Update app.py

app.py

@@ -12,15 +12,19 @@ st.title("🧭 Team Career Progression Assistant")
 st.caption("Program Managers • Scrum Masters • People Leads")
 
 # ------------------------------------------------
-# Load Hugging Face Model (FLAN-T5 Small – light & free)
+# Load Hugging Face Model (OFFICIALLY SUPPORTED)
 # ------------------------------------------------
 @st.cache_resource
 def load_hf_model():
+    # This model works 100% with HF Inference API on Spaces
     return InferenceClient("google/gemma-1.1-2b-it")
 
 hf = load_hf_model()
 
-def safe_generate(prompt, tokens=200):
+# ------------------------------------------------
+# Safe text generation wrapper (Gemma-compatible)
+# ------------------------------------------------
+def safe_generate(prompt: str, tokens: int = 200):
     try:
         response = hf.text_generation(
             prompt,
@@ -29,19 +33,55 @@ def safe_generate(prompt, tokens=200):
             do_sample=True
         )
 
-        # Gemma returns {"generated_text": "..."}
+        # Gemma returns a dict: {"generated_text": "...output..."}
         if isinstance(response, dict) and "generated_text" in response:
             return response["generated_text"].strip()
 
-        return str(response).strip()
+        # rare fallback
+        if isinstance(response, str):
+            return response.strip()
+
+        return str(response)
 
     except Exception as e:
         st.warning(f"LLM error: {e}")
         return None
 
+# ------------------------------------------------
+# Next-Level Role (AI)
+# ------------------------------------------------
+def generate_next_role(current_role: str) -> str:
+    prompt = f"""
+Suggest one realistic next-level job title for someone currently working as a {current_role}.
+Return only the job title. Do not explain.
+"""
+    result = safe_generate(prompt, tokens=40)
+    return result if result else "Unable to generate"
 
 # ------------------------------------------------
-# Readiness Score & Recommendations
+# 30-60-90 Day Plan (AI)
+# ------------------------------------------------
+def generate_llm_plan(role: str, next_role: str) -> str:
+    prompt = f"""
+Create a clear, structured 30-60-90 day development plan for someone currently
+in the role {role} who wants to grow into the next-level role: {next_role}.
+
+Use this format:
+
+### 30-Day Goals
+- ...
+
+### 60-Day Goals
+- ...
+
+### 90-Day Goals
+- ...
+"""
+    result = safe_generate(prompt, tokens=350)
+    return result if result else "Unable to generate plan."
+
+# ------------------------------------------------
+# Scoring Logic
 # ------------------------------------------------
 def score(row):
     years = min(row["YearsExperience"], 10) / 10 * 5
@@ -50,10 +90,10 @@ def score(row):
     perf = row["PerformanceRating"]
     leadership = 5 if str(row["LeadershipInterest"]).lower() == "yes" else 2
 
-    score_5 = (0.3 * years + 0.2 * tech + 0.2 * soft + 0.2 * perf + 0.1 * leadership)
+    score_5 = (0.3*years + 0.2*tech + 0.2*soft + 0.2*perf + 0.1*leadership)
     return round(score_5 / 5 * 100, 1)
 
-def suggest_next_role(row):
+def suggest_next_role_rule(row):
     s = row["ReadinessScore"]
     if s >= 80:
         return "Team Lead / Scrum Master"
@@ -71,7 +111,7 @@ def suggest_actions(row):
     return "• " + "\n• ".join(acts)
 
 # ------------------------------------------------
-# Sidebar – Data Input
+# Sidebar File Input
 # ------------------------------------------------
 with st.sidebar:
     st.header("📂 Upload CSV or Use Sample")
@@ -92,15 +132,15 @@ st.subheader("📥 Input Data")
 st.dataframe(df_raw, use_container_width=True)
 
 # ------------------------------------------------
-# Compute Metrics
+# Compute Columns
 # ------------------------------------------------
 df = df_raw.copy()
 df["ReadinessScore"] = df.apply(score, axis=1)
-df["SuggestedNextRole"] = df.apply(suggest_next_role, axis=1)
+df["SuggestedNextRole"] = df.apply(suggest_next_role_rule, axis=1)
 df["RecommendedActions"] = df.apply(suggest_actions, axis=1)
 
 # ------------------------------------------------
-# Team Summary (Table)
+# Summary Table
 # ------------------------------------------------
 st.markdown("## 📊 Team Summary")
 st.dataframe(
@@ -109,25 +149,25 @@ st.dataframe(
 )
 
 # ------------------------------------------------
-# Dashboard (Charts)
+# Dashboard Charts
 # ------------------------------------------------
 st.markdown("---")
 st.markdown("## 📈 Team Dashboard")
 
-col1, col2 = st.columns(2)
+c1, c2 = st.columns(2)
 
-with col1:
+with c1:
     fig = px.bar(df, x="Name", y="ReadinessScore", text="ReadinessScore")
     st.plotly_chart(fig, use_container_width=True)
 
-with col2:
+with c2:
     role_counts = df["SuggestedNextRole"].value_counts().reset_index()
     role_counts.columns = ["Role", "Count"]
     fig2 = px.pie(role_counts, names="Role", values="Count")
     st.plotly_chart(fig2, use_container_width=True)
 
 # ------------------------------------------------
-# Employee-Level Recommendations (BOTTOM SECTION)
+# Employee-Level AI Section (BOTTOM)
 # ------------------------------------------------
 st.markdown("---")
 st.markdown("## 👤 Employee-Level Recommendations & AI Plan")
@@ -137,52 +177,14 @@ emp = df[df["Name"] == selected_name].iloc[0]
 
 st.markdown(f"### {emp['Name']} — {emp['CurrentRole']}")
 
-# Non-AI info
-st.markdown("#### Readiness & Suggested Path")
+st.markdown("#### Readiness & Suggested Path (Rule-Based)")
 st.write(f"**Readiness Score:** {emp['ReadinessScore']} / 100")
-st.write(f"**Suggested Next Role (rule-based):** {emp['SuggestedNextRole']}")
+st.write(f"**Suggested Next Role:** {emp['SuggestedNextRole']}")
 st.markdown("**Recommended Actions:**")
 st.write(emp["RecommendedActions"])
 
-# AI button
+# AI Button
 if st.button("🚀 Generate AI Next Role & 30-60-90 Plan"):
-    # ------------------------------------------------
-    # Next-Level Role (LLM)
-    # ------------------------------------------------
-    def generate_next_role(current_role: str) -> str:
-        prompt = (
-            f"Suggest one realistic next-level job title for someone currently "
-            f"working as a {current_role}. Return only the job title."
-        )
-        result = safe_generate(prompt, tokens=40)
-        if not result or "Error" in result:
-            return "Unable to generate"
-        return result
-    
-    # ------------------------------------------------
-    # 30-60-90 Plan (LLM)
-    # ------------------------------------------------
-    def generate_llm_plan(role: str, next_role: str) -> str:
-        prompt = f"""
-    Create a clear, structured 30-60-90 day development plan for someone currently
-    working as a {role} who wants to grow into the next-level role: {next_role}.
-    
-    Follow this format:
-    
-    ### 30-Day Goals
-    - ...
-    
-    ### 60-Day Goals
-    - ...
-    
-    ### 90-Day Goals
-    - ...
-    """
-        result = safe_generate(prompt, tokens=350)
-        if not result or "Error" in result:
-            return "Unable to generate plan."
-        return result
-    
     with st.spinner("Generating AI recommendations for this employee..."):
         next_role_ai = generate_next_role(emp["CurrentRole"])
         plan_ai = generate_llm_plan(emp["CurrentRole"], next_role_ai)
@@ -194,7 +196,7 @@ if st.button("🚀 Generate AI Next Role & 30-60-90 Plan"):
     st.write(plan_ai)
 
 # ------------------------------------------------
-# Download Results
+# Download CSV
 # ------------------------------------------------
 buf = StringIO()
 df.to_csv(buf, index=False)