apunkt/dograh
1
0
Fork 0
mirror of https://github.com/dograh-hq/dograh.git synced 2026-07-25 12:01:04 +02:00
Code Issues Projects Releases Packages Wiki Activity

Merge remote-tracking branch 'origin/main' into feat/inworld-tts

Browse source 
# Conflicts:
#	api/services/configuration/registry.py
This commit is contained in:
Abhishek Kumar 2026-06-19 11:39:46 +05:30
commit eedc69b3d9
241 changed files with 16973 additions and 3525 deletions
Download patch file Download diff file Expand all files Collapse all files

62
api/services/pipecat/event_handlers.py
View file

@ -9,8 +9,8 @@ from api.services.integrations import IntegrationRuntimeSession
from api.services.pipecat.audio_config import AudioConfig
from api.services.pipecat.audio_playback import play_audio_loop
from api.services.pipecat.in_memory_buffers import (
InMemoryAudioBuffer,
InMemoryLogsBuffer,
InMemoryRecordingBuffers,
)
from api.services.pipecat.pipeline_metrics_aggregator import PipelineMetricsAggregator
from api.services.pipecat.tracing_config import get_trace_url
@ -40,11 +40,11 @@ async def _capture_call_event(
"workflow_run_id": workflow_run_id,
"workflow_id": workflow_run.workflow_id if workflow_run else None,
"call_type": workflow_run.mode if workflow_run else None,
"call_direction": (workflow_run.initial_context or {}).get(
"direction", "outbound"
)
if workflow_run
else None,
"call_direction": (
(workflow_run.initial_context or {}).get("direction", "outbound")
if workflow_run
else None
),
}
if extra_properties:
properties.update(extra_properties)
@ -73,7 +73,7 @@ def register_event_handlers(
"""Register all event handlers for transport and task events.
Returns:
in_memory_audio_buffer for use by other handlers.
In-memory recording buffers for use by other handlers.
"""
# Initialize in-memory buffers with proper audio configuration
sample_rate = audio_config.pipeline_sample_rate if audio_config else 16000
@ -84,7 +84,7 @@ def register_event_handlers(
f"with sample_rate={sample_rate}Hz, channels={num_channels}"
)
in_memory_audio_buffer = InMemoryAudioBuffer(
in_memory_audio_buffers = InMemoryRecordingBuffers(
workflow_run_id=workflow_run_id,
sample_rate=sample_rate,
num_channels=num_channels,
@ -363,14 +363,32 @@ def register_event_handlers(
# Write buffers to temp files and enqueue combined processing task
audio_temp_path = None
user_audio_temp_path = None
bot_audio_temp_path = None
transcript_temp_path = None
try:
if not in_memory_audio_buffer.is_empty:
audio_temp_path = await in_memory_audio_buffer.write_to_temp_file()
if not in_memory_audio_buffers.mixed.is_empty:
audio_temp_path = (
await in_memory_audio_buffers.mixed.write_to_temp_file()
)
else:
logger.debug("Audio buffer is empty, skipping upload")
if not in_memory_audio_buffers.user.is_empty:
user_audio_temp_path = (
await in_memory_audio_buffers.user.write_to_temp_file()
)
else:
logger.debug("User audio buffer is empty, skipping upload")
if not in_memory_audio_buffers.bot.is_empty:
bot_audio_temp_path = (
await in_memory_audio_buffers.bot.write_to_temp_file()
)
else:
logger.debug("Bot audio buffer is empty, skipping upload")
transcript_temp_path = in_memory_logs_buffer.write_transcript_to_temp_file()
if not transcript_temp_path:
logger.debug("No transcript events in logs buffer, skipping upload")
@ -385,16 +403,18 @@ def register_event_handlers(
workflow_run_id,
audio_temp_path,
transcript_temp_path,
user_audio_temp_path,
bot_audio_temp_path,
)
# Return the buffer so it can be passed to other handlers
return in_memory_audio_buffer
return in_memory_audio_buffers
def register_audio_data_handler(
audio_buffer: AudioBufferProcessor,
workflow_run_id,
in_memory_buffer: InMemoryAudioBuffer,
in_memory_buffers: InMemoryRecordingBuffers,
):
"""Register event handler for audio data"""
logger.info(f"Registering audio data handler for workflow run {workflow_run_id}")
@ -404,9 +424,19 @@ def register_audio_data_handler(
if not audio:
return
# Use in-memory buffer
try:
await in_memory_buffer.append(audio)
await in_memory_buffers.mixed.append(audio)
except MemoryError as e:
logger.error(f"Memory buffer full: {e}")
# Could implement overflow to disk here if needed
logger.error(f"Mixed audio buffer full: {e}")
@audio_buffer.event_handler("on_track_audio_data")
async def on_track_audio_data(
buffer, user_audio, bot_audio, sample_rate, num_channels
):
try:
if user_audio:
await in_memory_buffers.user.append(user_audio)
if bot_audio:
await in_memory_buffers.bot.append(bot_audio)
except MemoryError as e:
logger.error(f"Track audio buffer full: {e}")

21
api/services/pipecat/in_memory_buffers.py
View file

@ -75,6 +75,27 @@ class InMemoryAudioBuffer:
return self._total_size
class InMemoryRecordingBuffers:
"""Holds the mixed recording plus aligned user and bot mono tracks."""
def __init__(self, workflow_run_id: int, sample_rate: int, num_channels: int = 1):
self.mixed = InMemoryAudioBuffer(
workflow_run_id=workflow_run_id,
sample_rate=sample_rate,
num_channels=num_channels,
)
self.user = InMemoryAudioBuffer(
workflow_run_id=workflow_run_id,
sample_rate=sample_rate,
num_channels=1,
)
self.bot = InMemoryAudioBuffer(
workflow_run_id=workflow_run_id,
sample_rate=sample_rate,
num_channels=1,
)
class InMemoryLogsBuffer:
"""Buffer real-time feedback events in memory during a call, then save to workflow run logs."""

89
api/services/pipecat/run_pipeline.py
View file

@ -6,6 +6,7 @@ from loguru import logger
from api.db import db_client
from api.enums import WorkflowRunMode
from api.services.configuration.options import DEEPGRAM_FLUX_MODELS
from api.services.configuration.registry import ServiceProviders
from api.services.integrations import (
IntegrationRuntimeContext,
@ -162,15 +163,13 @@ async def run_pipeline_telephony(
workflow_id: Workflow being executed.
workflow_run_id: Workflow run row.
user_id: Owner of the workflow.
call_id: Provider call identifier (stored in cost_info for billing).
call_id: Provider call identifier.
transport_kwargs: Provider-specific kwargs forwarded to the transport
factory (e.g. stream_sid + call_sid for Twilio).
"""
logger.debug(f"Running {provider_name} pipeline for workflow_run {workflow_run_id}")
set_current_run_id(workflow_run_id)
await db_client.update_workflow_run(workflow_run_id, cost_info={"call_id": call_id})
workflow = await db_client.get_workflow(workflow_id, user_id)
if workflow:
set_current_org_id(workflow.organization_id)
@ -195,14 +194,17 @@ async def run_pipeline_telephony(
# Resolve effective user config here so the transport can tune its
# bot-stopped-speaking fallback based on is_realtime; pass the resolved
# values into _run_pipeline so it doesn't fetch them again.
from api.services.configuration.resolve import resolve_effective_config
from api.services.configuration.ai_model_configuration import (
get_effective_ai_model_configuration_for_workflow,
)
user_config = await db_client.get_user_configurations(user_id)
run_configs = (
(workflow_run.definition.workflow_configurations or {}) if workflow_run else {}
)
user_config = resolve_effective_config(
user_config, run_configs.get("model_overrides")
user_config = await get_effective_ai_model_configuration_for_workflow(
user_id=user_id,
organization_id=workflow.organization_id if workflow else None,
workflow_configurations=run_configs,
)
is_realtime = bool(user_config.is_realtime and user_config.realtime is not None)
@ -272,15 +274,18 @@ async def run_pipeline_smallwebrtc(
# Resolve workflow_run + effective user_config here so the transport can
# tune its bot-stopped-speaking fallback based on is_realtime. _run_pipeline
# reuses these via kwargs so we don't fetch twice.
from api.services.configuration.resolve import resolve_effective_config
from api.services.configuration.ai_model_configuration import (
get_effective_ai_model_configuration_for_workflow,
)
workflow_run = await db_client.get_workflow_run(workflow_run_id, user_id)
user_config = await db_client.get_user_configurations(user_id)
run_configs = (
(workflow_run.definition.workflow_configurations or {}) if workflow_run else {}
)
user_config = resolve_effective_config(
user_config, run_configs.get("model_overrides")
user_config = await get_effective_ai_model_configuration_for_workflow(
user_id=user_id,
organization_id=workflow.organization_id if workflow else None,
workflow_configurations=run_configs,
)
is_realtime = bool(user_config.is_realtime and user_config.realtime is not None)
@ -334,7 +339,7 @@ async def _run_pipeline(
if workflow_run.is_completed:
raise HTTPException(status_code=400, detail="Workflow run already completed")
merged_call_context_vars = workflow_run.initial_context
merged_call_context_vars = dict(workflow_run.initial_context or {})
# If there is some extra call_context_vars, fold them in. Persistence
# happens once below, after runtime_configuration is also resolved.
if call_context_vars:
@ -380,15 +385,31 @@ async def _run_pipeline(
# Resolve model overrides from the version onto global user config (skip
# when the caller already resolved it).
if resolved_user_config is None:
from api.services.configuration.resolve import resolve_effective_config
from api.services.configuration.ai_model_configuration import (
get_effective_ai_model_configuration_for_workflow,
)
user_config = await db_client.get_user_configurations(user_id)
user_config = resolve_effective_config(
user_config, run_configs.get("model_overrides")
user_config = await get_effective_ai_model_configuration_for_workflow(
user_id=user_id,
organization_id=workflow.organization_id,
workflow_configurations=run_configs,
)
else:
user_config = resolved_user_config
from api.services.managed_model_services import (
MPS_CORRELATION_ID_CONTEXT_KEY,
ensure_mps_correlation_id,
)
mps_correlation_id = await ensure_mps_correlation_id(
ai_model_config=user_config,
workflow_run_id=workflow_run_id,
initial_context=merged_call_context_vars,
)
if mps_correlation_id:
merged_call_context_vars[MPS_CORRELATION_ID_CONTEXT_KEY] = mps_correlation_id
# Detect realtime mode (speech-to-speech services like OpenAI Realtime, Gemini Live)
is_realtime = user_config.is_realtime and user_config.realtime is not None
@ -400,11 +421,23 @@ async def _run_pipeline(
# Realtime services don't implement run_inference, so create a
# separate text LLM for variable extraction and other out-of-band
# inference calls.
inference_llm = create_llm_service(user_config)
inference_llm = create_llm_service(
user_config,
correlation_id=mps_correlation_id,
)
else:
stt = create_stt_service(user_config, audio_config, keyterms=keyterms)
tts = create_tts_service(user_config, audio_config)
llm = create_llm_service(user_config)
stt = create_stt_service(
user_config,
audio_config,
keyterms=keyterms,
correlation_id=mps_correlation_id,
)
tts = create_tts_service(
user_config,
audio_config,
correlation_id=mps_correlation_id,
)
llm = create_llm_service(user_config, correlation_id=mps_correlation_id)
inference_llm = None
# Stamp the providers/models actually resolved for this run onto
@ -508,10 +541,17 @@ async def _run_pipeline(
embeddings_endpoint = None
embeddings_api_version = None
if user_config and user_config.embeddings:
from api.services.configuration.ai_model_configuration import (
apply_managed_embeddings_base_url,
)
embeddings_api_key = user_config.embeddings.api_key
embeddings_model = user_config.embeddings.model
embeddings_provider = getattr(user_config.embeddings, "provider", None)
embeddings_base_url = getattr(user_config.embeddings, "base_url", None)
embeddings_base_url = apply_managed_embeddings_base_url(
provider=embeddings_provider,
base_url=getattr(user_config.embeddings, "base_url", None),
)
embeddings_endpoint = getattr(user_config.embeddings, "endpoint", None)
embeddings_api_version = getattr(user_config.embeddings, "api_version", None)
@ -587,7 +627,7 @@ async def _run_pipeline(
# Other models use configurable turn detection strategy
is_deepgram_flux = (
user_config.stt.provider == ServiceProviders.DEEPGRAM.value
and user_config.stt.model == "flux-general-en"
and user_config.stt.model in DEEPGRAM_FLUX_MODELS
)
if is_deepgram_flux:
@ -679,7 +719,10 @@ async def _run_pipeline(
# Create a separate LLM instance for the voicemail sub-pipeline
# (can't share with main pipeline as it would mess up frame linking)
if voicemail_config.get("use_workflow_llm", True):
voicemail_llm = create_llm_service(user_config)
voicemail_llm = create_llm_service(
user_config,
correlation_id=mps_correlation_id,
)
else:
voicemail_llm = create_llm_service_from_provider(
provider=voicemail_config.get("provider", "openai"),

159
api/services/pipecat/service_factory.py
View file

@ -6,6 +6,7 @@ from fastapi import HTTPException
from loguru import logger
from api.constants import MPS_API_URL
from api.services.configuration.options import DEEPGRAM_FLUX_MODELS
from api.services.configuration.registry import ServiceProviders
from api.services.pipecat.inworld_tts import InworldOwnedSessionTTSService
from api.services.pipecat.minimax_tts import MiniMaxOwnedSessionTTSService
@ -41,8 +42,17 @@ from pipecat.services.google.vertex.llm import (
)
from pipecat.services.inworld.tts import InworldTTSSettings
from pipecat.services.groq.llm import GroqLLMService, GroqLLMSettings
from pipecat.services.huggingface.llm import (
HuggingFaceLLMService,
HuggingFaceLLMSettings,
)
from pipecat.services.huggingface.stt import (
HuggingFaceSTTService,
HuggingFaceSTTSettings,
)
from pipecat.services.minimax.llm import MiniMaxLLMService
from pipecat.services.minimax.tts import MiniMaxTTSSettings
from pipecat.services.openai._constants import OPENAI_SAMPLE_RATE
from pipecat.services.openai.base_llm import OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.stt import (
@ -55,6 +65,8 @@ from pipecat.services.rime.tts import RimeTTSService, RimeTTSSettings
from pipecat.services.sarvam.llm import SarvamLLMService, SarvamLLMSettings
from pipecat.services.sarvam.stt import SarvamSTTService, SarvamSTTSettings
from pipecat.services.sarvam.tts import SarvamTTSService, SarvamTTSSettings
from pipecat.services.smallest.stt import SmallestSTTService, SmallestSTTSettings
from pipecat.services.smallest.tts import SmallestTTSService, SmallestTTSSettings
from pipecat.services.speaches.llm import SpeachesLLMService, SpeachesLLMSettings
from pipecat.services.speaches.stt import SpeachesSTTService, SpeachesSTTSettings
from pipecat.services.speaches.tts import SpeachesTTSService, SpeachesTTSSettings
@ -69,6 +81,20 @@ if TYPE_CHECKING:
from api.services.pipecat.audio_config import AudioConfig
DEEPGRAM_FLUX_LANGUAGE_HINTS = {
"de": Language.DE,
"en": Language.EN,
"es": Language.ES,
"fr": Language.FR,
"hi": Language.HI,
"it": Language.IT,
"ja": Language.JA,
"nl": Language.NL,
"pt": Language.PT,
"ru": Language.RU,
}
def _validate_runtime_service_url(url: str, field_name: str) -> None:
try:
validate_user_configured_service_url(
@ -80,7 +106,10 @@ def _validate_runtime_service_url(url: str, field_name: str) -> None:
def create_stt_service(
user_config, audio_config: "AudioConfig", keyterms: list[str] | None = None
user_config,
audio_config: "AudioConfig",
keyterms: list[str] | None = None,
correlation_id: str | None = None,
):
"""Create and return appropriate STT service based on user configuration
@ -92,17 +121,23 @@ def create_stt_service(
f"Creating STT service: provider={user_config.stt.provider}, model={user_config.stt.model}"
)
if user_config.stt.provider == ServiceProviders.DEEPGRAM.value:
# Check if using Flux model (English-only, no language selection)
if user_config.stt.model == "flux-general-en":
if user_config.stt.model in DEEPGRAM_FLUX_MODELS:
settings_kwargs = {
"model": user_config.stt.model,
"eot_timeout_ms": 3000,
"eot_threshold": 0.7,
"eager_eot_threshold": 0.5,
"keyterm": keyterms or [],
}
if user_config.stt.model == "flux-general-multi":
language = getattr(user_config.stt, "language", None)
language_hint = DEEPGRAM_FLUX_LANGUAGE_HINTS.get(language)
if language_hint:
settings_kwargs["language_hints"] = [language_hint]
return DeepgramFluxSTTService(
api_key=user_config.stt.api_key,
settings=DeepgramFluxSTTSettings(
model=user_config.stt.model,
eot_timeout_ms=3000,
eot_threshold=0.7,
eager_eot_threshold=0.5,
keyterm=keyterms or [],
),
settings=DeepgramFluxSTTSettings(**settings_kwargs),
should_interrupt=False, # Let UserAggregator take care of sending InterruptionFrame
sample_rate=audio_config.transport_in_sample_rate,
)
@ -162,6 +197,7 @@ def create_stt_service(
return DograhSTTService(
base_url=base_url,
api_key=user_config.stt.api_key,
correlation_id=correlation_id,
settings=DograhSTTSettings(
model=user_config.stt.model,
language=language,
@ -216,6 +252,22 @@ def create_stt_service(
),
sample_rate=audio_config.transport_in_sample_rate,
)
elif user_config.stt.provider == ServiceProviders.HUGGINGFACE.value:
base_url = (
getattr(user_config.stt, "base_url", None)
or "https://router.huggingface.co/hf-inference"
)
_validate_runtime_service_url(base_url, "base_url")
return HuggingFaceSTTService(
api_key=user_config.stt.api_key,
base_url=base_url,
bill_to=getattr(user_config.stt, "bill_to", None),
settings=HuggingFaceSTTSettings(
model=user_config.stt.model,
return_timestamps=getattr(user_config.stt, "return_timestamps", False),
),
sample_rate=audio_config.transport_in_sample_rate,
)
elif user_config.stt.provider == ServiceProviders.ASSEMBLYAI.value:
language = getattr(user_config.stt, "language", None)
settings_kwargs = {"model": user_config.stt.model, "language": language}
@ -282,13 +334,29 @@ def create_stt_service(
settings=AzureSTTSettings(language=pipecat_language),
sample_rate=audio_config.transport_in_sample_rate,
)
elif user_config.stt.provider == ServiceProviders.SMALLEST.value:
language_code = getattr(user_config.stt, "language", None) or "en"
try:
pipecat_language = Language(language_code)
except ValueError:
pipecat_language = Language.EN
return SmallestSTTService(
api_key=user_config.stt.api_key,
settings=SmallestSTTSettings(
model=user_config.stt.model,
language=pipecat_language,
),
sample_rate=audio_config.transport_in_sample_rate,
)
else:
raise HTTPException(
status_code=400, detail=f"Invalid STT provider {user_config.stt.provider}"
)
def create_tts_service(user_config, audio_config: "AudioConfig"):
def create_tts_service(
user_config, audio_config: "AudioConfig", correlation_id: str | None = None
):
"""Create and return appropriate TTS service based on user configuration
Args:
@ -316,6 +384,7 @@ def create_tts_service(user_config, audio_config: "AudioConfig"):
kwargs["base_url"] = base_url
return OpenAITTSService(
api_key=user_config.tts.api_key,
sample_rate=OPENAI_SAMPLE_RATE,
settings=OpenAITTSSettings(model=user_config.tts.model),
text_filters=[xml_function_tag_filter],
skip_aggregator_types=["recording_router", "recording"],
@ -385,11 +454,13 @@ def create_tts_service(user_config, audio_config: "AudioConfig"):
generation_config = (
GenerationConfig(**gen_config_kwargs) if gen_config_kwargs else None
)
language = getattr(user_config.tts, "language", None) or "en"
return CartesiaTTSService(
api_key=user_config.tts.api_key,
settings=CartesiaTTSSettings(
voice=user_config.tts.voice,
model=user_config.tts.model,
language=language,
**(
{"generation_config": generation_config}
if generation_config
@ -428,6 +499,7 @@ def create_tts_service(user_config, audio_config: "AudioConfig"):
return DograhTTSService(
base_url=base_url,
api_key=user_config.tts.api_key,
correlation_id=correlation_id,
settings=DograhTTSSettings(
model=user_config.tts.model,
voice=user_config.tts.voice,
@ -509,14 +581,20 @@ def create_tts_service(user_config, audio_config: "AudioConfig"):
language = getattr(user_config.tts, "language", None)
pipecat_language = language_mapping.get(language, Language.HI)
voice = getattr(user_config.tts, "voice", None) or "anushka"
voice = (
getattr(user_config.tts, "voice", None) or ""
).strip().lower() or "anushka"
speed = getattr(user_config.tts, "speed", None)
settings_kwargs = {
"model": user_config.tts.model,
"voice": voice,
"language": pipecat_language,
}
if speed and speed != 1.0:
settings_kwargs["pace"] = speed
return SarvamTTSService(
api_key=user_config.tts.api_key,
settings=SarvamTTSSettings(
model=user_config.tts.model,
voice=voice,
language=pipecat_language,
),
settings=SarvamTTSSettings(**settings_kwargs),
text_filters=[xml_function_tag_filter],
skip_aggregator_types=["recording_router", "recording"],
silence_time_s=1.0,
@ -577,6 +655,28 @@ def create_tts_service(user_config, audio_config: "AudioConfig"):
skip_aggregator_types=["recording_router", "recording"],
silence_time_s=1.0,
)
elif user_config.tts.provider == ServiceProviders.SMALLEST.value:
language_code = getattr(user_config.tts, "language", None) or "en"
try:
pipecat_language = Language(language_code)
except ValueError:
pipecat_language = Language.EN
speed = getattr(user_config.tts, "speed", None)
model = user_config.tts.model.replace("lightning-v", "lightning_v")
settings_kwargs = SmallestTTSSettings(
model=model,
voice=user_config.tts.voice,
language=pipecat_language,
)
if speed and speed != 1.0:
settings_kwargs.speed = speed
return SmallestTTSService(
api_key=user_config.tts.api_key,
settings=settings_kwargs,
text_filters=[xml_function_tag_filter],
skip_aggregator_types=["recording_router", "recording"],
silence_time_s=1.0,
)
else:
raise HTTPException(
status_code=400, detail=f"Invalid TTS provider {user_config.tts.provider}"
@ -588,6 +688,7 @@ def create_llm_service_from_provider(
model: str,
api_key: str | None,
*,
correlation_id: str | None = None,
base_url: str | None = None,
endpoint: str | None = None,
aws_access_key: str | None = None,
@ -597,6 +698,7 @@ def create_llm_service_from_provider(
location: str | None = None,
credentials: str | None = None,
temperature: float | None = None,
bill_to: str | None = None,
):
"""Create an LLM service from explicit provider/model/api_key.
@ -661,6 +763,7 @@ def create_llm_service_from_provider(
return DograhLLMService(
base_url=f"{MPS_API_URL}/api/v1/llm",
api_key=api_key,
correlation_id=correlation_id,
settings=OpenAILLMSettings(model=model),
)
elif provider == ServiceProviders.AWS_BEDROCK.value:
@ -678,6 +781,15 @@ def create_llm_service_from_provider(
api_key=api_key or "none",
settings=SpeachesLLMSettings(model=model),
)
elif provider == ServiceProviders.HUGGINGFACE.value:
base_url = base_url or "https://router.huggingface.co/v1"
_validate_runtime_service_url(base_url, "base_url")
return HuggingFaceLLMService(
api_key=api_key,
base_url=base_url,
bill_to=bill_to,
settings=HuggingFaceLLMSettings(model=model, temperature=0.1),
)
elif provider == ServiceProviders.MINIMAX.value:
base_url = base_url or "https://api.minimax.io/v1"
_validate_runtime_service_url(base_url, "base_url")
@ -875,7 +987,7 @@ def create_realtime_llm_service(user_config, audio_config: "AudioConfig"):
)
def create_llm_service(user_config):
def create_llm_service(user_config, correlation_id: str | None = None):
"""Create and return appropriate LLM service based on user configuration."""
provider = user_config.llm.provider
model = user_config.llm.model
@ -890,6 +1002,9 @@ def create_llm_service(user_config):
kwargs["endpoint"] = user_config.llm.endpoint
elif provider == ServiceProviders.SPEACHES.value:
kwargs["base_url"] = user_config.llm.base_url
elif provider == ServiceProviders.HUGGINGFACE.value:
kwargs["base_url"] = user_config.llm.base_url
kwargs["bill_to"] = user_config.llm.bill_to
elif provider == ServiceProviders.AWS_BEDROCK.value:
kwargs["aws_access_key"] = user_config.llm.aws_access_key
kwargs["aws_secret_key"] = user_config.llm.aws_secret_key
@ -904,4 +1019,10 @@ def create_llm_service(user_config):
elif provider == ServiceProviders.SARVAM.value:
kwargs["temperature"] = user_config.llm.temperature
return create_llm_service_from_provider(provider, model, api_key, **kwargs)
return create_llm_service_from_provider(
provider,
model,
api_key,
correlation_id=correlation_id,
**kwargs,
)