Update app.py

app.py

@@ -1,70 +1,50 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-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")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    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,
-    ):
-        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,
-    type="messages",
-    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)",
-        ),
-    ],
+from typing import TypedDict, Annotated
+from langgraph.graph.message import add_messages
+from langchain_core.messages import AnyMessage, HumanMessage, AIMessage
+from langgraph.prebuilt import ToolNode
+from langgraph.graph import START, StateGraph
+from langgraph.prebuilt import tools_condition
+from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
+
+# Generate the chat interface, including the tools
+llm = HuggingFaceEndpoint(
+    repo_id="Qwen/Qwen2.5-Coder-32B-Instruct",
+    huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN,
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+chat = ChatHuggingFace(llm=llm, verbose=True)
+tools = [guest_info_tool]
+chat_with_tools = chat.bind_tools(tools)
+
+# Generate the AgentState and Agent graph
+class AgentState(TypedDict):
+    messages: Annotated[list[AnyMessage], add_messages]
+
+def assistant(state: AgentState):
+    return {
+        "messages": [chat_with_tools.invoke(state["messages"])],
+    }
+
+## The graph
+builder = StateGraph(AgentState)
+
+# Define nodes: these do the work
+builder.add_node("assistant", assistant)
+builder.add_node("tools", ToolNode(tools))
+
+# Define edges: these determine how the control flow moves
+builder.add_edge(START, "assistant")
+builder.add_conditional_edges(
+    "assistant",
+    # If the latest message requires a tool, route to tools
+    # Otherwise, provide a direct response
+    tools_condition,
+)
+builder.add_edge("tools", "assistant")
+alfred = builder.compile()
 
+messages = [HumanMessage(content="Tell me about our guest named 'Lady Ada Lovelace'.")]
+response = alfred.invoke({"messages": messages})
 
-if __name__ == "__main__":
-    demo.launch()
+print("🎩 Alfred's Response:")
+print(response['messages'][-1].content)