File size: 2,437 Bytes
79cade0 18d6e67 79cade0 18d6e67 79cade0 18d6e67 79cade0 18d6e67 79cade0 18d6e67 79cade0 18d6e67 79cade0 18d6e67 04ec251 18d6e67 59c1b45 79cade0 b2d2790 9a5dab3 b2d2790 79cade0 fa42334 14dee08 79cade0 d2bcd0b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 |
import gradio as gr
from openai import OpenAI, APIError
import os
import tenacity
ACCESS_TOKEN = os.getenv("HF_TOKEN")
client = OpenAI(
base_url="https://api-inference.huggingface.co/v1/",
api_key=ACCESS_TOKEN,
)
@tenacity.retry(wait=tenacity.wait_exponential(multiplier=1, min=4, max=10))
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
try:
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.completions.create(
model="NousResearch/Hermes-3-Llama-3.1-8B",
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
messages=messages,
):
token = message.choices[0].delta.content
response += token
yield response
except APIError as e:
error_details = e.body
error_type = error_details.get("type")
error_code = error_details.get("code")
error_param = error_details.get("param")
error_message = error_details.get("message")
if error_type:
error_str = f"{error_type}: {error_message} (code: {error_code}, param: {error_param})"
else:
error_str = "An error occurred during streaming"
print(f"Error: {error_str}")
yield error_str
except Exception as e:
print(f"Error: {e}")
yield "Error occurred. Please try again."
chatbot = gr.Chatbot(height=600)
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=2048, 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",
),
],
fill_height=True,
chatbot=chatbot
)
if __name__ == "__main__":
demo.launch(show_error=True) |