Update app.py

app.py

@@ -1,70 +1,65 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
+from langchain.llms import HuggingFacePipeline
+from langchain.prompts import PromptTemplate
+from langchain.chains import LLMChain
 
+# -------------------------
+# Load Model (CPU Friendly)
+# -------------------------
+MODEL_NAME = "google/flan-t5-base"
 
-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")
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME)
 
-    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
+hf_pipeline = pipeline(
+    "text2text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_length=512,
+    temperature=0.3
+)
 
-        response += token
-        yield response
+llm = HuggingFacePipeline(pipeline=hf_pipeline)
 
+# -------------------------
+# Prompt Template
+# -------------------------
+prompt = PromptTemplate(
+    input_variables=["question"],
+    template="""
+You are an intelligent AI assistant.
+Answer the question clearly and concisely.
 
+Question: {question}
+Answer:
 """
-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)",
-        ),
-    ],
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+chain = LLMChain(llm=llm, prompt=prompt)
 
+# -------------------------
+# Chat Function
+# -------------------------
+def chat_fn(user_input):
+    if not user_input.strip():
+        return "Please enter a question."
+    response = chain.run(user_input)
+    return response
+
+# -------------------------
+# Gradio Interface
+# -------------------------
+interface = gr.Interface(
+    fn=chat_fn,
+    inputs=gr.Textbox(
+        lines=2,
+        placeholder="Ask something...",
+        label="User Question"
+    ),
+    outputs=gr.Textbox(label="AI Response"),
+    title="LangChain + Hugging Face Chatbot",
+    description="A CPU-based chatbot built with LangChain and Hugging Face Transformers.",
+)
 
-if __name__ == "__main__":
-    demo.launch()
+interface.launch()