Update app.py

app.py

@@ -1,69 +1,97 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers.utils import get_json_schema
+import torch
 
+# -----------------------
+# Load model
+# -----------------------
+model_name = "bhaiyahnsingh45/functiongemma-multiagent-router"
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    device_map="auto",
+    torch_dtype="auto"
+)
+
+# -----------------------
+# Agents
+# -----------------------
+def technical_support_agent(issue_type: str, priority: str) -> str:
+    return f"🛠️ Routing to Technical Support: {issue_type} ({priority})"
+
+def billing_agent(request_type: str, urgency: str) -> str:
+    return f"💰 Routing to Billing: {request_type} ({urgency})"
+
+def product_info_agent(query_type: str, category: str) -> str:
+    return f"📦 Routing to Product Info: {query_type} ({category})"
 
-    messages = [{"role": "system", "content": system_message}]
+# Tool schemas
+AGENT_TOOLS = [
+    get_json_schema(technical_support_agent),
+    get_json_schema(billing_agent),
+    get_json_schema(product_info_agent)
+]
 
-    messages.extend(history)
+SYSTEM_MSG = "You are an intelligent routing agent that directs customer queries to the appropriate specialized agent."
 
-    messages.append({"role": "user", "content": message})
+# -----------------------
+# Core inference
+# -----------------------
+def route_query(user_query: str):
 
-    response = ""
+    messages = [
+        {"role": "developer", "content": SYSTEM_MSG},
+        {"role": "user", "content": user_query}
+    ]
 
-    for message in client.chat_completion(
+    inputs = tokenizer.apply_chat_template(
         messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = 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
-"""
-chatbot = 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)",
-        ),
-    ],
-)
+        tools=AGENT_TOOLS,
+        add_generation_prompt=True,
+        return_dict=True,
+        return_tensors="pt"
+    )
+
+    inputs = {k: v.to(model.device) for k, v in inputs.items()}
+
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=128,
+        pad_token_id=tokenizer.eos_token_id
+    )
 
+    result = tokenizer.decode(
+        outputs[0][len(inputs["input_ids"][0]):],
+        skip_special_tokens=True
+    )
+
+    return result
+
+
+# -----------------------
+# Chatbot logic
+# -----------------------
+def chat_fn(message, history):
+    response = route_query(message)
+    history.append((message, response))
+    return history, history
+
+
+# -----------------------
+# UI
+# -----------------------
 with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+    gr.Markdown("## 🤖 Multi-Agent Router Chatbot")
+    gr.Markdown("Ask anything about billing, product, or technical issues.")
+
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(placeholder="Type your query here...")
+    clear = gr.Button("Clear")
 
+    msg.submit(chat_fn, [msg, chatbot], [chatbot, chatbot])
+    clear.click(lambda: None, None, chatbot, queue=False)
 
-if __name__ == "__main__":
-    demo.launch()
+# Launch
+demo.launch()