Update app.py

app.py

@@ -1,70 +1,46 @@
 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)",
-        ),
-    ],
+import os
+from langchain_groq import ChatGroq
+from langchain_core.messages import HumanMessage, AIMessage, SystemMessage
+
+# 1. Initialize the Chat Model
+# We use the specific Groq integration as described in LangChain's provider docs
+llm = ChatGroq(
+    groq_api_key=os.environ.get("GROQ_API"),
+    model_name="llama-3.3-70b-versatile",
+    temperature=0.7
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
+# 2. Define the Chat Function
+def chat_function(message, history):
+    # The docs recommend using a list of specific message types
+    conversation_messages = []
+    
+    # Add a System Message to define behavior
+    conversation_messages.append(SystemMessage(content="You are a helpful assistant."))
+    
+    # Reconstruct history from Gradio's list
+    for user_text, ai_text in history:
+        if user_text:
+            conversation_messages.append(HumanMessage(content=user_text))
+        if ai_text:
+            conversation_messages.append(AIMessage(content=ai_text))
+            
+    # Add the user's latest message
+    conversation_messages.append(HumanMessage(content=message))
+    
+    # Invoke the model with the full list
+    response = llm.invoke(conversation_messages)
+    
+    # Return the text content of the response
+    return response.content
+
+# 3. Launch the Interface
+demo = gr.ChatInterface(
+    fn=chat_function,
+    title="🤖 Groq Chatbot",
+    description="A simple chatbot using LangChain's message history structures."
+)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()