Update app.py

app.py

@@ -1,50 +1,49 @@
 import os
-import requests
-from llama_cpp import Llama
 import streamlit as st
+from llama_cpp import Llama
+from huggingface_hub import hf_hub_download
 
-MODEL_URL = "https://huggingface.co/MaziyarPanahi/BioMistral-7B-GGUF/resolve/main/BioMistral-7B.Q4_K_M.gguf"
-MODEL_PATH = "BioMistral-7B.Q4_K_M.gguf"
+# Hugging Face repo and model info
+REPO_ID = "MaziyarPanahi/BioMistral-7B-GGUF"
+MODEL_FILENAME = "BioMistral-7B.Q4_K_M.gguf"
 
-# Streamlit app title
+# Streamlit UI
 st.set_page_config(page_title="Medical Chatbot")
 st.title("🩺 Medical Chatbot using BioMistral-7B")
 
-# Download model manually if not present
-def download_model():
-    with st.spinner("🔄 Downloading model... please wait (few minutes)..."):
-        response = requests.get(MODEL_URL, stream=True)
-        if response.status_code == 200:
-            with open(MODEL_PATH, "wb") as f:
-                for chunk in response.iter_content(chunk_size=8192):
-                    if chunk:
-                        f.write(chunk)
-        else:
-            st.error(f"Failed to download model. Status: {response.status_code}")
-            st.stop()
-
-# Check and download
-if not os.path.exists(MODEL_PATH):
-    download_model()
-
-# Verify model exists
-if not os.path.exists(MODEL_PATH):
-    st.error("❌ Model file missing after download. Exiting.")
-    st.stop()
+# Download model via huggingface_hub
+with st.spinner("🔄 Checking/downloading model (this may take a few minutes)..."):
+    try:
+        model_path = hf_hub_download(
+            repo_id=REPO_ID,
+            filename=MODEL_FILENAME,
+            cache_dir="models"  # Optional: use your preferred directory
+        )
+    except Exception as e:
+        st.error(f"❌ Failed to download model: {e}")
+        st.stop()
 
 # Load model
 with st.spinner("⚙️ Loading BioMistral model..."):
-    llm = Llama(
-        model_path=MODEL_PATH,
-        n_ctx=4096,
-        n_threads=8,
-        n_gpu_layers=35  # Use 0 for CPU-only
-    )
+    try:
+        llm = Llama(
+            model_path=model_path,
+            n_ctx=4096,
+            n_threads=8,
+            n_gpu_layers=35  # Set to 0 for CPU
+        )
+    except Exception as e:
+        st.error(f"❌ Failed to load model: {e}")
+        st.stop()
 
-# UI
-query = st.text_input("💬 Enter your medical question:")
+# Chat UI
+query = st.text_input("💬 Ask a medical question:")
 if query:
-    with st.spinner("🧠 Thinking..."):
-        response = llm(query, max_tokens=512, stop=["</s>"])
-        st.markdown("**Answer:**")
-        st.write(response["choices"][0]["text"].strip())
+    with st.spinner("🧠 Generating answer..."):
+        try:
+            response = llm(query, max_tokens=512, stop=["</s>"])
+            answer = response["choices"][0]["text"].strip()
+            st.markdown("**🩺 Answer:**")
+            st.write(answer)
+        except Exception as e:
+            st.error(f"⚠️ Error generating response: {e}")