apunkt/dograh
1
0
Fork 0
mirror of https://github.com/dograh-hq/dograh.git synced 2026-06-10 08:05:22 +02:00
Code Issues Projects Releases Packages Wiki Activity

feat: add Azure AI multi-provider support (TTS, STT, Embeddings, Realtime) (#381)

Browse source 
* feat: add Azure AI multi-provider support (TTS, STT, Embeddings, Realtime)

Enables Azure AI services across all model layers so users with Azure
credits can consolidate billing on a single provider.

- Voice (TTS): AzureSpeechTTSConfiguration via azure_speech provider
- Transcriber (STT): AzureSpeechSTTConfiguration via azure_speech provider
- Embedding: AzureOpenAIEmbeddingsConfiguration via azure provider
- Realtime: AzureRealtimeLLMConfiguration via azure_realtime provider

New files:
- api/services/pipecat/realtime/azure_realtime.py
- api/services/gen_ai/embedding/azure_openai_service.py
- api/tests/test_azure_speech_service_factory.py

The UI picks up all four providers automatically from the schema —
no frontend changes required.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: add validation for URL and params

---------

Co-authored-by: Vishal Dhateria <vishal@finela.ai>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Abhishek Kumar <abhishek@a6k.me>
This commit is contained in:
Vishal Dhateria 2026-06-02 12:50:00 +05:30 • committed by GitHub
parent 8a4a2e25db
commit 7ba95c0fbe
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 1082 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

41
api/tasks/knowledge_base_processing.py
View file

@ -12,7 +12,8 @@ from loguru import logger
from api.db import db_client
from api.db.models import KnowledgeBaseChunkModel
from api.services.gen_ai import OpenAIEmbeddingService
from api.services.configuration.registry import ServiceProviders
from api.services.gen_ai import AzureOpenAIEmbeddingService, OpenAIEmbeddingService
from api.services.mps_service_key_client import mps_service_key_client
from api.services.storage import storage_fs
@ -148,21 +149,32 @@ async def process_knowledge_base_document(
)
return
# Chunked mode: fetch user embedding config, embed via OpenAI, persist chunks.
# Chunked mode: fetch user embedding config, embed, and persist chunks.
embeddings_provider = None
embeddings_api_key = None
embeddings_model = None
embeddings_base_url = None
embeddings_endpoint = None
embeddings_api_version = None
if document.created_by:
user_config = await db_client.get_user_configurations(document.created_by)
if user_config.embeddings:
embeddings_provider = getattr(user_config.embeddings, "provider", None)
embeddings_api_key = user_config.embeddings.api_key
embeddings_model = user_config.embeddings.model
embeddings_base_url = getattr(user_config.embeddings, "base_url", None)
logger.info(f"Using user embeddings config: model={embeddings_model}")
embeddings_endpoint = getattr(user_config.embeddings, "endpoint", None)
embeddings_api_version = getattr(
user_config.embeddings, "api_version", None
)
logger.info(
f"Using user embeddings config: provider={embeddings_provider}, "
f"model={embeddings_model}"
)
if not embeddings_api_key:
error_message = (
"OpenAI API key not configured. Please set your API key in "
"API key not configured. Please set your API key in "
"Model Configurations > Embedding to process documents."
)
logger.warning(f"Document {document_id}: {error_message}")
@ -171,12 +183,21 @@ async def process_knowledge_base_document(
)
return
embedding_service = OpenAIEmbeddingService(
db_client=db_client,
api_key=embeddings_api_key,
model_id=embeddings_model or "text-embedding-3-small",
base_url=embeddings_base_url,
)
if embeddings_provider == ServiceProviders.AZURE.value and embeddings_endpoint:
embedding_service = AzureOpenAIEmbeddingService(
db_client=db_client,
api_key=embeddings_api_key,
endpoint=embeddings_endpoint,
model_id=embeddings_model or "text-embedding-3-small",
api_version=embeddings_api_version or "2024-02-15-preview",
)
else:
embedding_service = OpenAIEmbeddingService(
db_client=db_client,
api_key=embeddings_api_key,
model_id=embeddings_model or "text-embedding-3-small",
base_url=embeddings_base_url,
)
mps_chunks = mps_response.get("chunks", [])
if not mps_chunks: