Update app.py

app.py

@@ -1,63 +1,43 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    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)",
-        ),
-    ],
+from langchain import PromptTemplate, LLMChain
+from langchain_huggingface import HuggingFacePipeline, HuggingFaceEndpoint
+from transformers import pipeline
+import os
+from google.colab import userdata
+
+# Authenticate with Hugging Face
+os.environ["HUGGINGFACEHUB_API_TOKEN"] = userdata.get('huggingface')
+
+# Load the LLM
+pipe = pipeline(
+    'text2text-generation',
+    model='google/flan-t5-small',
+    max_length=60,
+    do_sample=True,
+    temperature=0.9
+)
+llm = HuggingFacePipeline(pipeline=pipe)
+
+# Define the prompt template
+prompt_template = """AI assistant. I am always here to help.
+User: {question}
+Assistant:"""
+prompt = PromptTemplate(template=prompt_template, input_variables=["question"])
+
+# Create the LLM chain
+chain = LLMChain(llm=llm, prompt=prompt)
+
+# Define the Gradio function
+def chatbot(question):
+    response = chain.run(question)
+    return response
+
+# Create the Gradio interface
+demo = gr.Interface(
+    fn=chatbot,
+    inputs=gr.inputs.Textbox(lines=2, label="Question"),
+    outputs=gr.outputs.Textbox(label="Answer")
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the interface
+demo.launch()