Update main.py

main.py

@@ -7,8 +7,11 @@ from pydantic import BaseModel
 from fastapi import Query
 from transformers import pipeline
 import os, logging, traceback
-from model import summarize_review, smart_summarize, detect_industry, detect_product_category, answer_followup
-from typing import Optional, List
+from model import (
+    summarize_review, smart_summarize, detect_industry, 
+    detect_product_category, answer_followup, detect_emotion, generate_explanation
+)
+from typing import Optional, List, Union
 
 app = FastAPI(
     title="\U0001f9e0 NeuroPulse AI",
@@ -51,7 +54,7 @@ class ReviewInput(BaseModel):
     model: str = "distilbert-base-uncased-finetuned-sst-2-english"
     industry: Optional[str] = None
     aspects: bool = False
-    follow_up: Optional[str] = None
+    follow_up: Optional[Union[str, List[str]]] = None
     product_category: Optional[str] = None
     device: Optional[str] = None
     intelligence: Optional[bool] = False
@@ -65,8 +68,10 @@ class BulkReviewInput(BaseModel):
     aspects: bool = False
     product_category: Optional[List[str]] = None
     device: Optional[List[str]] = None
+    follow_up: Optional[List[Union[str, List[str]]]] = None
+    explain: Optional[bool] = False
     intelligence: Optional[bool] = False 
-    
+
 VALID_API_KEY = "my-secret-key"
 logging.basicConfig(level=logging.INFO)
 sentiment_pipeline = pipeline("sentiment-analysis")
@@ -80,22 +85,22 @@ def auto_fill(value: Optional[str], fallback: str) -> str:
 async def analyze(data: ReviewInput, x_api_key: str = Header(None)):
     if x_api_key and x_api_key != VALID_API_KEY:
         raise HTTPException(status_code=401, detail="❌ Invalid API key")
-    
+
     if len(data.text.split()) < 20:
         raise HTTPException(status_code=400, detail="⚠️ Review too short for analysis (min. 20 words).")
 
     try:
         response = {}
 
-        # Only perform core analysis if follow-up not present (or first-time analysis)
         if not data.follow_up:
-            if data.verbosity.lower() == "brief":
-                summary = summarize_review(data.text, max_len=40, min_len=8)
-            else:
-                summary = smart_summarize(data.text, n_clusters=2 if data.intelligence else 1)
+            summary = (
+                summarize_review(data.text, max_len=40, min_len=8)
+                if data.verbosity.lower() == "brief"
+                else smart_summarize(data.text, n_clusters=2 if data.intelligence else 1)
+            )
 
             sentiment = sentiment_pipeline(data.text)[0]
-            emotion = "joy"
+            emotion = detect_emotion(data.text)
 
             industry = detect_industry(data.text) if not data.industry or "auto" in data.industry.lower() else data.industry
             product_category = detect_product_category(data.text) if not data.product_category or "auto" in data.product_category.lower() else data.product_category
@@ -110,10 +115,11 @@ async def analyze(data: ReviewInput, x_api_key: str = Header(None)):
                 "industry": industry
             }
 
-        # If follow-up question is asked, generate answer
+            if data.explain:
+                response["explanation"] = generate_explanation(data.text)
+
         if data.follow_up:
-            follow_up_response = answer_followup(data.text, data.follow_up, verbosity=data.verbosity)
-            response["follow_up"] = follow_up_response
+            response["follow_up"] = answer_followup(data.text, data.follow_up, verbosity=data.verbosity)
 
         return response
 
@@ -122,12 +128,10 @@ async def analyze(data: ReviewInput, x_api_key: str = Header(None)):
         raise HTTPException(status_code=500, detail="Internal Server Error during analysis. Please contact support.")
 
 @app.post("/bulk/")
-async def bulk_analyze(
-    data: BulkReviewInput,
-    token: str = Query(None)
-):
+async def bulk_analyze(data: BulkReviewInput, token: str = Query(None)):
     if token != VALID_API_KEY:
         raise HTTPException(status_code=401, detail="❌ Unauthorized: Invalid API token")
+
     try:
         results = []
         for i, review_text in enumerate(data.reviews):
@@ -140,13 +144,13 @@ async def bulk_analyze(
 
             summary = smart_summarize(review_text, n_clusters=2 if data.intelligence else 1)
             sentiment = sentiment_pipeline(review_text)[0]
-            emotion = "joy"
+            emotion = detect_emotion(review_text)
 
             ind = auto_fill(data.industry[i] if data.industry else None, detect_industry(review_text))
             prod = auto_fill(data.product_category[i] if data.product_category else None, detect_product_category(review_text))
             dev = auto_fill(data.device[i] if data.device else None, "Web")
 
-            results.append({
+            result = {
                 "review": review_text,
                 "summary": summary,
                 "sentiment": sentiment["label"],
@@ -155,9 +159,21 @@ async def bulk_analyze(
                 "industry": ind,
                 "product_category": prod,
                 "device": dev
-            })
+            }
+
+            # Optional follow-up
+            if data.follow_up and i < len(data.follow_up):
+                follow_q = data.follow_up[i]
+                result["follow_up"] = answer_followup(review_text, follow_q)
+
+            # Optional explanation
+            if data.explain:
+                result["explanation"] = generate_explanation(review_text)
+
+            results.append(result)
+
         return {"results": results}
-    
+
     except Exception as e:
         logging.error(f"🔥 Bulk processing failed: {traceback.format_exc()}")
         raise HTTPException(status_code=500, detail="Failed to analyze bulk reviews")