Upload app.py with huggingface_hub

app.py

@@ -1,70 +1,34 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+from langchain.chat_models import ChatOpenAI
+from langchain import LLMChain, PromptTemplate
+from langchain.memory import ConversationBufferMemory
 
+OPENAI_API_KEY=os.getenv('OPENAI_API_KEY')
 
-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")
+template = """You are a helpful assistant to answer all user queries.
+{chat_history}
+User: {user_message}
+Chatbot:"""
 
-    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
+prompt = PromptTemplate(
+    input_variables=["chat_history", "user_message"], template=template
+)
 
+memory = ConversationBufferMemory(memory_key="chat_history")
 
-"""
-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)",
-        ),
-    ],
+llm_chain = LLMChain(
+    llm=ChatOpenAI(temperature='0.5', model_name="gpt-3.5-turbo"),
+    prompt=prompt,
+    verbose=True,
+    memory=memory,
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+def get_text_response(user_message,history):
+    response = llm_chain.predict(user_message = user_message)
+    return response
 
+demo = gr.ChatInterface(get_text_response)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch() #To create a public link, set `share=True` in `launch()`. To enable errors and logs, set `debug=True` in `launch()`.