Initial MVP Commit: Ingest, Enrich, Dashboard

Dockerfile

@@ -0,0 +1,9 @@
+FROM python:3.9-slim
+
+WORKDIR /app
+
+COPY . .
+
+RUN pip install streamlit pandas
+
+CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]

app.py

@@ -0,0 +1,55 @@
+import streamlit as st
+import pandas as pd
+from db import get_leads, init_db
+import json
+
+st.set_page_config(page_title="TradingTwins Lead Engine", layout="wide")
+
+st.title("🚀 Lead Engine: TradingTwins")
+
+# Metrics
+leads = get_leads()
+df = pd.DataFrame(leads)
+
+if not df.empty:
+    col1, col2, col3 = st.columns(3)
+    col1.metric("Total Leads", len(df))
+    col2.metric("New Today", len(df[df['status'] == 'new']))
+    col3.metric("Action Required", len(df[df['status'] == 'enriched']))
+
+    st.subheader("Latest Inquiries")
+    
+    for index, row in df.iterrows():
+        with st.expander(f"{row['company_name']} - {row['status']}"):
+            c1, c2 = st.columns(2)
+            c1.write(f"**Contact:** {row['contact_name']}")
+            c1.write(f"**Email:** {row['email']}")
+            
+            enrichment = json.loads(row['enrichment_data']) if row['enrichment_data'] else {}
+            
+            if enrichment:
+                c2.success(f"Score: {enrichment.get('score')}")
+                c2.write(f"**Vertical:** {enrichment.get('vertical')}")
+                c2.info(f"💡 {enrichment.get('recommendation')}")
+            
+            if st.button(f"Generate Response for {row['id']}"):
+                st.write("Generating draft... (Simulated)")
+                # Here we would call the LLM
+                draft = f"Hallo {row['contact_name']},\n\ndanke für Ihre Anfrage..."
+                st.text_area("Draft", draft, height=200)
+
+else:
+    st.info("No leads found. Waiting for ingest...")
+
+if st.sidebar.button("Run Ingest (Mock)"):
+    from ingest import ingest_mock_leads
+    init_db()
+    count = ingest_mock_leads()
+    st.sidebar.success(f"Ingested {count} leads.")
+    st.rerun()
+
+if st.sidebar.button("Run Enrichment"):
+    from enrich import run_enrichment
+    run_enrichment()
+    st.sidebar.success("Enrichment complete.")
+    st.rerun()

db.py

@@ -0,0 +1,70 @@
+import sqlite3
+import json
+from datetime import datetime
+
+DB_PATH = 'lead-engine/data/leads.db'
+
+def init_db():
+    conn = sqlite3.connect(DB_PATH)
+    c = conn.cursor()
+    c.execute('''
+        CREATE TABLE IF NOT EXISTS leads (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            source_id TEXT UNIQUE,
+            received_at TIMESTAMP,
+            company_name TEXT,
+            contact_name TEXT,
+            email TEXT,
+            phone TEXT,
+            raw_body TEXT,
+            enrichment_data TEXT,
+            status TEXT DEFAULT 'new',
+            response_draft TEXT,
+            sent_at TIMESTAMP
+        )
+    ''')
+    conn.commit()
+    conn.close()
+
+def insert_lead(lead_data):
+    conn = sqlite3.connect(DB_PATH)
+    c = conn.cursor()
+    try:
+        c.execute('''
+            INSERT INTO leads (source_id, received_at, company_name, contact_name, email, phone, raw_body, status)
+            VALUES (?, ?, ?, ?, ?, ?, ?, ?)
+        ''', (
+            lead_data.get('id'),
+            datetime.now(),
+            lead_data.get('company'),
+            lead_data.get('contact'),
+            lead_data.get('email'),
+            lead_data.get('phone'),
+            lead_data.get('raw_body'),
+            'new'
+        ))
+        conn.commit()
+        return True
+    except sqlite3.IntegrityError:
+        return False
+    finally:
+        conn.close()
+
+def get_leads():
+    conn = sqlite3.connect(DB_PATH)
+    conn.row_factory = sqlite3.Row
+    c = conn.cursor()
+    c.execute('SELECT * FROM leads ORDER BY received_at DESC')
+    rows = c.fetchall()
+    conn.close()
+    return [dict(row) for row in rows]
+
+def update_lead_status(lead_id, status, response_draft=None):
+    conn = sqlite3.connect(DB_PATH)
+    c = conn.cursor()
+    if response_draft:
+        c.execute('UPDATE leads SET status = ?, response_draft = ? WHERE id = ?', (status, response_draft, lead_id))
+    else:
+        c.execute('UPDATE leads SET status = ? WHERE id = ?', (status, lead_id))
+    conn.commit()
+    conn.close()

enrich.py

@@ -0,0 +1,43 @@
+import json
+from db import update_lead_status, get_leads
+import sqlite3
+
+def enrich_lead(lead):
+    # Mock Enrichment Logic
+    # In production, this would call the Company Explorer API
+    
+    enrichment = {
+        'vertical': 'Unknown',
+        'score': 0,
+        'recommendation': 'Manual Review'
+    }
+    
+    company = lead['company_name'].lower()
+    raw = lead['raw_body']
+    
+    if 'küche' in company or 'einbau' in company:
+        enrichment['vertical'] = 'Manufacturing / Woodworking'
+        enrichment['score'] = 85
+        enrichment['recommendation'] = 'High Priority - Pitch Dust Control'
+        
+    if 'shop' in company or 'roller' in company:
+        enrichment['vertical'] = 'Retail / Automotive'
+        enrichment['score'] = 60
+        enrichment['recommendation'] = 'Medium Priority - Pitch Showroom Cleanliness'
+
+    # Update DB
+    conn = sqlite3.connect('lead-engine/data/leads.db')
+    c = conn.cursor()
+    c.execute('UPDATE leads SET enrichment_data = ?, status = ? WHERE id = ?', 
+              (json.dumps(enrichment), 'enriched', lead['id']))
+    conn.commit()
+    conn.close()
+    
+def run_enrichment():
+    leads = get_leads()
+    for lead in leads:
+        if lead['status'] == 'new':
+            enrich_lead(lead)
+
+if __name__ == "__main__":
+    run_enrichment()

ingest.py

@@ -0,0 +1,75 @@
+import re
+from db import insert_lead
+
+def parse_tradingtwins_email(body):
+    data = {}
+    
+    # Simple regex extraction based on the email format
+    patterns = {
+        'id': r'Lead-ID:\s*(\d+)',
+        'company': r'Firma:\s*(.+)',
+        'contact_first': r'Vorname:\s*(.+)',
+        'contact_last': r'Nachname:\s*(.+)',
+        'email': r'E-Mail:\s*([^\s<]+)',
+        'phone': r'Rufnummer:\s*([^\n]+)',
+        'area': r'Reinigungs-Flche:\s*([^\n]+)',
+        'purpose': r'Einsatzzweck:\s*([^\n]+)'
+    }
+    
+    for key, pattern in patterns.items():
+        match = re.search(pattern, body)
+        if match:
+            data[key] = match.group(1).strip()
+            
+    # Combine names
+    if 'contact_first' in data and 'contact_last' in data:
+        data['contact'] = f"{data['contact_first']} {data['contact_last']}"
+    
+    data['raw_body'] = body
+    return data
+
+def ingest_mock_leads():
+    # Mock data from the session context
+    leads = [
+        {
+            'id': '2397256',
+            'company': 'pronorm Einbauküchen GmbH',
+            'contact': 'Jakob Funk',
+            'email': 'jakob.funk@pronorm.de',
+            'phone': '+49 5733 979175',
+            'raw_body': """
+            Lead-ID: 2397256
+            Firma: pronorm Einbauküchen GmbH
+            Vorname: Jakob
+            Nachname: Funk
+            Reinigungs-Flche: 1.001 - 10.000 qm
+            Einsatzzweck: Reinigung von Böden
+            """
+        },
+        {
+            'id': '2414364',
+            'company': 'Quad & Rollershop Schwabmünchen GmbH',
+            'contact': 'Manfred Bihler',
+            'email': 'Rollershop.Schwabmuenchen@web.de',
+            'phone': '+49 8232 905246',
+            'raw_body': """
+            Lead-ID: 2414364
+            Firma: Quad & Rollershop Schwabmünchen GmbH
+            Vorname: Manfred
+            Nachname: Bihler
+            Reinigungs-Flche: 301 - 1.000 qm
+            Einsatzzweck: Reinigung von Böden
+            """
+        }
+    ]
+    
+    count = 0
+    for lead in leads:
+        if insert_lead(lead):
+            count += 1
+    return count
+
+if __name__ == "__main__":
+    from db import init_db
+    init_db()
+    print(f"Ingested {ingest_mock_leads()} new leads.")