PipelineTask that + lets you add any additional attributes you'd like to the conversation span. + +### Fixed + +- Fixed an issue with `CartesiaSTTService` initialization. + +## [0.0.70] - 2025-06-10 ### Added diff --git a/README.md b/README.md index f906cb8bb..7ec4c6000 100644 --- a/README.md +++ b/README.md @@ -53,7 +53,7 @@ You can connect to Pipecat from any platform using our official SDKs: | Category | Services | | ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), Cartesia, [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Parakeet (NVIDIA)](https://docs.pipecat.ai/server/services/stt/parakeet), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper) | +| Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Parakeet (NVIDIA)](https://docs.pipecat.ai/server/services/stt/parakeet), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper) | | LLMs | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [Together AI](https://docs.pipecat.ai/server/services/llm/together) | | Text-to-Speech | [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [FastPitch (NVIDIA)](https://docs.pipecat.ai/server/services/tts/fastpitch), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) | | Speech-to-Speech | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai) | diff --git a/examples/foundational/22b-natural-conversation-proposal.py b/examples/foundational/22b-natural-conversation-proposal.py index 1b03f341e..b76bfd274 100644 --- a/examples/foundational/22b-natural-conversation-proposal.py +++ b/examples/foundational/22b-natural-conversation-proposal.py @@ -312,9 +312,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si # to start the conversation. bot_output_gate = OutputGate(notifier=notifier, start_open=True) - async def block_user_stopped_speaking(frame): - return not isinstance(frame, UserStoppedSpeakingFrame) - async def pass_only_llm_trigger_frames(frame): return ( isinstance(frame, OpenAILLMContextFrame) @@ -331,11 +328,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si stt, context_aggregator.user(), ParallelPipeline( - [ - # Pass everything except UserStoppedSpeaking to the elements after - # this ParallelPipeline - FunctionFilter(filter=block_user_stopped_speaking), - ], [ # Ignore everything except an OpenAILLMContextFrame. Pass a specially constructed # LLMMessagesFrame to the statement classifier LLM. The only frame this diff --git a/src/pipecat/pipeline/task.py b/src/pipecat/pipeline/task.py index 6bf5dd688..736f98244 100644 --- a/src/pipecat/pipeline/task.py +++ b/src/pipecat/pipeline/task.py @@ -184,7 +184,9 @@ class PipelineTask(BaseTask): the idle timeout is reached. enable_turn_tracking: Whether to enable turn tracking. enable_turn_tracing: Whether to enable turn tracing. - + conversation_id: Optional custom ID for the conversation. + additional_span_attributes: Optional dictionary of attributes to propagate as + OpenTelemetry conversation span attributes. """ def __init__( @@ -205,6 +207,7 @@ class PipelineTask(BaseTask): enable_turn_tracking: bool = True, enable_tracing: bool = False, conversation_id: Optional[str] = None, + additional_span_attributes: Optional[dict] = None, ): super().__init__() self._pipeline = pipeline @@ -217,6 +220,7 @@ class PipelineTask(BaseTask): self._enable_turn_tracking = enable_turn_tracking self._enable_tracing = enable_tracing and is_tracing_available() self._conversation_id = conversation_id + self._additional_span_attributes = additional_span_attributes or {} if self._params.observers: import warnings @@ -235,7 +239,9 @@ class PipelineTask(BaseTask): observers.append(self._turn_tracking_observer) if self._enable_tracing and self._turn_tracking_observer: self._turn_trace_observer = TurnTraceObserver( - self._turn_tracking_observer, conversation_id=self._conversation_id + self._turn_tracking_observer, + conversation_id=self._conversation_id, + additional_span_attributes=self._additional_span_attributes, ) observers.append(self._turn_trace_observer) self._finished = False diff --git a/src/pipecat/services/cartesia/stt.py b/src/pipecat/services/cartesia/stt.py index 618908ed9..104e4b2c5 100644 --- a/src/pipecat/services/cartesia/stt.py +++ b/src/pipecat/services/cartesia/stt.py @@ -101,7 +101,7 @@ class CartesiaSTTService(STTService): ) self._settings = merged_options - self.set_model_name(merged_options["model"]) + self.set_model_name(merged_options.model) self._api_key = api_key self._base_url = base_url or "api.cartesia.ai" self._connection = None diff --git a/src/pipecat/utils/tracing/turn_trace_observer.py b/src/pipecat/utils/tracing/turn_trace_observer.py index 26fc5b38a..f67ca3b28 100644 --- a/src/pipecat/utils/tracing/turn_trace_observer.py +++ b/src/pipecat/utils/tracing/turn_trace_observer.py @@ -35,7 +35,11 @@ class TurnTraceObserver(BaseObserver): """ def __init__( - self, turn_tracker: TurnTrackingObserver, conversation_id: Optional[str] = None, **kwargs + self, + turn_tracker: TurnTrackingObserver, + conversation_id: Optional[str] = None, + additional_span_attributes: Optional[dict] = None, + **kwargs, ): super().__init__(**kwargs) self._turn_tracker = turn_tracker @@ -47,6 +51,7 @@ class TurnTraceObserver(BaseObserver): # Conversation tracking properties self._conversation_span: Optional["Span"] = None self._conversation_id = conversation_id + self._additional_span_attributes = additional_span_attributes or {} if turn_tracker: @@ -89,6 +94,9 @@ class TurnTraceObserver(BaseObserver): # Set span attributes self._conversation_span.set_attribute("conversation.id", conversation_id) self._conversation_span.set_attribute("conversation.type", "voice") + # Set custom otel attributes if provided + for k, v in (self._additional_span_attributes or {}).items(): + self._conversation_span.set_attribute(k, v) # Update the conversation context provider context_provider.set_current_conversation_context(