Update src/streamlit_app.py

src/streamlit_app.py

@@ -695,63 +695,64 @@ with tabs[4]:
                 if not HF_TOKEN:
                     st.error("HF_TOKEN not detected in environment or secrets.toml.")
                 else:
-                    API_URL = "https://router.huggingface.co/hf-inference/v1/chat/completions"
-
+                    #  Correct endpoint per Hugging Face Router API
+                    API_URL = "https://router.huggingface.co/hf-inference/models/meta-llama/Llama-3-8B-Instruct"
+                
                     headers = {
                         "Authorization": f"Bearer {HF_TOKEN}",
-                        "Content-Type": "application/json"
+                        "Content-Type": "application/json",
                     }
                 
-                    # Safer prompt handling
+                    # Prepare prompt
                     prompt = textwrap.dedent(f"""
                         You are an expert metallurgical process advisor.
-                        Analyze these operator recommendations and rewrite them
+                        Analyze these SHAP-based operator recommendations and rewrite them
                         as a concise 3-line professional advisory note.
+                        
                         Recommendations: {recs}
                         Target variable: {target}
                         Use case: {use_case}
                     """)
                 
+                    #  HF Router supports both "inputs" and OpenAI-style "messages"
                     payload = {
-                        "model": "meta-llama/Llama-3-8B-Instruct",
-                        "messages": [
-                            {"role": "system", "content": "You are an expert metallurgical advisor."},
-                            {"role": "user", "content": prompt}
-                        ],
-                        "max_tokens": 200,
-                        "temperature": 0.5
+                        "inputs": prompt,
+                        "parameters": {
+                            "max_new_tokens": 200,
+                            "temperature": 0.5,
+                            "top_p": 0.95,
+                            "return_full_text": False
+                        }
                     }
                 
                     with st.spinner("Generating operator advisory (Llama 3-8B)…"):
                         try:
                             resp = requests.post(API_URL, headers=headers, json=payload, timeout=90)
+                
                             if resp.status_code != 200:
-                                st.warning(f" HF API error {resp.status_code}: {resp.text}")
+                                st.warning(f"HF API error {resp.status_code}: {resp.text}")
                             else:
-                                raw_text = resp.text.strip()
-                                if not raw_text:
-                                    st.warning("Operator advisory skipped: empty HF response body.")
-                                else:
-                                    try:
-                                        data = resp.json()
-                                        # OpenAI-compatible schema
-                                        text = ""
-                                        if "choices" in data and len(data["choices"]) > 0:
-                                            text = data["choices"][0]["message"]["content"].strip()
-                                        elif isinstance(data, list) and "generated_text" in data[0]:
-                                            text = data[0]["generated_text"].strip()
-                                        if text:
-                                            st.success("Operator Advisory Generated:")
-                                            st.info(text)
-                                        else:
-                                            st.warning(f"Operator advisory skipped: could not parse text.\nRaw HF output:\n{raw_text}")
-                                    except Exception:
-                                        st.warning(f"Operator advisory skipped: invalid JSON. Raw response:\n{raw_text}")
+                                try:
+                                    data = resp.json()
+                                    text = ""
+                
+                                    # The router returns list-based structure for text generation
+                                    if isinstance(data, list) and len(data) > 0 and "generated_text" in data[0]:
+                                        text = data[0]["generated_text"].strip()
+                                    elif isinstance(data, dict) and "generated_text" in data:
+                                        text = data["generated_text"].strip()
+                
+                                    if text:
+                                        st.success(" Operator Advisory Generated:")
+                                        st.info(text)
+                                    else:
+                                        st.warning(f"Operator advisory skipped: no text returned.\nRaw response:\n{data}")
+                
+                                except json.JSONDecodeError:
+                                    st.warning(f"Operator advisory skipped: invalid JSON.\nRaw response:\n{resp.text}")
                         except Exception as e:
                             st.warning(f"Operator advisory skipped: {e}")
 
-            except Exception as e:
-                st.warning(f"Operator advisory skipped: {e}")
 
 
 # ----- Business Impact tab