Update app.py

app.py

@@ -1,70 +1,37 @@
 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 transformers import AutoModelForSeq2SeqLM, AutoTokenizer, pipeline
+
+# Load model from Google Drive path
+model_path = "/content/drive/MyDrive/models/flan-t5-small"  # change if needed
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_path)
+
+# Create text generation pipeline
+generator = pipeline("text2text-generation", model=model, tokenizer=tokenizer, device=-1)  # CPU
+
+def answer_question(question):
+    result = generator(
+        question,
+        max_new_tokens=256,
+        do_sample=True,
+        temperature=0.7,
+        repetition_penalty=1.2
+    )
+    return result[0]['generated_text']
+
+# Gradio UI
 with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
+    gr.Markdown("## FPV2 Chatbot")
+    chatbox = gr.Chatbot()
+    question_input = gr.Textbox(label="Ask a question")
+    
+    def respond(question, chat_history):
+        answer = answer_question(question)
+        chat_history.append((question, answer))
+        return chat_history, ""
+    
+    question_input.submit(respond, [question_input, chatbox], [chatbox, question_input])
+
+# Launch with public link enabled
+demo.launch(share=True)
 
-if __name__ == "__main__":
-    demo.launch()