Refactor configuration management; update S3 integration, add new migration scripts, and implement pre-flight checks

This commit is contained in:
Santiago Martinez-Avial
2025-12-22 17:46:36 +01:00
parent f860d17206
commit 5c6d87dab7
17 changed files with 598 additions and 450 deletions

39
scripts/verify_turns.py Normal file
View File

@@ -0,0 +1,39 @@
import asyncio
import logging
from helia.configuration import HeliaConfig
from helia.db import init_db
from helia.models.transcript import Transcript
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
async def verify() -> None:
config = HeliaConfig() # type: ignore[call-arg]
await init_db(config)
transcript = await Transcript.find_one(Transcript.transcript_id == "300")
if not transcript:
logger.error("Transcript 300 not found.")
return
logger.info("Transcript 300 found with %d utterances.", len(transcript.utterances))
turns = transcript.turns
logger.info("Aggregated into %d turns.", len(turns))
for i, turn in enumerate(turns[:5]):
logger.info(
"Turn %d [%s] (%s - %s): %s... (Merged %d utterances)",
i + 1,
turn.speaker,
turn.start_time,
turn.end_time,
turn.value[:50],
turn.utterance_count,
)
if __name__ == "__main__":
asyncio.run(verify())