163 lines
6.0 KiB
Python
163 lines
6.0 KiB
Python
|
|
import sys
|
|
import os
|
|
import json
|
|
import argparse
|
|
from typing import List
|
|
|
|
# Setup Environment
|
|
sys.path.append(os.path.join(os.path.dirname(__file__), "../../"))
|
|
|
|
from backend.database import SessionLocal, Industry, Persona, MarketingMatrix
|
|
|
|
# --- Configuration ---
|
|
MODEL = "gpt-4o"
|
|
|
|
def generate_prompt(industry: Industry, persona: Persona) -> str:
|
|
"""
|
|
Builds the prompt for the AI to generate the marketing texts.
|
|
Combines Industry context with Persona specific pains/gains.
|
|
"""
|
|
|
|
# Safely load JSON lists
|
|
try:
|
|
persona_pains = json.loads(persona.pains) if persona.pains else []
|
|
persona_gains = json.loads(persona.gains) if persona.gains else []
|
|
except:
|
|
persona_pains = [persona.pains] if persona.pains else []
|
|
persona_gains = [persona.gains] if persona.gains else []
|
|
|
|
industry_pains = industry.pains if industry.pains else "Allgemeine Effizienzprobleme"
|
|
|
|
prompt = f"""
|
|
Du bist ein erfahrener B2B-Copywriter für Robotik-Lösungen (Reinigung, Transport, Service).
|
|
Ziel: Erstelle personalisierte E-Mail-Textbausteine für einen Outreach.
|
|
|
|
--- KONTEXT ---
|
|
ZIELBRANCHE: {industry.name}
|
|
BRANCHEN-KONTEXT: {industry.description or 'Keine spezifische Beschreibung'}
|
|
BRANCHEN-PAINS: {industry_pains}
|
|
|
|
ZIELPERSON (ARCHETYP): {persona.name}
|
|
PERSÖNLICHE PAINS (Herausforderungen):
|
|
{chr(10).join(['- ' + p for p in persona_pains])}
|
|
|
|
GEWÜNSCHTE GAINS (Ziele):
|
|
{chr(10).join(['- ' + g for g in persona_gains])}
|
|
|
|
--- AUFGABE ---
|
|
Erstelle ein JSON-Objekt mit genau 3 Textbausteinen.
|
|
Tonalität: Professionell, lösungsorientiert, auf den Punkt. Keine Marketing-Floskeln ("Game Changer").
|
|
|
|
1. "subject": Betreffzeile (Max 6 Wörter). Muss neugierig machen und einen Pain adressieren.
|
|
2. "intro": Einleitungssatz (1-2 Sätze). Verbinde die Branchen-Herausforderung mit der persönlichen Rolle des Empfängers. Zeige Verständnis für seine Situation.
|
|
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 ---
|
|
{{
|
|
"subject": "...",
|
|
"intro": "...",
|
|
"social_proof": "..."
|
|
}}
|
|
"""
|
|
return prompt
|
|
|
|
def mock_openai_call(prompt: str):
|
|
"""Simulates an API call for dry runs."""
|
|
print(f"\n--- [MOCK] GENERATING PROMPT ---\n{prompt[:300]}...\n--------------------------------")
|
|
return {
|
|
"subject": "[MOCK] Effizienzsteigerung in der Produktion",
|
|
"intro": "[MOCK] Als Produktionsleiter wissen Sie, wie teuer Stillstand ist. Unsere Roboter helfen.",
|
|
"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")
|
|
|
|
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
|
|
)
|
|
return json.loads(response.choices[0].message.content)
|
|
|
|
def run_matrix_generation(dry_run: bool = True, force: bool = False):
|
|
db = SessionLocal()
|
|
try:
|
|
industries = db.query(Industry).all()
|
|
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'}")
|
|
|
|
total_combinations = len(industries) * len(personas)
|
|
processed = 0
|
|
|
|
for ind in industries:
|
|
for pers in personas:
|
|
processed += 1
|
|
print(f"[{processed}/{total_combinations}] Check: {ind.name} x {pers.name}")
|
|
|
|
# Check existing
|
|
existing = db.query(MarketingMatrix).filter(
|
|
MarketingMatrix.industry_id == ind.id,
|
|
MarketingMatrix.persona_id == pers.id
|
|
).first()
|
|
|
|
if existing and not force:
|
|
print(f" -> Skipped (Already exists)")
|
|
continue
|
|
|
|
# Generate
|
|
prompt = generate_prompt(ind, pers)
|
|
|
|
if dry_run:
|
|
result = mock_openai_call(prompt)
|
|
else:
|
|
try:
|
|
result = real_openai_call(prompt)
|
|
except Exception as e:
|
|
print(f" -> API ERROR: {e}")
|
|
continue
|
|
|
|
# Write to DB (only if not dry run)
|
|
if not dry_run:
|
|
if not existing:
|
|
new_entry = MarketingMatrix(
|
|
industry_id=ind.id,
|
|
persona_id=pers.id,
|
|
subject=result.get("subject"),
|
|
intro=result.get("intro"),
|
|
social_proof=result.get("social_proof")
|
|
)
|
|
db.add(new_entry)
|
|
print(f" -> Created new entry.")
|
|
else:
|
|
existing.subject = result.get("subject")
|
|
existing.intro = result.get("intro")
|
|
existing.social_proof = result.get("social_proof")
|
|
print(f" -> Updated entry.")
|
|
|
|
db.commit()
|
|
|
|
except Exception as e:
|
|
print(f"Error: {e}")
|
|
finally:
|
|
db.close()
|
|
|
|
if __name__ == "__main__":
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("--live", action="store_true", help="Actually call OpenAI 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)
|