Spaces:
Sleeping
Sleeping
File size: 9,342 Bytes
67f25fb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 |
"""
FastAPI backend for Multi-Lingual Product Catalog Translator
Uses IndicTrans2 by AI4Bharat for translation between Indian languages
"""
from fastapi import FastAPI, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel
from typing import Optional, List, Dict
import uvicorn
import logging
from datetime import datetime
from translation_service import TranslationService
from database import DatabaseManager
from models import (
LanguageDetectionRequest,
LanguageDetectionResponse,
TranslationRequest,
TranslationResponse,
CorrectionRequest,
CorrectionResponse,
TranslationHistory
)
# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
# Initialize FastAPI app
app = FastAPI(
title="Multi-Lingual Catalog Translator",
description="AI-powered translation service for e-commerce product catalogs using IndicTrans2",
version="1.0.0"
)
# Add CORS middleware
app.add_middleware(
CORSMiddleware,
allow_origins=["*"], # Configure appropriately for production
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
# Initialize services
translation_service = TranslationService()
db_manager = DatabaseManager()
@app.on_event("startup")
async def startup_event():
"""Initialize services on startup"""
logger.info("Starting Multi-Lingual Catalog Translator API...")
db_manager.initialize_database()
await translation_service.load_models()
logger.info("API startup complete!")
@app.get("/")
async def root():
"""Health check endpoint"""
return {
"message": "Multi-Lingual Product Catalog Translator API",
"status": "healthy",
"version": "1.0.0",
"supported_languages": translation_service.get_supported_languages()
}
@app.post("/detect-language", response_model=LanguageDetectionResponse)
async def detect_language(request: LanguageDetectionRequest):
"""
Detect the language of input text
Args:
request: Contains text to analyze
Returns:
Detected language code and confidence score
"""
try:
logger.info(f"Language detection request for text: {request.text[:50]}...")
result = await translation_service.detect_language(request.text)
logger.info(f"Language detected: {result['language']} (confidence: {result['confidence']})")
return LanguageDetectionResponse(
language=result['language'],
confidence=result['confidence'],
language_name=result.get('language_name', result['language'])
)
except Exception as e:
logger.error(f"Language detection error: {str(e)}")
raise HTTPException(status_code=500, detail=f"Language detection failed: {str(e)}")
@app.post("/translate", response_model=TranslationResponse)
async def translate_text(request: TranslationRequest):
"""
Translate text using IndicTrans2
Args:
request: Contains text, source and target language codes
Returns:
Translated text and metadata
"""
try:
logger.info(f"Translation request: {request.source_language} -> {request.target_language}")
# Auto-detect source language if not provided
if not request.source_language:
detection_result = await translation_service.detect_language(request.text)
request.source_language = detection_result['language']
logger.info(f"Auto-detected source language: {request.source_language}")
# Perform translation
translation_result = await translation_service.translate(
text=request.text,
source_lang=request.source_language,
target_lang=request.target_language
)
# Store translation in database
translation_id = db_manager.store_translation(
original_text=request.text,
translated_text=translation_result['translated_text'],
source_language=request.source_language,
target_language=request.target_language,
model_confidence=translation_result.get('confidence', 0.0)
)
logger.info(f"Translation completed. ID: {translation_id}")
return TranslationResponse(
translated_text=translation_result['translated_text'],
source_language=request.source_language,
target_language=request.target_language,
confidence=translation_result.get('confidence', 0.0),
translation_id=translation_id
)
except Exception as e:
logger.error(f"Translation error: {str(e)}")
raise HTTPException(status_code=500, detail=f"Translation failed: {str(e)}")
@app.post("/submit-correction", response_model=CorrectionResponse)
async def submit_correction(request: CorrectionRequest):
"""
Submit manual correction for a translation
Args:
request: Contains translation ID and corrected text
Returns:
Confirmation of correction submission
"""
try:
logger.info(f"Correction submission for translation ID: {request.translation_id}")
# Store correction in database
correction_id = db_manager.store_correction(
translation_id=request.translation_id,
corrected_text=request.corrected_text,
feedback=request.feedback
)
logger.info(f"Correction stored with ID: {correction_id}")
return CorrectionResponse(
correction_id=correction_id,
message="Correction submitted successfully",
status="success"
)
except Exception as e:
logger.error(f"Correction submission error: {str(e)}")
raise HTTPException(status_code=500, detail=f"Failed to submit correction: {str(e)}")
@app.get("/history", response_model=List[TranslationHistory])
async def get_translation_history(limit: int = 50, offset: int = 0):
"""
Get translation history
Args:
limit: Maximum number of records to return
offset: Number of records to skip
Returns:
List of translation history records
"""
try:
history = db_manager.get_translation_history(limit=limit, offset=offset)
return [TranslationHistory(**record) for record in history]
except Exception as e:
logger.error(f"History retrieval error: {str(e)}")
raise HTTPException(status_code=500, detail=f"Failed to retrieve history: {str(e)}")
@app.get("/supported-languages")
async def get_supported_languages():
"""Get list of supported languages"""
return {
"languages": translation_service.get_supported_languages(),
"total_count": len(translation_service.get_supported_languages())
}
@app.post("/batch-translate")
async def batch_translate(texts: List[str], target_language: str, source_language: Optional[str] = None):
"""
Batch translate multiple texts
Args:
texts: List of texts to translate
target_language: Target language code
source_language: Source language code (auto-detect if not provided)
Returns:
List of translation results
"""
try:
logger.info(f"Batch translation request for {len(texts)} texts")
results = []
for text in texts:
# Auto-detect source language if not provided
if not source_language:
detection_result = await translation_service.detect_language(text)
detected_source = detection_result['language']
else:
detected_source = source_language
# Perform translation
translation_result = await translation_service.translate(
text=text,
source_lang=detected_source,
target_lang=target_language
)
# Store translation in database
translation_id = db_manager.store_translation(
original_text=text,
translated_text=translation_result['translated_text'],
source_language=detected_source,
target_language=target_language,
model_confidence=translation_result.get('confidence', 0.0)
)
results.append({
"original_text": text,
"translated_text": translation_result['translated_text'],
"source_language": detected_source,
"target_language": target_language,
"translation_id": translation_id,
"confidence": translation_result.get('confidence', 0.0)
})
logger.info(f"Batch translation completed for {len(results)} texts")
return {"translations": results}
except Exception as e:
logger.error(f"Batch translation error: {str(e)}")
raise HTTPException(status_code=500, detail=f"Batch translation failed: {str(e)}")
if __name__ == "__main__":
uvicorn.run(
"main:app",
host="0.0.0.0",
port=8000,
reload=True,
log_level="info"
)
|