Fix dependency issues and update OpenAI API usage

- Updated OpenAI package from 1.3.7 to 1.51.0 for latest API compatibility
- Added PyTorch and torchaudio dependencies for Whisper model support
- Fixed OpenAI API calls to use new AsyncOpenAI client format
- Updated transcription service to use client.audio.transcriptions.create()
- Updated translation service to use client.chat.completions.create()
- Added proper logging to language detection service
- Added environment variable loading with python-dotenv in main.py
- Fixed import order to comply with linting standards

🤖 Generated with BackendIM

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

app/services/language_detection_service.py

@@ -3,6 +3,9 @@ import tempfile
 import whisper
 import ffmpeg
 from typing import Optional
+import logging
+
+logger = logging.getLogger(__name__)
 
 
 async def detect_language_from_video(video_content: bytes) -> Optional[str]:
@@ -51,5 +54,5 @@ async def detect_language_from_video(video_content: bytes) -> Optional[str]:
                 
     except Exception as e:
         # Log error but don't fail the upload
-        print(f"Language detection failed: {e}")
+        logger.error(f"Language detection failed: {e}")
         return None

app/services/transcription_service.py

@@ -1,5 +1,5 @@
 import os
-import openai
+from openai import AsyncOpenAI
 from typing import Optional
 import logging
 import tempfile
@@ -12,11 +12,11 @@ OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
 if not OPENAI_API_KEY:
     logger.warning("OpenAI API key not configured")
 
-openai.api_key = OPENAI_API_KEY
+client = AsyncOpenAI(api_key=OPENAI_API_KEY) if OPENAI_API_KEY else None
 
 
 async def transcribe_video_audio(video_s3_url: str) -> Optional[str]:
-    if not OPENAI_API_KEY:
+    if not client:
         logger.error("OpenAI API key not configured")
         return None
     
@@ -38,7 +38,7 @@ async def transcribe_video_audio(video_s3_url: str) -> Optional[str]:
         try:
             # Transcribe using OpenAI Whisper
             with open(temp_file_path, 'rb') as audio_file:
-                transcript = openai.Audio.transcribe(
+                transcript = await client.audio.transcriptions.create(
                     model="whisper-1",
                     file=audio_file,
                     response_format="text"

app/services/translation_service.py

@@ -1,5 +1,5 @@
 import os
-import openai
+from openai import AsyncOpenAI
 from typing import Optional
 import logging
 
@@ -10,11 +10,11 @@ OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
 if not OPENAI_API_KEY:
     logger.warning("OpenAI API key not configured")
 
-openai.api_key = OPENAI_API_KEY
+client = AsyncOpenAI(api_key=OPENAI_API_KEY) if OPENAI_API_KEY else None
 
 
 async def translate_text(text: str, target_language: str, source_language: str = "auto") -> Optional[str]:
-    if not OPENAI_API_KEY:
+    if not client:
         logger.error("OpenAI API key not configured")
         return None
     
@@ -45,7 +45,7 @@ async def translate_text(text: str, target_language: str, source_language: str =
             prompt = f"Translate the following text from {source_lang_name} to {target_lang_name}. Maintain the original tone and meaning:\n\n{text}"
         
         # Use GPT-4 for translation
-        response = openai.ChatCompletion.create(
+        response = await client.chat.completions.create(
             model="gpt-4",
             messages=[
                 {

main.py

@@ -3,11 +3,15 @@ from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
 from contextlib import asynccontextmanager
 import logging
+from dotenv import load_dotenv
 
 from app.db.session import engine
 from app.db.base import Base
 from app.routes import auth, videos, transcription, translation, voice_cloning, video_processing, profile
 
+# Load environment variables from .env file
+load_dotenv()
+
 # Configure logging
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)

requirements.txt

@@ -4,8 +4,10 @@ python-multipart==0.0.6
 sqlalchemy==2.0.23
 alembic==1.12.1
 boto3==1.34.0
-openai==1.3.7
+openai==1.51.0
 openai-whisper==20231117
+torch==2.1.2
+torchaudio==2.1.2
 python-decouple==3.8
 ruff==0.1.6
 requests==2.31.0