Files
Brancheneinstufung2/transcription-tool/backend/services/translation_service.py

65 lines
2.1 KiB
Python

from sqlalchemy.orm import Session
from ..database import Meeting, AnalysisResult
from .llm_service import call_gemini_api
from ..prompt_library import get_prompt
from typing import Dict, Any, List
def _format_transcript_for_translation(chunks: List[Any]) -> str:
"""Formats the transcript into a single string for the translation prompt."""
full_transcript = []
# Ensure chunks are treated correctly, whether they are dicts or objects
for chunk in chunks:
json_content = getattr(chunk, 'json_content', None)
if not json_content:
continue
for line in json_content:
speaker = line.get("speaker", "Unknown")
text = line.get("text", "")
full_transcript.append(f"{speaker}: {text}")
return "\n".join(full_transcript)
def translate_transcript(db: Session, meeting_id: int, target_language: str) -> AnalysisResult:
"""
Translates the transcript of a meeting and stores it.
"""
meeting = db.query(Meeting).filter(Meeting.id == meeting_id).first()
if not meeting:
raise ValueError("Meeting not found")
prompt_key = f"translation_{target_language.lower()}"
# Check if translation already exists
existing_translation = db.query(AnalysisResult).filter(
AnalysisResult.meeting_id == meeting_id,
AnalysisResult.prompt_key == prompt_key
).first()
if existing_translation:
return existing_translation
# Prepare transcript
transcript_text = _format_transcript_for_translation(meeting.chunks)
if not transcript_text:
raise ValueError("Transcript is empty, cannot translate.")
# Get prompt from library
prompt = get_prompt('translate_transcript', {
'transcript': transcript_text,
'target_language': target_language
})
# Call Gemini API using the new service function
translated_text = call_gemini_api(prompt)
# Store result
translation_result = AnalysisResult(
meeting_id=meeting_id,
prompt_key=prompt_key,
result_text=translated_text
)
db.add(translation_result)
db.commit()
db.refresh(translation_result)
return translation_result