dv-pipecat-ai 0.0.85.dev853__py3-none-any.whl → 0.0.85.dev856__py3-none-any.whl

{dv_pipecat_ai-0.0.85.dev853.dist-info → dv_pipecat_ai-0.0.85.dev856.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dv-pipecat-ai
-Version: 0.0.85.dev853
+Version: 0.0.85.dev856
 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-0.0.85.dev853.dist-info → dv_pipecat_ai-0.0.85.dev856.dist-info}/RECORD

@@ -1,4 +1,4 @@
-dv_pipecat_ai-0.0.85.dev853.dist-info/licenses/LICENSE,sha256=DWY2QGf2eMCFhuu2ChairtT6CB7BEFffNVhXWc4Od08,1301
+dv_pipecat_ai-0.0.85.dev856.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
@@ -217,7 +217,7 @@ pipecat/services/deepgram/flux/stt.py,sha256=yCZodrHAOShgYy_GbdviX8iAuh36dBgDL41
 pipecat/services/deepseek/__init__.py,sha256=bU5z_oNGzgrF_YpsD9pYIMtEibeZFaUobbRjJ9WcYyE,259
 pipecat/services/deepseek/llm.py,sha256=5KjpU2blmhUTM3LcRE1ymdsk6OmoFkIzeQgyNOGwQh8,3112
 pipecat/services/elevenlabs/__init__.py,sha256=cMx5v0HEMh4WetMm5byR9tIjG6_wNVs9UxqWyB3tjlM,313
-pipecat/services/elevenlabs/stt.py,sha256=dy88MvQdhUQ-SFA7YTBRykZsIozMnnYQaJ4og1RYlVc,30811
+pipecat/services/elevenlabs/stt.py,sha256=c-6GDeyZCMcXu4FmcG0vugBRsUnq8Iz_L9XX_Y_8TlM,29453
 pipecat/services/elevenlabs/tts.py,sha256=skUndgUatx2F5rjg2tBZLutB8k9B9Cjy-cUeglCDdwc,45314
 pipecat/services/fal/__init__.py,sha256=z_kfZETvUcKy68Lyvni4B-RtdkOvz3J3eh6sFDVKq6M,278
 pipecat/services/fal/image.py,sha256=vArKLKrIGoZfw_xeZY_E7zbUzfzVsScj-R7mOmVqjRQ,4585
@@ -280,7 +280,7 @@ pipecat/services/nim/llm.py,sha256=o4WPGI6kOmSiMV7WwOZ0cNEAoq9hW4Aqs2R8X7c9i94,4
 pipecat/services/ollama/__init__.py,sha256=aw-25zYsR8LR74OFFlMKMTnJjaKwOzdPWVsClueNRkI,255
 pipecat/services/ollama/llm.py,sha256=rfpG92LRHGJlpENKhF6ld8CLVS9DxlKW-WRVNldOIGs,1605
 pipecat/services/openai/__init__.py,sha256=V0ZVa8PzEm3hmcStYICbAsYwfgk4ytZ6kiQoq9UZPmI,354
-pipecat/services/openai/base_llm.py,sha256=jOiWacimREywCMZZwAwH8RAHCbwnnXvbqAjWQUYA0yM,20727
+pipecat/services/openai/base_llm.py,sha256=mrHRwYL-0lYr0BhJMg_ByTfqY2no6T8DOrhqMDztBlY,21518
 pipecat/services/openai/image.py,sha256=3e3h-dVQ6DQuQE7fp8akXwRMd-oYOdGuZg7RCOjHu9A,2994
 pipecat/services/openai/llm.py,sha256=_aKtz1VebSFUUenT3tH6mBW9pSCm65_u45cDu_dkTzs,7396
 pipecat/services/openai/stt.py,sha256=Idf0k73kxFyDgNRBt62MFpoKKNsBV9bwvJteJ6MGWzQ,2419
@@ -351,7 +351,7 @@ pipecat/sync/event_notifier.py,sha256=h50fC-RBGaGldWZx_wpgOmMIwJiq0PeNwQq5GPmfRR
 pipecat/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pipecat/tests/utils.py,sha256=DEHDQV8uhCuKIqoHUPGVdUoCiKqTCG9zv5GqLXWWwvY,7870
 pipecat/transcriptions/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pipecat/transcriptions/language.py,sha256=-mWI1MiZbasuoqZTOBH69dAmoM7-UJzWq9rSCcrnmh4,8228
+pipecat/transcriptions/language.py,sha256=9kqmqCJF2NUTksWn0TH7-huRwtDqQzzALKzF1CnK_cY,10106
 pipecat/transports/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pipecat/transports/base_input.py,sha256=AkdE-j9UksjIrUGJc7laMOaknXgOS7L22D5sehZ-6ew,20176
 pipecat/transports/base_output.py,sha256=T_NfU38sT6wKxXF1jA7hW5eLhTK11pundQBxAojswW8,36723
@@ -416,7 +416,7 @@ pipecat/utils/tracing/service_decorators.py,sha256=fwzxFpi8DJl6BJbK74G0UEB4ccMJg
 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-0.0.85.dev853.dist-info/METADATA,sha256=EYGfmlCPPW0nGP9R-LdVgrrq-88dt6s8U_f1bf5PXqc,32955
-dv_pipecat_ai-0.0.85.dev853.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dv_pipecat_ai-0.0.85.dev853.dist-info/top_level.txt,sha256=kQzG20CxGf-nSsHmtXHx3hY2-8zHA3jYg8jk0TajqXc,8
-dv_pipecat_ai-0.0.85.dev853.dist-info/RECORD,,
+dv_pipecat_ai-0.0.85.dev856.dist-info/METADATA,sha256=61LBrVZvlHne5jwbVTqjC0ZEtrErzfnhK5IXbIHs0Sk,32955
+dv_pipecat_ai-0.0.85.dev856.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dv_pipecat_ai-0.0.85.dev856.dist-info/top_level.txt,sha256=kQzG20CxGf-nSsHmtXHx3hY2-8zHA3jYg8jk0TajqXc,8
+dv_pipecat_ai-0.0.85.dev856.dist-info/RECORD,,

pipecat/services/elevenlabs/stt.py

@@ -34,7 +34,7 @@ from pipecat.frames.frames import (
 )
 from pipecat.processors.frame_processor import FrameDirection
 from pipecat.services.stt_service import SegmentedSTTService, WebsocketSTTService
-from pipecat.transcriptions.language import Language
+from pipecat.transcriptions.language import Language, resolve_language
 from pipecat.utils.time import time_now_iso8601
 from pipecat.utils.tracing.service_decorators import traced_stt
 
@@ -61,7 +61,7 @@ def language_to_elevenlabs_language(language: Language) -> Optional[str]:
     Returns:
         The corresponding ElevenLabs language code, or None if not supported.
     """
-    BASE_LANGUAGES = {
+    LANGUAGE_MAP = {
         Language.AF: "afr",  # Afrikaans
         Language.AM: "amh",  # Amharic
         Language.AR: "ara",  # Arabic
@@ -163,21 +163,7 @@ def language_to_elevenlabs_language(language: Language) -> Optional[str]:
         Language.ZU: "zul",  # Zulu
     }
 
-    result = BASE_LANGUAGES.get(language)
-
-    # If not found in base languages, try to find the base language from a variant
-    # For example, Language.EN_US (value "en-US") -> Language("en") -> "eng"
-    if not result:
-        lang_str = str(language.value)
-        base_code = lang_str.split("-")[0]  # Get "en" from "en-US"
-        try:
-            base_language = Language(base_code)
-            result = BASE_LANGUAGES.get(base_language)
-        except (ValueError, KeyError):
-            # If base language not found in Language enum, return None
-            result = None
-
-    return result
+    return resolve_language(language, LANGUAGE_MAP, use_base_code=False)
 
 
 class ElevenLabsSTTService(SegmentedSTTService):
@@ -365,8 +351,8 @@ class ElevenLabsSTTService(SegmentedSTTService):
                 )
 
         except Exception as e:
-            logger.error(f"ElevenLabs STT error: {e}")
-            yield ErrorFrame(f"ElevenLabs STT error: {str(e)}")
+            logger.error(f"{self} exception: {e}")
+            yield ErrorFrame(error=f"{self} error: {e}")
 
 
 def audio_format_from_sample_rate(sample_rate: int) -> str:
@@ -414,12 +400,6 @@ class ElevenLabsRealtimeSTTService(WebsocketSTTService):
 
     By default, uses manual commit strategy where Pipecat's VAD controls when to
     commit transcript segments, providing consistency with other STT services.
-
-    Important:
-        When using manual commit strategy with Pipecat's VAD, it is recommended to set
-        the VAD `stop_secs` parameter to at least 0.5 seconds. Lower values may result
-        in incomplete transcriptions due to a known limitation in the ElevenLabs model
-        where audio sent near the commit boundary may not be fully processed.
     """
 
     class InputParams(BaseModel):
@@ -436,11 +416,6 @@ class ElevenLabsRealtimeSTTService(WebsocketSTTService):
                 Only used when commit_strategy is VAD. None uses ElevenLabs default.
             min_silence_duration_ms: Minimum silence duration for VAD (50-2000ms).
                 Only used when commit_strategy is VAD. None uses ElevenLabs default.
-
-        Note:
-            When using manual commit strategy, ensure Pipecat's VAD `stop_secs` is set to
-            at least 0.5 seconds to avoid incomplete transcriptions. This is a known
-            limitation of the ElevenLabs model.
         """
 
         language_code: Optional[str] = None
@@ -469,10 +444,6 @@ class ElevenLabsRealtimeSTTService(WebsocketSTTService):
             sample_rate: Audio sample rate in Hz. If not provided, uses the pipeline's rate.
             params: Configuration parameters for the STT service.
             **kwargs: Additional arguments passed to WebsocketSTTService.
-
-        Note:
-            When using manual commit strategy (default), configure Pipecat's VAD with
-            `stop_secs` of at least 0.5 seconds to ensure complete transcriptions.
         """
         super().__init__(
             sample_rate=sample_rate,
@@ -746,12 +717,7 @@ class ElevenLabsRealtimeSTTService(WebsocketSTTService):
             logger.error(f"ElevenLabs input error: {error_msg}")
             await self.push_error(ErrorFrame(f"Input error: {error_msg}"))
 
-        elif message_type in [
-            "auth_error",
-            "quota_exceeded",
-            "transcriber_error",
-            "error",
-        ]:
+        elif message_type in ["auth_error", "quota_exceeded", "transcriber_error", "error"]:
             error_msg = data.get("error", data.get("message", "Unknown error"))
             logger.error(f"ElevenLabs error ({message_type}): {error_msg}")
             await self.push_error(ErrorFrame(f"{message_type}: {error_msg}"))

pipecat/services/openai/base_llm.py

@@ -18,6 +18,7 @@ from openai import (
     APITimeoutError,
     AsyncOpenAI,
     AsyncStream,
+    BadRequestError,
     DefaultAsyncHttpxClient,
 )
 from openai.types.chat import ChatCompletionChunk, ChatCompletionMessageParam
@@ -100,6 +101,7 @@ class BaseOpenAILLMService(LLMService):
         params: Optional[InputParams] = None,
         retry_timeout_secs: Optional[float] = 5.0,
         retry_on_timeout: Optional[bool] = False,
+        enable_warmup: bool = False,
         **kwargs,
     ):
         """Initialize the BaseOpenAILLMService.
@@ -114,6 +116,7 @@ class BaseOpenAILLMService(LLMService):
             params: Input parameters for model configuration and behavior.
             retry_timeout_secs: Request timeout in seconds. Defaults to 5.0 seconds.
             retry_on_timeout: Whether to retry the request once if it times out.
+            enable_warmup: Whether to enable LLM cache warmup. Defaults to False.
             **kwargs: Additional arguments passed to the parent LLMService.
         """
         super().__init__(**kwargs)
@@ -133,6 +136,7 @@ class BaseOpenAILLMService(LLMService):
         }
         self._retry_timeout_secs = retry_timeout_secs
         self._retry_on_timeout = retry_on_timeout
+        self._enable_warmup = enable_warmup
         self.set_model_name(model)
         self._client = self.create_client(
             api_key=api_key,
@@ -477,6 +481,11 @@ class BaseOpenAILLMService(LLMService):
                 await self.stop_processing_metrics()
                 await self.push_frame(LLMFullResponseEndFrame())
 
+    def _is_gpt5_model(self) -> bool:
+        """Check if the current model is a GPT-5 series model that requires max_completion_tokens."""
+        model = (self.model_name or "").lower()
+        return model.startswith("gpt-5")
+
     async def _handle_warmup_frame(self, frame: WarmupLLMFrame):
         """Handle WarmupLLMFrame to prime the LLM cache without emitting responses.
 
@@ -486,18 +495,30 @@ class BaseOpenAILLMService(LLMService):
         Args:
             frame: WarmupLLMFrame containing the messages to cache.
         """
+        # Skip warmup if disabled
+        if not self._enable_warmup:
+            self.logger.debug("LLM warmup is disabled, skipping")
+            return
+
         try:
             # Use the provided messages for warmup
             messages: List[ChatCompletionMessageParam] = frame.messages  # type: ignore
 
             # Make a non-streaming call to warm the cache
-            # We use a minimal max_tokens to reduce latency and cost
-            await self._client.chat.completions.create(
-                model=self.model_name,  # Use the property, not self._model
-                messages=messages,
-                max_tokens=10,  # Minimal response
-                stream=False,
-            )
+            # We use a minimal token limit to reduce latency and cost
+            # GPT-5 series models require max_completion_tokens instead of max_tokens
+            warmup_params = {
+                "model": self.model_name,
+                "messages": messages,
+                "stream": False,
+            }
+
+            if self._is_gpt5_model():
+                warmup_params["max_completion_tokens"] = 10
+            else:
+                warmup_params["max_tokens"] = 10
+
+            await self._client.chat.completions.create(**warmup_params)
 
             self.logger.info("LLM cache warmed successfully")
             # Intentionally don't emit any frames - this is a silent warmup

pipecat/transcriptions/language.py

@@ -569,3 +569,53 @@ class Language(StrEnum):
     # Zulu
     ZU = "zu"
     ZU_ZA = "zu-ZA"
+
+
+def resolve_language(
+    language: Language, language_map: dict[Language, str], use_base_code: bool = True
+) -> str:
+    """Resolve a Language enum to a service-specific language code.
+
+    Checks the language map first, then falls back to extracting the appropriate
+    code format with a warning if not found in the verified list.
+
+    Args:
+        language: The Language enum value to convert.
+        language_map: Dictionary mapping Language enums to service language codes.
+        use_base_code: If True, extracts base code (e.g., 'en' from 'en-US').
+                      If False, uses full language code as-is.
+
+    Returns:
+        The resolved language code for the service.
+
+    Examples::
+
+        # Service expecting base codes (e.g., Cartesia)
+        >>> LANGUAGE_MAP = {Language.EN: "en", Language.ES: "es"}
+        >>> resolve_language(Language.EN_US, LANGUAGE_MAP, use_base_code=True)
+        # Logs: "Language en-US not verified. Using base code 'en'."
+        "en"
+
+        # Service expecting full codes (e.g., AWS)
+        >>> LANGUAGE_MAP = {Language.EN_US: "en-US", Language.ES_ES: "es-ES"}
+        >>> resolve_language(Language.EN_GB, LANGUAGE_MAP, use_base_code=False)
+        # Logs: "Language en-GB not verified. Using 'en-GB'."
+        "en-GB"
+    """
+    # Check if language is in the verified map
+    result = language_map.get(language)
+
+    if result is not None:
+        return result
+
+    # Not in map - fall back with warning
+    lang_str = str(language.value)
+
+    if use_base_code:
+        # Extract base code (e.g., "en" from "en-US")
+        base_code = lang_str.split("-")[0].lower()
+        # logger.warning(f"Language {language.value} not verified. Using base code '{base_code}'.")
+        return base_code
+    else:
+        # logger.warning(f"Language {language.value} not verified. Using '{lang_str}'.")
+        return lang_str