Create app.py

app.py

@@ -0,0 +1,119 @@
+import streamlit as st
+import requests
+import pandas as pd
+import json
+
+# ----------------------------
+# CONFIG
+# ----------------------------
+st.set_page_config(page_title="Startup Candidate Dashboard", layout="wide")
+
+JSON_URL = "https://file.notion.so/f/f/f86ed84d-b33c-4dfb-b0e0-97c5661516a3/3ed586a1-78e7-46af-9cf1-0961f95b5109/form-submissions-1.json?table=block&id=18a5392c-c93e-8054-b617-eb2a1a213d6c&spaceId=f86ed84d-b33c-4dfb-b0e0-97c5661516a3&expirationTimestamp=1758932214635&signature=sq1Jw2w3WoKIVMc8X078LO4SbfViD9ppdO0VXZ72Nro&downloadName=form-submissions.json"
+
+MODEL_ID = "HuggingFaceH4/zephyr-7b-beta"
+HF_API_TOKEN = st.secrets.get("HF_API_TOKEN")  # store your Hugging Face token in Space Secrets
+
+# ----------------------------
+# CATEGORIES DEFINED BY JOB TITLES
+# ----------------------------
+CATEGORIES = {
+    "AI": [
+        "AI/ML Ops Engineer","Senior Machine Learning Engineer","Principal Data Scientist",
+        "Senior Data Scientist","Machine Learning Research Scientist","Senior AI/ML Engineer",
+        "AI/ML Engineer","Big Data Engineer","AI Research Scientist","AI Research Analyst Consultant",
+        "AI Analyst","Senior Data Analyst","Automation Engineer","Senior Data Engineer",
+        "Machine Learning Engineer","Data Engineer","Data Scientist","Data Analyst"
+    ],
+    "Marketing": [
+        "Marketing Specialist","Sales Agent","Salesman","Sales Associate"
+    ],
+    "CTO": [
+        "Chief Technology Officer","CTO"
+    ],
+    "Legal": [
+        "Legal Specialist","Attorney","Legal Intern","Lawyer"
+    ],
+    "Finance": [
+        "Financial Analyst","Financial Advisor"
+    ]
+}
+
+# ----------------------------
+# HELPER FUNCTIONS
+# ----------------------------
+def fetch_json(url):
+    resp = requests.get(url)
+    resp.raise_for_status()
+    return resp.json()
+
+def call_zephyr(prompt):
+    headers = {
+        "Authorization": f"Bearer {HF_API_TOKEN}",
+        "Content-Type": "application/json"
+    }
+    payload = {"inputs": prompt}
+    response = requests.post(
+        f"https://api-inference.huggingface.co/models/{MODEL_ID}",
+        headers=headers,
+        data=json.dumps(payload),
+        timeout=60
+    )
+    if response.status_code != 200:
+        st.error(f"Zephyr API error: {response.text}")
+        return None
+    result = response.json()
+    if isinstance(result, dict) and "error" in result:
+        st.error(result["error"])
+        return None
+    return result[0].get("generated_text", "")
+
+def get_candidates_by_category(data, category_name, job_titles):
+    candidates = []
+    for person in data:
+        work_exps = person.get("work_experiences", [])
+        if len(work_exps) == 0:
+            continue  # skip no experience
+        if any("full stack developer" in exp.get("roleName","").lower() for exp in work_exps):
+            continue  # skip full stack
+
+        # Prepare prompt: ask Zephyr if this candidate matches any of the predefined job titles
+        prompt = f"""
+You are an HR assistant. Determine if the following candidate is suitable for the category '{category_name}'.
+The category is defined by the job titles: {job_titles}
+
+Candidate JSON: {json.dumps(person)}
+
+Respond only 'Yes' or 'No'.
+"""
+        try:
+            llm_response = call_zephyr(prompt)
+            if llm_response and "Yes" in llm_response:
+                candidates.append({
+                    "Name": person.get("name"),
+                    "Email": person.get("email"),
+                    "Phone": person.get("phone"),
+                    "Location": person.get("location"),
+                    "Roles": ", ".join([exp.get("roleName") for exp in work_exps]),
+                    "Skills": ", ".join(person.get("skills", [])),
+                    "Salary": person.get("annual_salary_expectation", {}).get("full-time", "N/A")
+                })
+        except Exception as e:
+            st.warning(f"Error processing {person.get('name')}: {e}")
+    return pd.DataFrame(candidates)
+
+# ----------------------------
+# MAIN
+# ----------------------------
+st.title("🚀 Startup Candidate Dashboard - Zephyr LLM")
+
+st.markdown("Fetching candidate data from Notion...")
+data = fetch_json(JSON_URL)
+st.success(f"✅ Loaded {len(data)} submissions!")
+
+for category_name, job_titles in CATEGORIES.items():
+    st.subheader(f"{category_name} Suitable Candidates")
+    df = get_candidates_by_category(data, category_name, job_titles)
+    if df.empty:
+        st.write("No suitable candidates found.")
+    else:
+        st.dataframe(df)