selfhostyourtech/reflector
2
0
Fork 0
mirror of https://github.com/Monadical-SAS/reflector.git synced 2025-12-21 20:59:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: implement service-specific Modal API keys with auto processor pattern (#528)

Browse Source 
* fix: refactor modal API key configuration for better separation of concerns

- Split generic MODAL_API_KEY into service-specific keys:
  - TRANSCRIPT_API_KEY for transcription service
  - DIARIZATION_API_KEY for diarization service
  - TRANSLATE_API_KEY for translation service
- Remove deprecated *_MODAL_API_KEY settings
- Add proper validation to ensure URLs are set when using modal processors
- Update README with new configuration format

BREAKING CHANGE: Configuration keys have changed. Update your .env file:
- TRANSCRIPT_MODAL_API_KEY → TRANSCRIPT_API_KEY
- LLM_MODAL_API_KEY → (removed, use TRANSCRIPT_API_KEY)
- Add DIARIZATION_API_KEY and TRANSLATE_API_KEY if using those services

* fix: update Modal backend configuration to use service-specific API keys

- Changed from generic MODAL_API_KEY to service-specific keys:
  - TRANSCRIPT_MODAL_API_KEY for transcription
  - DIARIZATION_MODAL_API_KEY for diarization
  - TRANSLATION_MODAL_API_KEY for translation
- Updated audio_transcript_modal.py and audio_diarization_modal.py to use modal_api_key parameter
- Updated documentation in README.md, CLAUDE.md, and env.example

* feat: implement auto/modal pattern for translation processor

- Created TranscriptTranslatorAutoProcessor following the same pattern as transcript/diarization
- Created TranscriptTranslatorModalProcessor with TRANSLATION_MODAL_API_KEY support
- Added TRANSLATION_BACKEND setting (defaults to "modal")
- Updated all imports to use TranscriptTranslatorAutoProcessor instead of TranscriptTranslatorProcessor
- Updated env.example with TRANSLATION_BACKEND and TRANSLATION_MODAL_API_KEY
- Updated test to expect TranscriptTranslatorModalProcessor name
- All tests passing

* refactor: simplify transcript_translator base class to match other processors

- Moved all implementation from base class to modal processor
- Base class now only defines abstract _translate method
- Follows the same minimal pattern as audio_diarization and audio_transcript base classes
- Updated test mock to use _translate instead of get_translation
- All tests passing

* chore: clean up settings and improve type annotations

- Remove deprecated generic API key variables from settings
- Add comments to group Modal-specific settings
- Improve type annotations for modal_api_key parameters

* fix: typing

* fix: passing key to openai

* test: fix rtc test failing due to change on transcript

It also correctly setup database from sqlite, in case our configuration
is setup to postgres.

* ci: deactivate translation backend by default

* test: fix modal->mock

* refactor: implementing igor review, mock to passthrough
This commit is contained in:
Mathieu Virbel
2025-08-04 12:07:30 -06:00
committed by GitHub
parent 5bd8233657
commit dc177af3ff
20 changed files with 220 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
server/reflector/pipelines/main_live_pipeline.py
View File

@@ -47,7 +47,7 @@ from reflector.processors import (
TranscriptFinalTitleProcessor,
TranscriptLinerProcessor,
TranscriptTopicDetectorProcessor,
TranscriptTranslatorProcessor,
TranscriptTranslatorAutoProcessor,
)
from reflector.processors.audio_waveform_processor import AudioWaveformProcessor
from reflector.processors.types import AudioDiarizationInput
@@ -361,7 +361,7 @@ class PipelineMainLive(PipelineMainBase):
AudioMergeProcessor(),
AudioTranscriptAutoProcessor.as_threaded(),
TranscriptLinerProcessor(),
TranscriptTranslatorProcessor.as_threaded(callback=self.on_transcript),
TranscriptTranslatorAutoProcessor.as_threaded(callback=self.on_transcript),
TranscriptTopicDetectorProcessor.as_threaded(callback=self.on_topic),
]
pipeline = Pipeline(*processors)

1
server/reflector/processors/__init__.py
View File

@@ -16,6 +16,7 @@ from .transcript_final_title import TranscriptFinalTitleProcessor # noqa: F401
from .transcript_liner import TranscriptLinerProcessor # noqa: F401
from .transcript_topic_detector import TranscriptTopicDetectorProcessor # noqa: F401
from .transcript_translator import TranscriptTranslatorProcessor # noqa: F401
from .transcript_translator_auto import TranscriptTranslatorAutoProcessor # noqa: F401
from .types import ( # noqa: F401
AudioFile,
FinalLongSummary,

13
server/reflector/processors/audio_diarization_modal.py
View File

@@ -10,12 +10,17 @@ class AudioDiarizationModalProcessor(AudioDiarizationProcessor):
INPUT_TYPE = AudioDiarizationInput
OUTPUT_TYPE = TitleSummary
def __init__(self, **kwargs):
def __init__(self, modal_api_key: str | None = None, **kwargs):
super().__init__(**kwargs)
if not settings.DIARIZATION_URL:
raise Exception(
"DIARIZATION_URL required to use AudioDiarizationModalProcessor"
)
self.diarization_url = settings.DIARIZATION_URL + "/diarize"
self.headers = {
"Authorization": f"Bearer {settings.LLM_MODAL_API_KEY}",
}
self.modal_api_key = modal_api_key
self.headers = {}
if self.modal_api_key:
self.headers["Authorization"] = f"Bearer {self.modal_api_key}"
async def _diarize(self, data: AudioDiarizationInput):
# Gather diarization data

10
server/reflector/processors/audio_transcript_modal.py
View File

@@ -21,16 +21,20 @@ from reflector.settings import settings
class AudioTranscriptModalProcessor(AudioTranscriptProcessor):
def __init__(self, modal_api_key: str):
def __init__(self, modal_api_key: str | None = None, **kwargs):
super().__init__()
if not settings.TRANSCRIPT_URL:
raise Exception(
"TRANSCRIPT_URL required to use AudioTranscriptModalProcessor"
)
self.transcript_url = settings.TRANSCRIPT_URL + "/v1"
self.timeout = settings.TRANSCRIPT_TIMEOUT
self.api_key = settings.TRANSCRIPT_MODAL_API_KEY
self.modal_api_key = modal_api_key
async def _transcript(self, data: AudioFile):
async with AsyncOpenAI(
base_url=self.transcript_url,
api_key=self.api_key,
api_key=self.modal_api_key,
timeout=self.timeout,
) as client:
self.logger.debug(f"Try to transcribe audio {data.name}")

59
server/reflector/processors/transcript_translator.py
View File

@@ -1,9 +1,5 @@
import httpx
from reflector.processors.base import Processor
from reflector.processors.types import Transcript, TranslationLanguages
from reflector.settings import settings
from reflector.utils.retry import retry
from reflector.processors.types import Transcript
class TranscriptTranslatorProcessor(Processor):
@@ -17,56 +13,23 @@ class TranscriptTranslatorProcessor(Processor):
def __init__(self, **kwargs):
super().__init__(**kwargs)
self.transcript = None
self.translate_url = settings.TRANSLATE_URL
self.timeout = settings.TRANSLATE_TIMEOUT
self.headers = {"Authorization": f"Bearer {settings.TRANSCRIPT_MODAL_API_KEY}"}
async def _push(self, data: Transcript):
self.transcript = data
await self.flush()
async def get_translation(self, text: str) -> str | None:
# FIXME this should be a processor after, as each user may want
# different languages
source_language = self.get_pref("audio:source_language", "en")
target_language = self.get_pref("audio:target_language", "en")
if source_language == target_language:
return
languages = TranslationLanguages()
# Only way to set the target should be the UI element like dropdown.
# Hence, this assert should never fail.
assert languages.is_supported(target_language)
self.logger.debug(f"Try to translate {text=}")
json_payload = {
"text": text,
"source_language": source_language,
"target_language": target_language,
}
async with httpx.AsyncClient() as client:
response = await retry(client.post)(
self.translate_url + "/translate",
headers=self.headers,
params=json_payload,
timeout=self.timeout,
follow_redirects=True,
logger=self.logger,
)
response.raise_for_status()
result = response.json()["text"]
# Sanity check for translation status in the result
if target_language in result:
translation = result[target_language]
self.logger.debug(f"Translation response: {text=}, {translation=}")
return translation
async def _translate(self, text: str) -> str | None:
raise NotImplementedError
async def _flush(self):
if not self.transcript:
return
self.transcript.translation = await self.get_translation(
text=self.transcript.text
)
source_language = self.get_pref("audio:source_language", "en")
target_language = self.get_pref("audio:target_language", "en")
if source_language == target_language:
self.transcript.translation = None
else:
self.transcript.translation = await self._translate(self.transcript.text)
await self.emit(self.transcript)

32
server/reflector/processors/transcript_translator_auto.py Normal file
View File

@@ -0,0 +1,32 @@
import importlib
from reflector.processors.transcript_translator import TranscriptTranslatorProcessor
from reflector.settings import settings
class TranscriptTranslatorAutoProcessor(TranscriptTranslatorProcessor):
_registry = {}
@classmethod
def register(cls, name, kclass):
cls._registry[name] = kclass
def __new__(cls, name: str | None = None, **kwargs):
if name is None:
name = settings.TRANSLATION_BACKEND
if name not in cls._registry:
module_name = f"reflector.processors.transcript_translator_{name}"
importlib.import_module(module_name)
# gather specific configuration for the processor
# search `TRANSLATION_BACKEND_XXX_YYY`, push to constructor as `backend_xxx_yyy`
config = {}
name_upper = name.upper()
settings_prefix = "TRANSLATION_"
config_prefix = f"{settings_prefix}{name_upper}_"
for key, value in settings:
if key.startswith(config_prefix):
config_name = key[len(settings_prefix) :].lower()
config[config_name] = value
return cls._registry[name](**config | kwargs)

66
server/reflector/processors/transcript_translator_modal.py Normal file
View File

@@ -0,0 +1,66 @@
import httpx
from reflector.processors.transcript_translator import TranscriptTranslatorProcessor
from reflector.processors.transcript_translator_auto import (
TranscriptTranslatorAutoProcessor,
)
from reflector.processors.types import TranslationLanguages
from reflector.settings import settings
from reflector.utils.retry import retry
class TranscriptTranslatorModalProcessor(TranscriptTranslatorProcessor):
"""
Translate the transcript into the target language using Modal.com
"""
def __init__(self, modal_api_key: str | None = None, **kwargs):
super().__init__(**kwargs)
if not settings.TRANSLATE_URL:
raise Exception(
"TRANSLATE_URL is required for TranscriptTranslatorModalProcessor"
)
self.translate_url = settings.TRANSLATE_URL
self.timeout = settings.TRANSLATE_TIMEOUT
self.modal_api_key = modal_api_key
self.headers = {}
if self.modal_api_key:
self.headers["Authorization"] = f"Bearer {self.modal_api_key}"
async def _translate(self, text: str) -> str | None:
source_language = self.get_pref("audio:source_language", "en")
target_language = self.get_pref("audio:target_language", "en")
languages = TranslationLanguages()
# Only way to set the target should be the UI element like dropdown.
# Hence, this assert should never fail.
assert languages.is_supported(target_language)
self.logger.debug(f"Try to translate {text=}")
json_payload = {
"text": text,
"source_language": source_language,
"target_language": target_language,
}
async with httpx.AsyncClient() as client:
response = await retry(client.post)(
self.translate_url + "/translate",
headers=self.headers,
params=json_payload,
timeout=self.timeout,
follow_redirects=True,
logger=self.logger,
)
response.raise_for_status()
result = response.json()["text"]
# Sanity check for translation status in the result
if target_language in result:
translation = result[target_language]
else:
translation = None
self.logger.debug(f"Translation response: {text=}, {translation=}")
return translation
TranscriptTranslatorAutoProcessor.register("modal", TranscriptTranslatorModalProcessor)

14
server/reflector/processors/transcript_translator_passthrough.py Normal file
View File

@@ -0,0 +1,14 @@
from reflector.processors.transcript_translator import TranscriptTranslatorProcessor
from reflector.processors.transcript_translator_auto import (
TranscriptTranslatorAutoProcessor,
)
class TranscriptTranslatorPassthroughProcessor(TranscriptTranslatorProcessor):
async def _translate(self, text: str) -> None:
return None
TranscriptTranslatorAutoProcessor.register(
"passthrough", TranscriptTranslatorPassthroughProcessor
)

9
server/reflector/settings.py
View File

@@ -25,7 +25,7 @@ class Settings(BaseSettings):
TRANSCRIPT_URL: str | None = None
TRANSCRIPT_TIMEOUT: int = 90
# Audio transcription modal.com configuration
# Audio Transcription: modal backend
TRANSCRIPT_MODAL_API_KEY: str | None = None
# Audio transcription storage
@@ -38,9 +38,13 @@ class Settings(BaseSettings):
TRANSCRIPT_STORAGE_AWS_SECRET_ACCESS_KEY: str | None = None
# Translate into the target language
TRANSLATION_BACKEND: str = "passthrough"
TRANSLATE_URL: str | None = None
TRANSLATE_TIMEOUT: int = 90
# Translation: modal backend
TRANSLATE_MODAL_API_KEY: str | None = None
# LLM
LLM_MODEL: str = "microsoft/phi-4"
LLM_URL: str | None = None
@@ -52,6 +56,9 @@ class Settings(BaseSettings):
DIARIZATION_BACKEND: str = "modal"
DIARIZATION_URL: str | None = None
# Diarization: modal backend
DIARIZATION_MODAL_API_KEY: str | None = None
# Sentry
SENTRY_DSN: str | None = None

4
server/reflector/tools/process.py
View File

@@ -13,7 +13,7 @@ from reflector.processors import (
TranscriptFinalTitleProcessor,
TranscriptLinerProcessor,
TranscriptTopicDetectorProcessor,
TranscriptTranslatorProcessor,
TranscriptTranslatorAutoProcessor,
)
from reflector.processors.base import BroadcastProcessor
@@ -31,7 +31,7 @@ async def process_audio_file(
AudioMergeProcessor(),
AudioTranscriptAutoProcessor.as_threaded(),
TranscriptLinerProcessor(),
TranscriptTranslatorProcessor.as_threaded(),
TranscriptTranslatorAutoProcessor.as_threaded(),
]
if not only_transcript:
processors += [

4
server/reflector/tools/process_with_diarization.py
View File

@@ -27,7 +27,7 @@ from reflector.processors import (
TranscriptFinalTitleProcessor,
TranscriptLinerProcessor,
TranscriptTopicDetectorProcessor,
TranscriptTranslatorProcessor,
TranscriptTranslatorAutoProcessor,
)
from reflector.processors.base import BroadcastProcessor, Processor
from reflector.processors.types import (
@@ -103,7 +103,7 @@ async def process_audio_file_with_diarization(
processors += [
TranscriptLinerProcessor(),
TranscriptTranslatorProcessor.as_threaded(),
TranscriptTranslatorAutoProcessor.as_threaded(),
]
if not only_transcript: