Guhanselvam's picture
Update app.py
b2523cd verified
import gradio as gr
from huggingface_hub import InferenceClient
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})
# Check for financial-related keywords
financial_keywords = ["bank", "investment", "financial", "insurance", "savings", "interest", "loan", "mortgage", "credit"]
if any(keyword in message.lower() for keyword in financial_keywords):
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
return response
else:
return "This is a financial FAQ chatbot. Please ask me about banking, investments, insurance, or savings."
# Initialize Gradio Chat Interface
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="You are a friendly financial FAQ Chatbot. Only answer questions about finance.", 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()