Update app.py

app.py

@@ -1,64 +1,63 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
+import torch
+import pandas as pd
+import faiss
+from sentence_transformers import SentenceTransformer
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# Initialize components (automatically cached)
+def load_components():
+    tokenizer = AutoTokenizer.from_pretrained("punitub01/llama2-7b-qlora-finetuned")
+    model = AutoModelForCausalLM.from_pretrained(
+        "punitub01/llama2-7b-qlora-finetuned",
+        device_map="cpu",
+        torch_dtype= torch.float32
+    )
+    encoder = SentenceTransformer('all-MiniLM-L6-v2')
+    index = faiss.read_index("diabetes_abstracts.index")
+    metadata = pd.read_csv("diabetes_metadata.csv")
+    return tokenizer, model, encoder, index, metadata
+
+tokenizer, model, encoder, index, metadata = load_components()
+chat_history = []
+
+def summarize_with_llama(text):
+    prompt = f"""Summarize this medical information in 1-2 lines:
+    {text}
+    Concise summary:"""
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    with torch.no_grad():
+        outputs = model.generate(**inputs, max_new_tokens=100, temperature=0.1)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True).split("Concise summary:")[-1].strip()
+
+def respond(message, history):
+    # Semantic search
+    query_embed = encoder.encode([message])
+    distances, indices = index.search(query_embed, k=3)
+    
+    # Build context
+    references = [
+        f"{metadata.iloc[idx]['title']} (Score: {dist:.2f})" 
+        for idx, dist in zip(indices[0], distances[0]) if dist >= 0.3
+    ]
+    context_summary = summarize_with_llama("\n".join(references)) if references else "No clinical references"
+    
+    # Generate response
+    prompt = f"""Clinical Context: {context_summary}
+    Chat History: {history[-2:] if history else 'None'}
+    Question: {message}
+    Answer:"""
+    
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    with torch.no_grad():
+        outputs = model.generate(**inputs, max_new_tokens=200, temperature=0.7)
+    
+    return tokenizer.decode(outputs[0], skip_special_tokens=True).split("Answer:")[-1].strip()
+
+# Gradio interface
+gr.ChatInterface(
     respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+    title="Diabetes Assistant",
+    description="Ask questions about diabetes management",
+    examples=["What are hypoglycemia symptoms?", "¿Cómo manejar la diabetes tipo 2?"]
+).launch()