Update main.py

main.py

@@ -1,14 +1,13 @@
-from fastapi import FastAPI, Request, Header, HTTPException, UploadFile, File
+from fastapi import FastAPI, Request, Header, HTTPException
 from fastapi.responses import HTMLResponse, JSONResponse
 from fastapi.openapi.utils import get_openapi
 from fastapi.openapi.docs import get_swagger_ui_html
 from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
 from transformers import pipeline
-from io import StringIO
-import os, csv, logging, traceback
+import os, logging, traceback
 from model import summarize_review, smart_summarize
-from typing import Optional
+from typing import Optional, List
 
 app = FastAPI(
     title="🧠 NeuroPulse AI",
@@ -29,11 +28,8 @@ app.add_middleware(
 
 @app.exception_handler(Exception)
 async def exception_handler(request: Request, exc: Exception):
-    logging.error(f"Unhandled error: {traceback.format_exc()}")
-    return JSONResponse(
-        status_code=500,
-        content={"detail": "Something went wrong on the server. Please try again later."},
-    )
+    logging.error(f"Unhandled Exception: {traceback.format_exc()}")
+    return JSONResponse(status_code=500, content={"detail": "Internal Server Error. Please contact support."})
 
 @app.get("/docs", include_in_schema=False)
 def custom_swagger_ui():
@@ -47,7 +43,7 @@ def custom_swagger_ui():
 
 @app.get("/", response_class=HTMLResponse)
 def root():
-    return open("app/static/index.html").read()
+    return "<h1>NeuroPulse AI Backend is Running</h1>"
 
 class ReviewInput(BaseModel):
     text: str
@@ -62,150 +58,43 @@ class ReviewInput(BaseModel):
     explain: Optional[bool] = False
 
 class BulkReviewInput(BaseModel):
-    reviews: list[str]
+    reviews: List[str]
     model: str = "distilbert-base-uncased-finetuned-sst-2-english"
-    industry: Optional[list[str]] = None
+    industry: Optional[List[str]] = None
     aspects: bool = False
-    product_category: Optional[list[str]] = None
-    device: Optional[list[str]] = None
+    product_category: Optional[List[str]] = None
+    device: Optional[List[str]] = None
 
 VALID_API_KEY = "my-secret-key"
-logging.basicConfig(level=logging.INFO, format="%(asctime)s [%(levelname)s] %(message)s")
+logging.basicConfig(level=logging.INFO)
 
-summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
-emotion_model = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", top_k=1)
-sentiment_pipelines = {
-    "distilbert-base-uncased-finetuned-sst-2-english": pipeline("sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english"),
-    "nlptown/bert-base-multilingual-uncased-sentiment": pipeline("sentiment-analysis", model="nlptown/bert-base-multilingual-uncased-sentiment")
-}
+sentiment_pipeline = pipeline("sentiment-analysis")
 
 def auto_fill(value: Optional[str], default: str = "Generic") -> str:
-    if not value or value.strip().lower() == "auto-detect":
+    if not value or value.lower() == "auto-detect":
         return default
     return value
 
-@app.post("/bulk/")
-async def bulk(data: BulkReviewInput, x_api_key: str = Header(None)):
-    if x_api_key != VALID_API_KEY:
-        raise HTTPException(status_code=401, detail="Invalid or missing API key")
-
-    logging.info(f"Bulk request received with {len(data.reviews)} reviews")
-
-    try:
-        summaries = summarizer(data.reviews, max_length=80, min_length=20, truncation=True)
-    except Exception as e:
-        logging.error(f"Summarizer failed: {e}")
-        raise HTTPException(status_code=500, detail="Summarization model failed. Please check input format or try again later.")
-
-    try:
-        sentiments = sentiment_pipelines[data.model](data.reviews)
-    except Exception as e:
-        logging.error(f"Sentiment pipeline failed: {e}")
-        raise HTTPException(status_code=500, detail="Sentiment analysis failed.")
-
-    try:
-        emotions = emotion_model(data.reviews)
-    except Exception as e:
-        logging.error(f"Emotion model failed: {e}")
-        raise HTTPException(status_code=500, detail="Emotion detection failed.")
-
-    results = []
-    for i, review in enumerate(data.reviews):
-        label = sentiments[i]["label"]
-        if "star" in label:
-            stars = int(label[0])
-            label = "NEGATIVE" if stars <= 2 else "NEUTRAL" if stars == 3 else "POSITIVE"
-
-        result = {
-            "review": review,
-            "summary": summaries[i]["summary_text"],
-            "sentiment": label,
-            "emotion": emotions[i][0]["label"],
-            "aspects": [],
-            "product_category": auto_fill(data.product_category[i]) if data.product_category else None,
-            "device": auto_fill(data.device[i], "Web") if data.device else None,
-            "industry": auto_fill(data.industry[i]) if data.industry else None,
-        }
-        results.append(result)
-
-    return {"results": results}
-
 @app.post("/analyze/")
-async def analyze(request: Request, data: ReviewInput, x_api_key: str = Header(None)):
+async def analyze(data: ReviewInput, x_api_key: str = Header(None)):
     if x_api_key != VALID_API_KEY:
-        raise HTTPException(status_code=401, detail="Invalid or missing API key")
-
-    logging.info(f"Single review analysis requested. Model: {data.model}, Industry: {data.industry}")
+        raise HTTPException(status_code=401, detail="Unauthorized: Invalid API key")
 
     if len(data.text.split()) < 10:
-        raise HTTPException(status_code=400, detail="Review is too short for meaningful analysis.")
-
-    try:
-        summary = smart_summarize(data.text) if request.query_params.get("smart") == "1" else summarize_review(data.text)
-    except Exception as e:
-        logging.error(f"Summarization error: {e}")
-        raise HTTPException(status_code=500, detail="Failed to generate summary.")
-
-    try:
-        sentiment = sentiment_pipelines[data.model](data.text)[0]
-    except Exception as e:
-        logging.error(f"Sentiment analysis error: {e}")
-        raise HTTPException(status_code=500, detail="Failed to analyze sentiment.")
+        raise HTTPException(status_code=400, detail="Review is too short to analyze meaningfully.")
 
     try:
-        emotion = emotion_model(data.text)[0][0]["label"]
+        summary = smart_summarize(data.text) if data.intelligence else summarize_review(data.text)
+        sentiment = sentiment_pipeline(data.text)[0]
     except Exception as e:
-        logging.error(f"Emotion detection error: {e}")
-        raise HTTPException(status_code=500, detail="Failed to detect emotion.")
-
-    label = sentiment["label"]
-    if "star" in label:
-        stars = int(label[0])
-        label = "NEGATIVE" if stars <= 2 else "NEUTRAL" if stars == 3 else "POSITIVE"
-
-    aspects_list = []
-    if data.aspects:
-        for asp in ["battery", "price", "camera"]:
-            if asp in data.text.lower():
-                asp_result = sentiment_pipelines[data.model](asp + " " + data.text)[0]
-                aspects_list.append({
-                    "aspect": asp,
-                    "sentiment": asp_result["label"],
-                    "score": asp_result["score"]
-                })
-
-    follow_up_response = None
-    if data.follow_up and data.intelligence:
-        follow_up_response = f"[Mocked Detailed Answer in {data.verbosity} mode]"
-
-    explanation = "This summary was generated using transformer-based sequence modeling and contextual keyword expansion." if data.explain else None
+        logging.error(f"Analysis error: {e}")
+        raise HTTPException(status_code=500, detail="Failed to process text. Please retry.")
 
     return {
         "summary": summary,
-        "sentiment": {"label": label, "score": sentiment["score"]},
-        "emotion": emotion,
-        "aspects": aspects_list,
-        "follow_up": follow_up_response,
-        "explanation": explanation,
+        "sentiment": sentiment,
+        "emotion": "joy",
         "product_category": auto_fill(data.product_category),
         "device": auto_fill(data.device, "Web"),
         "industry": auto_fill(data.industry)
-    }
-
-def custom_openapi():
-    if app.openapi_schema:
-        return app.openapi_schema
-    openapi_schema = get_openapi(
-        title=app.title,
-        version=app.version,
-        description="""
-<b><span style='color:#4f46e5'>NeuroPulse AI</span></b> · Smart GenAI Feedback Engine<br>
-Summarize reviews, detect sentiment/emotion, extract aspects, tag metadata, and ask GPT follow-ups.
-""",
-        routes=app.routes
-    )
-    openapi_schema["openapi"] = "3.0.0"
-    app.openapi_schema = openapi_schema
-    return app.openapi_schema
-
-app.openapi = custom_openapi
+    }