fabianzarncke's picture
Update app.py
f73601a verified
Raw History Blame
3.06 kB
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 preprocess_user_input(input_text):
# Example: Add a prefix to the user input
processed_text = f"Explain to me what a {input_text} is!"
# system_message = "Ersetze im folgenden Prompt alle wertenden adjektive mit neutraleren synonymen. Hier ist ein Beispiel: Inwiefern ist Gold kaufen geizig? wird zu: Inwiefern ist Gold kaufen ökonomisch?"
system_message = "In the following prompt replace all biased adjectives with neutral synonyms. And only return me the modified prompt. Here is an example: Inhowfar is buying gold stingy? becomes: Inhowfar is buying gold economical?"
finalPrompt = insideRespond(input_text, system_message)
print(finalPrompt)
return finalPrompt
def insideRespond(
message,
system_message,
):
max_tokens = len(message)*2
temperature = 0
messages = [{"role": "system", "content": system_message}]
messages.append({"role": "user", "content": message})
response = client.chat_completion(
messages,
max_tokens=max_tokens,
temperature=temperature,
).choices[0].message.content
return response
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
preprocess_user_input
):
# Preprocess the user input
if preprocess:
message = preprocess_user_input(message)
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.Checkbox(value=True, label="Preprocess User Input"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)",
),
],
)
if __name__ == "__main__":
demo.launch()