Update src/streamlit_app.py

src/streamlit_app.py

@@ -2,12 +2,12 @@ import os
 import pandas as pd
 import numpy as np
 import streamlit as st
-import plotly.express as px
-import plotly.figure_factory as ff
 from dotenv import load_dotenv
 from huggingface_hub import InferenceClient, login
 import google.generativeai as genai
 from io import StringIO
+import time
+import requests
 
 # ======================================================
 # ⚙️ APP CONFIGURATION
@@ -70,25 +70,36 @@ if ANALYST_MODEL != "Gemini 2.5 Flash (Google)":
 # ======================================================
 # 🧩 SAFE GENERATION FUNCTION
 # ======================================================
-def safe_hf_generate(client, prompt, temperature=0.3, max_tokens=512):
-    try:
-        resp = client.text_generation(
-            prompt,
-            temperature=temperature,
-            max_new_tokens=max_tokens,
-            return_full_text=False,
-        )
-        return resp.strip()
-    except Exception as e:
-        if "Supported task: conversational" in str(e):
-            chat_resp = client.chat_completion(
-                messages=[{"role": "user", "content": prompt}],
-                max_tokens=max_tokens,
+def safe_hf_generate(client, prompt, temperature=0.3, max_tokens=512, retries=2):
+    """Try text generation, with retry + fallback on service errors."""
+    for attempt in range(retries + 1):
+        try:
+            resp = client.text_generation(
+                prompt,
                 temperature=temperature,
+                max_new_tokens=max_tokens,
+                return_full_text=False,
             )
-            return chat_resp["choices"][0]["message"]["content"].strip()
-        else:
-            raise e
+            return resp.strip()
+        except Exception as e:
+            err = str(e)
+            # 🩹 FIX: Handle common server overloads gracefully
+            if "503" in err or "Service Temporarily Unavailable" in err:
+                time.sleep(2)
+                if attempt < retries:
+                    continue  # retry
+                else:
+                    return "⚠️ The Hugging Face model is temporarily unavailable. Please try again or switch to Gemini."
+            elif "Supported task: conversational" in err:
+                chat_resp = client.chat_completion(
+                    messages=[{"role": "user", "content": prompt}],
+                    max_tokens=max_tokens,
+                    temperature=temperature,
+                )
+                return chat_resp["choices"][0]["message"]["content"].strip()
+            else:
+                raise e
+    return "⚠️ Failed after retries."
 
 # ======================================================
 # 🧩 DATA CLEANING
@@ -183,8 +194,18 @@ Respond with:
             )
             return response.text if hasattr(response, "text") else "No valid text response."
         else:
-            return safe_hf_generate(hf_analyst_client, prompt, temperature=temperature, max_tokens=max_tokens)
+            # 🩹 FIX: wrap in retry-aware generator
+            result = safe_hf_generate(hf_analyst_client, prompt, temperature=temperature, max_tokens=max_tokens)
+            # fallback to Gemini if Hugging Face failed entirely
+            if "temporarily unavailable" in result.lower() and GEMINI_API_KEY:
+                alt = genai.GenerativeModel("gemini-2.5-flash").generate_content(prompt)
+                return f"🔄 Fallback to Gemini:\n\n{alt.text}"
+            return result
     except Exception as e:
+        # 🩹 FIX: fallback if server rejects or 5xx
+        if "503" in str(e) and GEMINI_API_KEY:
+            response = genai.GenerativeModel("gemini-2.5-flash").generate_content(prompt)
+            return f"🔄 Fallback to Gemini due to 503 error:\n\n{response.text}"
         return f"⚠️ Analysis failed: {str(e)}"
 
 # ======================================================