Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,6 @@
+FROM python:3.9-slim
+WORKDIR /app
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+COPY . .
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

ai_engine.py

@@ -0,0 +1,38 @@
+import google.generativeai as genai
+import os
+import json
+
+# Configure the Gemini API
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+
+# Initialize the model (Flash is the free, fast model)
+model = genai.GenerativeModel(
+    model_name='gemini-1.5-flash',
+    generation_config={"response_mime_type": "application/json"} # Forces perfect JSON!
+)
+
+def analyze_lead(name: str, company: str, company_summary: str) -> dict:
+    prompt = f"""
+    You are a B2B sales expert. Analyze this lead.
+    Lead: {name} at {company}. Info: {company_summary}
+    
+    Return ONLY this JSON structure:
+    {{
+      "score": <integer 1-10>,
+      "score_reason": "<one sentence why this score>",
+      "cold_email": "<a 100-word personalized cold email pitching AI automation services. Start with Hi {name},. End by asking for a 10-min chat.>"
+    }}
+    """
+    
+    try:
+        response = model.generate_content(prompt)
+        # Because we forced JSON mime type, this is 100% safe to parse
+        return json.loads(response.text)
+        
+    except Exception as e:
+        # Fallback if something goes wrong
+        return {
+            "score": 0, 
+            "score_reason": f"AI Error: {str(e)}", 
+            "cold_email": "Error generating email."
+        }

database.py

@@ -0,0 +1,13 @@
+from supabase import create_client
+import os
+
+supabase = create_client(os.getenv("SUPABASE_URL", ""), os.getenv("SUPABASE_KEY", ""))
+
+def save_lead(data: dict):
+    return supabase.table("leads").insert(data).execute()
+
+def get_pending_leads():
+    return supabase.table("leads").select("*").eq("status", "pending").execute().data
+
+def update_lead_status(lead_id: int, status: str):
+    return supabase.table("leads").update({"status": status}).eq("id", lead_id).execute()

main.py

@@ -0,0 +1,56 @@
+from fastapi import FastAPI, UploadFile, File
+from fastapi.middleware.cors import CORSMiddleware
+from dotenv import load_dotenv
+import pandas as pd
+import io
+import os
+
+from scraper import scrape_company
+from ai_engine import analyze_lead
+from database import save_lead, get_pending_leads, update_lead_status
+
+load_dotenv()
+
+app = FastAPI()
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"], # Allow all origins for Vercel integration
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+@app.post("/process-csv")
+async def process_csv(file: UploadFile = File(...)):
+    contents = await file.read()
+    df = pd.read_csv(io.BytesIO(contents))
+    
+    for _, row in df.iterrows():
+        summary = scrape_company(row["url"])
+        result = analyze_lead(row["name"], row["company"], summary)
+        
+        save_lead({
+            "name": row["name"], 
+            "company": row["company"], 
+            "url": row["url"],
+            "email": row.get("email", ""), 
+            "company_summary": summary,
+            "score": result["score"], 
+            "score_reason": result["score_reason"],
+            "cold_email": result["cold_email"]
+        })
+    return {"status": "success"}
+
+@app.get("/get-leads")
+def fetch_leads():
+    return get_pending_leads()
+
+@app.post("/update-lead/{lead_id}")
+def update_lead(lead_id: int, status: str = "approved"):
+    update_lead_status(lead_id, status)
+    return {"status": "updated"}
+
+@app.get("/")
+def read_root():
+    return {"message": "Lead Qualifier API is running!"}

requirements.txt

@@ -0,0 +1,8 @@
+fastapi
+uvicorn
+google-generativeai
+supabase
+requests
+python-dotenv
+python-multipart
+pandas

scraper.py

@@ -0,0 +1,9 @@
+import requests
+
+def scrape_company(url: str) -> str:
+    try:
+        # Using Jina AI reader to bypass JS blocking and get clean markdown
+        res = requests.get(f"https://r.jina.ai/{url}", timeout=15)
+        return res.text[:800] if res.status_code == 200 else "No description found."
+    except Exception as e:
+        return f"Scraping error: {str(e)}"