File size: 2,067 Bytes
b2427ab 58c81e4 80a09fa b2427ab 58c81e4 b2427ab 58c81e4 b2427ab 58c81e4 b2427ab 58c81e4 b2427ab 58c81e4 b2427ab 58c81e4 bdf0a45 58c81e4 b2427ab 58c81e4 b2427ab 58c81e4 8af0ee8 b2427ab 58c81e4 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
import os
from rag import local_retriever, global_retriever
from transformers import LlamaTokenizer
"""
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,
search_strategy,
top_p,
):
if search_strategy == "Global":
return global_retriever(message, 2, "multiple paragraphs")
else:
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=6192,
stream=True,
temperature=1.0,
top_p=top_p,
):
token = message.choices[0].delta.content
response += token
return 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 medical assistant Chatbot. For any query that you don't know, you will say 'I don't know'. You will answer with the given information:",
label="System message",
),
gr.Dropdown(
choices=["Local", "Global"], value="Local", label="Select search strategy"
),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)",
),
],
)
if __name__ == "__main__":
demo.launch()
|