Floke/Brancheneinstufung2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[31388f42] Add SerpAPI debugging to UI and relax dotenv loading

Browse Source
This commit is contained in:
Floke
2026-03-02 09:40:04 +00:00
parent 4fa70f4ff1
commit faf2ac3670
2 changed files with 92 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

87
lead-engine/app.py
View File

@@ -2,9 +2,29 @@ import streamlit as st
import pandas as pd
from db import get_leads, init_db
import json
import re
import os
from enrich import run_sync, refresh_ce_data
from generate_reply import generate_email_draft
def clean_html_to_text(html_content):
"""Simple helper to convert HTML email body to readable plain text."""
if not html_content:
return ""
# Remove head and style tags entirely
clean = re.sub(r'<head.*?>.*?</head>', '', html_content, flags=re.DOTALL | re.IGNORECASE)
clean = re.sub(r'<style.*?>.*?</style>', '', clean, flags=re.DOTALL | re.IGNORECASE)
# Replace <br> and </p> with newlines
clean = re.sub(r'<br\s*/?>', '\n', clean, flags=re.IGNORECASE)
clean = re.sub(r'</p>', '\n', clean, flags=re.IGNORECASE)
# Remove all other tags
clean = re.sub(r'<.*?>', '', clean)
# Decode some common entities
clean = clean.replace('&nbsp;', ' ').replace('&amp;', '&').replace('&quot;', '"')
# Cleanup multiple newlines
clean = re.sub(r'\n\s*\n+', '\n\n', clean).strip()
return clean
st.set_page_config(page_title="TradingTwins Lead Engine", layout="wide")
st.title("🚀 Lead Engine: TradingTwins")
@@ -51,6 +71,42 @@ if st.sidebar.button("3. Sync to Company Explorer"):
except Exception as e:
st.error(f"Sync Failed: {e}")
if st.sidebar.checkbox("Show System Debug"):
st.sidebar.subheader("System Diagnostics")
# 1. API Key Check
from lookup_role import get_gemini_key
key = get_gemini_key()
if key:
st.sidebar.success(f"Gemini Key found ({key[:5]}...)")
else:
st.sidebar.error("Gemini Key NOT found!")
# 2. SerpAPI Check
serp_key = os.getenv("SERP_API")
if serp_key:
st.sidebar.success(f"SerpAPI Key found ({serp_key[:5]}...)")
else:
st.sidebar.error("SerpAPI Key NOT found in Env!")
# 3. Network Check
try:
import requests
res = requests.get("https://generativelanguage.googleapis.com", timeout=2)
st.sidebar.success(f"Gemini API Reachable ({res.status_code})")
except Exception as e:
st.sidebar.error(f"Network Error: {e}")
# 4. Live Lookup Test
if st.sidebar.button("Test Role Lookup (Georg Stahl)"):
from lookup_role import lookup_person_role
with st.sidebar.status("Running Lookup..."):
res = lookup_person_role("Georg Stahl", "Klemm Bohrtechnik GmbH")
if res:
st.sidebar.success(f"Result: {res}")
else:
st.sidebar.error("Result: None")
# Main View
leads = get_leads()
df = pd.DataFrame(leads)
@@ -64,7 +120,16 @@ if not df.empty:
st.subheader("Lead Pipeline")
for index, row in df.iterrows():
with st.expander(f"{row['company_name']} ({row['status']})"):
# Format date for title
date_str = ""
if row.get('received_at'):
try:
dt = pd.to_datetime(row['received_at'])
date_str = dt.strftime("%d.%m. %H:%M")
except:
pass
with st.expander(f"{date_str} | {row['company_name']} ({row['status']})"):
c1, c2 = st.columns(2)
# --- Left Column: Lead Data ---
@@ -79,14 +144,30 @@ if not df.empty:
except:
pass
role = meta.get('role')
if role:
c1.info(f"**Role:** {role}")
else:
if c1.button("🔍 Find Role (SerpAPI)", key=f"role_{row['id']}"):
from enrich import enrich_contact_role
with st.spinner("Searching LinkedIn via Google..."):
found_role = enrich_contact_role(row)
if found_role:
st.success(f"Found: {found_role}")
st.rerun()
else:
st.error("No role found.")
if meta:
c1.write("---")
c1.write(f"**Area:** {meta.get('area', '-')}")
c1.write(f"**Purpose:** {meta.get('purpose', '-')}")
c1.write(f"**Location:** {meta.get('zip', '')} {meta.get('city', '')}")
with c1.expander("Show Original Email Body"):
st.code(row['raw_body'], language="html")
with c1.expander("Show Original Email Content"):
st.text(clean_html_to_text(row['raw_body']))
if st.checkbox("Show Raw HTML", key=f"raw_{row['id']}"):
st.code(row['raw_body'], language="html")
# --- Right Column: Enrichment & Response ---
enrichment = json.loads(row['enrichment_data']) if row['enrichment_data'] else {}

22
lead-engine/lookup_role.py
View File

@@ -3,23 +3,15 @@ import requests
import re
from dotenv import load_dotenv
# Load env from root
# 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'))
load_dotenv(dotenv_path=env_path, override=True)
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: Failed to load SERP_API from {env_path}")
# Fallback: try reading directly if file exists
try:
with open(env_path, 'r') as f:
for line in f:
if line.startswith('SERP_API='):
SERP_API_KEY = line.split('=')[1].strip().strip('"')
print("DEBUG: Loaded key via manual parsing.")
except:
pass
print(f"DEBUG: SERP_API not found in environment.")
import json
@@ -75,8 +67,10 @@ def extract_role_with_llm(name, company, search_results):
# Cleanup: remove punctuation at the end
role = role.rstrip('.')
return None if "Unbekannt" in role else role
except:
pass
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):