feat: support OTLP telemetry via DIAL SDK

README.md

@@ -80,6 +80,7 @@ Also, following environment valuables can be used to configure the service behav
 |MODEL_RATES| {} | Specifies per-token price rates for models in JSON format|
 |TOPIC_MODEL| ./topic_model | Specifies the name or path for the topic model. If the model is specified by name, it will be downloaded from, the [Huggingface]( https://huggingface.co/).|
 |TOPIC_EMBEDDINGS_MODEL| None | Specifies the name or path for the embeddings model used with the topic model. If the model is specified by name, it will be downloaded from, the [Huggingface]( https://huggingface.co/). If None, the name will be used from the topic model config.|
+|LOG_LEVEL|INFO|The server logging level. Use DEBUG for dev purposes and INFO in prod|
 
 Example of the MODEL_RATES configuration:
 

aidial_analytics_realtime/app.py

@@ -9,6 +9,7 @@
 import aiohttp
 import starlette.requests
 import uvicorn
+from aidial_sdk.telemetry.init import TelemetryConfig, init_telemetry
 from fastapi import Depends, FastAPI, Request
 from fastapi.responses import JSONResponse
 
@@ -54,6 +55,8 @@ async def lifespan(app: FastAPI):
 
 app = FastAPI(lifespan=lifespan)
 
+init_telemetry(app, TelemetryConfig())
+
 configure_loggers()