Update app.py

app.py

@@ -120,9 +120,11 @@ def stream_response(client, model, messages):
             temperature=0.3,
         )
         for chunk in stream:
-            delta = chunk.choices[0].delta.content
-            if delta:
-                yield delta
+            # FIX: Check if choices exists before accessing [0]
+            if chunk.choices and len(chunk.choices) > 0:
+                delta = chunk.choices[0].delta.content
+                if delta:
+                    yield delta
     except Exception as e:
         # Try fallback model
         if model != FALLBACK_MODEL:
@@ -135,15 +137,16 @@ def stream_response(client, model, messages):
                     temperature=0.3,
                 )
                 for chunk in stream:
-                    delta = chunk.choices[0].delta.content
-                    if delta:
-                        yield delta
+                    # FIX: Check if choices exists before accessing [0]
+                    if chunk.choices and len(chunk.choices) > 0:
+                        delta = chunk.choices[0].delta.content
+                        if delta:
+                            yield delta
                 return
             except Exception:
                 pass
         yield f"\n\n⚠️ Generation error: {e}\n\nTip: Add a HuggingFace token in Settings for better rate limits."
 
-
 # ── Retrieval helpers ─────────────────────────────────────────────────────────
 
 def best_sentence(chunk: str, q_tokens: set) -> tuple: