Update main.py

main.py

@@ -12,7 +12,7 @@ from typing import Optional, List, Union
 from model import (
     summarize_review, smart_summarize, detect_industry,
     detect_product_category, detect_emotion, answer_followup, answer_only,
-    assess_churn_risk  # ✅ Add this
+    assess_churn_risk, extract_pain_points  # ✅ Added extract_pain_points
 )
 
 app = FastAPI(
@@ -34,7 +34,7 @@ app.add_middleware(
 
 logging.basicConfig(level=logging.INFO)
 VALID_API_KEY = "my-secret-key"
-log_store = []
+log_store = []  # ✅ Shared in-memory churn log
 
 @app.get("/", response_class=HTMLResponse)
 def root():
@@ -100,52 +100,45 @@ async def analyze(data: ReviewInput, x_api_key: str = Header(None)):
     if len(data.text.split()) < 20:
         raise HTTPException(status_code=400, detail="⚠️ Review too short for analysis (min. 20 words).")
 
-    try:
-        response = {}
-
-        if not data.follow_up:
-            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_pipeline = pipeline("sentiment-analysis", model=data.model)
-            sentiment = sentiment_pipeline(data.text)[0]
-            emotion_raw = detect_emotion(data.text)
-            emotion = emotion_raw["label"] if isinstance(emotion_raw, dict) and "label" in emotion_raw else str(emotion_raw)
-            churn_risk = assess_churn_risk(sentiment["label"], emotion)
-            
-            # Log churn risk analysis
-            log_entry = {
-                "timestamp": datetime.now(),
-                "product": data.product_category or "Generic",
-                "churn_risk": churn_risk,
-                "user_id": str(uuid.uuid4())  # Optional
-            }
-            log_store.append(log_entry)
-            if len(log_store) > 1000:
-                log_store = log_store[-1000:]  # keep latest 1000 entries
-
-            pain_points = []
-            if data.aspects:
-                from model import extract_pain_points  # 🔍 Import inline if not already
-                pain_points = extract_pain_points(data.text)
+    global log_store  # ✅ Needed for logging
 
-            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
-
-            response = {
-                "summary": summary,
-                "sentiment": sentiment,
-                "emotion": emotion,
-                "product_category": product_category,
-                "device": "Web",
-                "industry": industry,
-                "churn_risk": churn_risk,
-                "pain_points": pain_points
+    try:
+        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_pipeline = pipeline("sentiment-analysis", model=data.model)
+        sentiment = sentiment_pipeline(data.text)[0]
+        emotion_raw = detect_emotion(data.text)
+        emotion = emotion_raw["label"] if isinstance(emotion_raw, dict) and "label" in emotion_raw else str(emotion_raw)
+        churn_risk = assess_churn_risk(sentiment["label"], emotion)
+        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
+
+        pain_points = extract_pain_points(data.text) if data.aspects else []
+
+        # ✅ Log churn entry
+        log_store.append({
+            "timestamp": datetime.now(),
+            "product": product_category,
+            "churn_risk": churn_risk,
+            "user_id": str(uuid.uuid4())
+        })
+        if len(log_store) > 1000:
+            log_store = log_store[-1000:]
+
+        response = {
+            "summary": summary,
+            "sentiment": sentiment,
+            "emotion": emotion,
+            "product_category": product_category,
+            "device": "Web",
+            "industry": industry,
+            "churn_risk": churn_risk,
+            "pain_points": pain_points
+        }
 
         if data.follow_up:
             response["follow_up"] = answer_followup(data.text, data.follow_up, verbosity=data.verbosity)
@@ -154,22 +147,19 @@ async def analyze(data: ReviewInput, x_api_key: str = Header(None)):
 
     except Exception as e:
         logging.error(f"🔥 Unexpected analysis failure: {traceback.format_exc()}")
-        raise HTTPException(status_code=500, detail="Internal Server Error during analysis. Please contact support.")
+        raise HTTPException(status_code=500, detail="Internal Server Error during analysis.")
 
 @app.post("/followup/")
 async def followup(request: FollowUpRequest, 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 not request.question or len(request.text.split()) < 10:
-        raise HTTPException(status_code=400, detail="Question or text is too short.")
-
     try:
-        answer = answer_only(request.text, request.question)
-        return {"answer": answer}
+        if not request.question or len(request.text.split()) < 10:
+            raise HTTPException(status_code=400, detail="Question or text is too short.")
+        return {"answer": answer_only(request.text, request.question)}
     except Exception as e:
         logging.error(f"❌ Follow-up failed: {traceback.format_exc()}")
-        raise HTTPException(status_code=500, detail="Internal Server Error during follow-up.")
+        raise HTTPException(status_code=500, detail="Follow-up generation failed.")
 
 @app.get("/log/")
 async def get_churn_log(x_api_key: str = Header(None)):
@@ -177,12 +167,13 @@ async def get_churn_log(x_api_key: str = Header(None)):
         raise HTTPException(status_code=401, detail="Unauthorized")
     return {"log": log_store}
 
-
 @app.post("/bulk/")
 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")
 
+    global log_store  # ✅ Needed to log bulk churn
+
     try:
         results = []
         sentiment_pipeline = pipeline("sentiment-analysis", model=data.model)
@@ -198,22 +189,9 @@ async def bulk_analyze(data: BulkReviewInput, token: str = Query(None)):
             summary = smart_summarize(review_text, n_clusters=2 if data.intelligence else 1)
             sentiment = sentiment_pipeline(review_text)[0]
             emotion = detect_emotion(review_text)
-            
             churn = assess_churn_risk(sentiment["label"], emotion)
             pain = extract_pain_points(review_text) if data.aspects else []
 
-            # 🔁 Log churn data
-            log_entry = {
-                "timestamp": datetime.now(),
-                "product": prod,
-                "churn_risk": churn,
-                "user_id": str(uuid.uuid4())
-            }
-            log_store.append(log_entry)
-            if len(log_store) > 1000:
-                log_store = log_store[-1000:]
-
-
             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")
@@ -235,11 +213,21 @@ async def bulk_analyze(data: BulkReviewInput, token: str = Query(None)):
                 follow_q = data.follow_up[i]
                 result["follow_up"] = answer_followup(review_text, follow_q)
 
+            # ✅ Log churn
+            log_store.append({
+                "timestamp": datetime.now(),
+                "product": prod,
+                "churn_risk": churn,
+                "user_id": str(uuid.uuid4())
+            })
+
             results.append(result)
 
+        if len(log_store) > 1000:
+            log_store = log_store[-1000:]
+
         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")
-