[30388f42] Infrastructure Hardening: Repaired CE/Connector DB schema, fixed frontend styling build, implemented robust echo shield in worker v2.1.1, and integrated Lead Engine into gateway.

lead-engine/lookup_role.py

@@ -0,0 +1,129 @@
+import os
+import requests
+import re
+from dotenv import load_dotenv
+
+# Try loading .env only if file exists (Local Dev), otherwise rely on Docker Env
+env_path = os.path.abspath(os.path.join(os.path.dirname(__file__), '..', '.env'))
+if os.path.exists(env_path):
+    load_dotenv(dotenv_path=env_path, override=True)
+
+SERP_API_KEY = os.getenv("SERP_API")
+
+if not SERP_API_KEY:
+    print(f"DEBUG: SERP_API not found in environment.")
+
+import json
+
+# --- Helper: Get Gemini Key ---
+def get_gemini_key():
+    candidates = [
+        "gemini_api_key.txt",                     # Current dir
+        "/app/gemini_api_key.txt",                # Docker default
+        os.path.join(os.path.dirname(__file__), "gemini_api_key.txt"), # Script dir
+        os.path.join(os.path.dirname(os.path.dirname(__file__)), 'gemini_api_key.txt') # Parent dir
+    ]
+    
+    for path in candidates:
+        if os.path.exists(path):
+            try:
+                with open(path, 'r') as f:
+                    return f.read().strip()
+            except:
+                pass
+                
+    return os.getenv("GEMINI_API_KEY")
+
+def extract_role_with_llm(name, company, search_results):
+    """Uses Gemini to identify the job title from search snippets."""
+    api_key = get_gemini_key()
+    if not api_key: return None
+    
+    context = "\n".join([f"- {r.get('title')}: {r.get('snippet')}" for r in search_results])
+    
+    prompt = f"""
+    Analyze these Google Search results to identify the professional role of "{name}" at "{company}".
+    
+    SEARCH RESULTS:
+    {context}
+    
+    TASK:
+    Extract the professional Job Title / Role. 
+    Look for: 
+    - Management: "Geschäftsführer", "Vorstand", "CFO", "Mitglied der Klinikleitung"
+    - Department Heads: "Leiter", "Bereichsleitung", "Head of", "Pflegedienstleitung"
+    - Specialized: "Arzt", "Ingenieur", "Einkäufer"
+    
+    RULES:
+    1. Extract the most specific and senior current role.
+    2. Return ONLY the role string (e.g. "Bereichsleitung Patientenmanagement").
+    3. Maximum length: 60 characters.
+    4. If no role is found, return "Unbekannt".
+    """
+    
+    url = f"https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key={api_key}"
+    try:
+        response = requests.post(url, headers={'Content-Type': 'application/json'}, json={"contents": [{"parts": [{"text": prompt}]}]})
+        if response.status_code == 200:
+            role = response.json()['candidates'][0]['content']['parts'][0]['text'].strip()
+            # Remove markdown formatting if any
+            role = role.replace('**', '').replace('"', '').rstrip('.')
+            return None if "Unbekannt" in role else role
+        else:
+            print(f"DEBUG: Gemini API Error {response.status_code}: {response.text}")
+    except Exception as e:
+        print(f"DEBUG: Gemini API Exception: {e}")
+    return None
+
+def lookup_person_role(name, company):
+    """
+    Searches for a person's role via SerpAPI and extracts it using LLM.
+    Uses a multi-step search strategy to find the best snippets.
+    """
+    if not SERP_API_KEY:
+        print("Error: SERP_API key not found in .env")
+        return None
+
+    # Step 1: Highly specific search
+    queries = [
+        f'site:linkedin.com "{name}" "{company}"',
+        f'"{name}" "{company}" position',
+        f'{name} {company}'
+    ]
+    
+    all_results = []
+    for query in queries:
+        params = {
+            "engine": "google",
+            "q": query,
+            "api_key": SERP_API_KEY,
+            "num": 3,
+            "hl": "de",
+            "gl": "de"
+        }
+
+        try:
+            response = requests.get("https://serpapi.com/search", params=params)
+            response.raise_for_status()
+            data = response.json()
+            
+            results = data.get("organic_results", [])
+            if results:
+                all_results.extend(results)
+                # If we have good results, we don't necessarily need more searches
+                if len(all_results) >= 3:
+                    break
+        except Exception as e:
+            print(f"SerpAPI lookup failed for query '{query}': {e}")
+
+    if not all_results:
+        return None
+
+    # Delegate extraction to LLM with the best results found
+    return extract_role_with_llm(name, company, all_results)
+
+if __name__ == "__main__":
+    # Test cases
+    print(f"Markus Drees: {lookup_person_role('Markus Drees', 'Ärztehaus Rünthe')}")
+    print(f"Georg Stahl: {lookup_person_role('Georg Stahl', 'Klemm Bohrtechnik GmbH')}")
+    print(f"Steve Trüby: {lookup_person_role('Steve Trüby', 'RehaKlinikum Bad Säckingen GmbH')}")