updated app.py

app.py

@@ -1,63 +1,123 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+import os
+from huggingface_hub import login
+from transformers import AutoModelForSeq2SeqLM, T5Tokenizer
+from peft import PeftModel, PeftConfig
 
-"""
-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")
+token = os.environ.get("token")
+login(token)
+print("login is succesful")
+max_length=512
 
+MODEL_NAME = "google/flan-t5-base"
+tokenizer = T5Tokenizer.from_pretrained(MODEL_NAME, token=token)
+config = PeftConfig.from_pretrained("Orcawise/results")
+base_model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-base")
+model = PeftModel.from_pretrained(base_model, "Orcawise/results")
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+#gr.Interface.from_pipeline(pipe).launch()
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+def generate_text(prompt, max_length=512):
+    """Generates text using the PEFT model.
+    Args:
+        prompt (str): The user-provided prompt to start the generation.
+           Returns:
+        str: The generated text.
+    """
 
-    messages.append({"role": "user", "content": message})
 
-    response = ""
+    # Preprocess the prompt
+    # inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+    inputs = tokenizer(prompt, return_tensors="pt")
 
-    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
+    # Generate text using beam search
+    outputs = model.generate(
+       input_ids = inputs["input_ids"], 
+       max_length=max_length, 
+       num_beams=1
+       
+       )
 
-        response += token
-        yield response
+    # Decode the generated tokens
+    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    print("show the generated text", generated_text)
+    return generated_text
 
+#############
+custom_css="""
+.message.pending {
+    background: #A8C4D6;
+}
+/* Response message */
+.message.bot.svelte-1s78gfg.message-bubble-border {
+    /* background:  white; */
+    border-color: #266B99
+}
+/* User message */
+.message.user.svelte-1s78gfg.message-bubble-border{
+    background: #9DDDF9;
+    border-color: #9DDDF9
+    
+}   
+/* For both user and response message as per the document */
+span.md.svelte-8tpqd2.chatbot.prose p {
+    color: #266B99; 
+}
+/* Chatbot comtainer */
+.gradio-container{
+    /* background:  #84D5F7 */
+}
+/* RED (Hex: #DB1616) for action buttons and links only */
+.clear-btn {
+  background: #DB1616;
+  color: white;
+}
+/* #84D5F7 - Primary colours are set to be used for all sorts */
+.submit-btn {
+  background: #266B99; 
+  color: white;
+}
 """
-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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+
+### working correctly but  the welcoming message isnt rendering
+with gr.Blocks(css=custom_css) as demo:
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(placeholder="Ask your question...")  # Add placeholder text
+    submit_button = gr.Button("Submit", elem_classes="submit-btn")
+    clear = gr.Button("Clear", elem_classes="clear-btn")
+
+
+    def user(user_message, history):
+        return "", history + [[user_message, None]]
+
+
+    def bot(history):
+      history[-1][1] = ""  # Update the last bot message (welcome message or response)
+      if len(history) < 0:  # Check if it's the first interaction
+          bot_message = "Hi there! How can I help you today?"
+          history.append([None, bot_message])  # Add welcome message to history
+          for character in bot_message:
+            history[-1][1] += character
+            yield history  # Yield the updated history character by character
+
+      else:
+          previous_message = history[-1][0]  # Access the previous user message
+          bot_message = generate_text(previous_message)  # Generate response based on previous message
+          for character in bot_message:
+            history[-1][1] += character
+            yield history  # Yield the updated history character by character
+
+
+
+    # Connect submit button to user and then bot functions
+    submit_button.click(user, [msg,  chatbot], [msg, chatbot], queue=False).then(
+        bot, chatbot, chatbot
+    )
+
+    # Trigger user function on Enter key press (same chain as submit button)
+    msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(
+        bot, chatbot, chatbot
+    )
+
+    clear.click(lambda: None, None, chatbot, queue=False)
+
+demo.launch()