Update app.py

app.py

@@ -1,64 +1,156 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import uuid
+import json
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-"""
-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")
+# Load the DeepSeek-R1 model
+model = AutoModelForCausalLM.from_pretrained(
+    "deepseek-ai/DeepSeek-R1",
+    trust_remote_code=True,
+)
+tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-R1")
+
+def format_messages_for_model(messages):
+    """
+    Format the conversation history into a single string compatible with the DeepSeek-R1 model.
+    """
+    formatted_messages = ""
+    for msg in messages:
+        if msg["role"] == "user":
+            formatted_messages += f"User: {msg['content']}\n"
+        elif msg["role"] == "assistant":
+            formatted_messages += f"DeepSeek-R1: {msg['content']}\n"
+    return formatted_messages
 
+def generate_response(user_input, history):
+    """
+    Generate a response using DeepSeek-R1 and return it as a string.
+    """
+    formatted_history = format_messages_for_model(history)
+    full_input = f"{formatted_history}User: {user_input}\nDeepSeek-R1: "
 
-def respond(
+    inputs = tokenizer(full_input, return_tensors="np")
+    outputs = model.generate(
+        **inputs,
+        max_length=2048,
+        temperature=0.7,
+        top_p=0.9,
+        do_sample=True,
+        return_dict_in_generate=True,
+    )
+    
+    response = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)
+    return response.split("DeepSeek-R1: ")[-1].strip()
+
+def chatbot(
     message,
     history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    system_message: str,
+    max_tokens: int,
+    temperature: float,
+    top_p: float,
 ):
-    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(
-    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)",
-        ),
-    ],
-)
+    """
+    Main function for generating responses and saving chat history.
+    """
+    # Generate a unique session ID for this chat session
+    session_id = str(uuid.uuid4())
+
+    # Format messages for the model
+    messages = []
+    if system_message:
+        messages.append({"role": "system", "content": system_message})
+    for user_msg, bot_msg in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if bot_msg:
+            messages.append({"role": "assistant", "content": bot_msg})
+
+    # Generate response
+    response = generate_response(message, messages)
+
+    # Add to history
+    history.append((message, response))
+
+    # Save chat history to Hugging Face storage
+    storage = gr.HuggingFace()
+    storage.set(key=session_id, value={"messages": messages + [{"role": "assistant", "content": response}]})
+
+    return response
+
+def create_chat_interface():
+    """
+    Create the Gradio chat interface.
+    """
+    with gr.Blocks() as app:
+        session_id = str(uuid.uuid4())  # Generate session ID at startup
+
+        with gr.Row():
+            chatbot_interface = gr.Chatbot(label="DeepSeek-R1 Chatbot")
+            input_box = gr.Textbox(
+                label="Type your message here",
+                placeholder="Type your message here...",
+                show_label=True,
+            )
+
+        # Button to submit the message
+        submit_button = gr.Button("Send")
+
+        # Store chat history in the interface
+        history = gr.State([])
+
+        # Define the system message
+        system_message = gr.Textbox(
+            value="You are DeepSeek-R1, an AI assistant.",
+            label="System Message",
+            show_label=True,
+            visible=True,
+        )
+
+        # Define inference parameters
+        with gr.Accordion("Parameters", open=True):
+            max_tokens = gr.Slider(
+                minimum=1,
+                maximum=2048,
+                value=512,
+                step=1,
+                label="Max Tokens",
+                info="Maximum length of the generated response.",
+            )
+            temperature = gr.Slider(
+                minimum=0.0,
+                maximum=2.0,
+                value=1.0,
+                step=0.1,
+                label="Temperature",
+                info="Higher values produce more diverse outputs.",
+            )
+            top_p = gr.Slider(
+                minimum=0.1,
+                maximum=1.0,
+                value=0.9,
+                step=0.05,
+                label="Top-p",
+                info="Controls diversity through nucleus sampling.",
+            )
+
+        # Define the submit function
+        submit_button.click(
+            fn=chatbot,
+            inputs=[
+                input_box,
+                history,
+                system_message,
+                max_tokens,
+                temperature,
+                top_p,
+            ],
+            outputs=[gr.Textbox(), chatbot_interface],
+            api_name="chatbot",
+        )
 
+    return app
 
 if __name__ == "__main__":
-    demo.launch()
+    app = create_chat_interface()
+    app.launch()