[2ff88f42] Finalize SuperOffice Integration: Enhanced Persona model with Influencer role, switched Matrix Generator to Gemini, implemented Noise Reduction for Webhooks, and added E2E test scenarios.

company-explorer/backend/scripts/generate_matrix.py

@@ -1,17 +1,18 @@
-
 import sys
 import os
 import json
 import argparse
 from typing import List
+import google.generativeai as genai
 
 # Setup Environment
 sys.path.append(os.path.join(os.path.dirname(__file__), "../../"))
 
 from backend.database import SessionLocal, Industry, Persona, MarketingMatrix
+from backend.config import settings
 
 # --- Configuration ---
-MODEL = "gpt-4o"
+MODEL_NAME = "gemini-1.5-pro-latest" # High quality copy
 
 def generate_prompt(industry: Industry, persona: Persona) -> str:
     """
@@ -54,6 +55,8 @@ Tonalität: Professionell, lösungsorientiert, auf den Punkt. Keine Marketing-Fl
 3. "social_proof": Ein Satz, der Vertrauen aufbaut. Nenne generische Erfolge (z.B. "Unternehmen in der {industry.name} senken so ihre Kosten um 15%"), da wir noch keine spezifischen Logos nennen dürfen.
 
 --- FORMAT ---
+Respond ONLY with a valid JSON object. Do not add markdown formatting like ```json ... ```.
+Format:
 {{
   "subject": "...",
   "intro": "...",
@@ -62,7 +65,7 @@ Tonalität: Professionell, lösungsorientiert, auf den Punkt. Keine Marketing-Fl
 """
     return prompt
 
-def mock_openai_call(prompt: str):
+def mock_call(prompt: str):
     """Simulates an API call for dry runs."""
     print(f"\n--- [MOCK] GENERATING PROMPT ---\n{prompt[:300]}...\n--------------------------------")
     return {
@@ -71,23 +74,40 @@ def mock_openai_call(prompt: str):
         "social_proof": "[MOCK] Ähnliche Betriebe sparten 20% Kosten."
     }
 
-def real_openai_call(prompt: str):
-    # This would link to the actual OpenAI client
-    # For now, we keep it simple or import from a lib
-    import openai
-    from backend.config import settings
-    
-    if not settings.OPENAI_API_KEY:
-        raise ValueError("OPENAI_API_KEY not set")
+def real_gemini_call(prompt: str):
+    if not settings.GEMINI_API_KEY:
+        raise ValueError("GEMINI_API_KEY not set in config/env")
         
-    client = openai.OpenAI(api_key=settings.OPENAI_API_KEY)
-    response = client.chat.completions.create(
-        model=MODEL,
-        response_format={"type": "json_object"},
-        messages=[{"role": "user", "content": prompt}],
-        temperature=0.7
+    genai.configure(api_key=settings.GEMINI_API_KEY)
+    
+    # Configure Model
+    generation_config = {
+        "temperature": 0.7,
+        "top_p": 0.95,
+        "top_k": 64,
+        "max_output_tokens": 1024,
+        "response_mime_type": "application/json",
+    }
+    
+    model = genai.GenerativeModel(
+        model_name=MODEL_NAME,
+        generation_config=generation_config,
     )
-    return json.loads(response.choices[0].message.content)
+    
+    response = model.generate_content(prompt)
+    
+    try:
+        # Clean response if necessary (Gemini usually returns clean JSON with mime_type set, but safety first)
+        text = response.text.strip()
+        if text.startswith("```json"):
+            text = text[7:-3].strip()
+        elif text.startswith("```"):
+            text = text[3:-3].strip()
+            
+        return json.loads(text)
+    except Exception as e:
+        print(f"JSON Parse Error: {e}. Raw Response: {response.text}")
+        raise
 
 def run_matrix_generation(dry_run: bool = True, force: bool = False):
     db = SessionLocal()
@@ -96,7 +116,7 @@ def run_matrix_generation(dry_run: bool = True, force: bool = False):
         personas = db.query(Persona).all()
         
         print(f"Found {len(industries)} Industries and {len(personas)} Personas.")
-        print(f"Mode: {'DRY RUN (No API calls, no DB writes)' if dry_run else 'LIVE'}")
+        print(f"Mode: {'DRY RUN (No API calls, no DB writes)' if dry_run else 'LIVE - GEMINI GENERATION'}")
         
         total_combinations = len(industries) * len(personas)
         processed = 0
@@ -120,10 +140,15 @@ def run_matrix_generation(dry_run: bool = True, force: bool = False):
                 prompt = generate_prompt(ind, pers)
                 
                 if dry_run:
-                    result = mock_openai_call(prompt)
+                    result = mock_call(prompt)
                 else:
                     try:
-                        result = real_openai_call(prompt)
+                        result = real_gemini_call(prompt)
+                        # Basic Validation
+                        if not result.get("subject") or not result.get("intro"):
+                            print("  -> Invalid result structure. Skipping.")
+                            continue
+                            
                     except Exception as e:
                         print(f"  -> API ERROR: {e}")
                         continue
@@ -155,8 +180,8 @@ def run_matrix_generation(dry_run: bool = True, force: bool = False):
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.add_argument("--live", action="store_true", help="Actually call OpenAI and write to DB")
+    parser.add_argument("--live", action="store_true", help="Actually call Gemini and write to DB")
     parser.add_argument("--force", action="store_true", help="Overwrite existing matrix entries")
     args = parser.parse_args()
     
-    run_matrix_generation(dry_run=not args.live, force=args.force)
+    run_matrix_generation(dry_run=not args.live, force=args.force)