Spaces:
Runtime error
Runtime error
File size: 1,812 Bytes
4ac76b6 e6125fa 4ac76b6 b04f829 4ac76b6 b04f829 1855a35 b04f829 e6125fa 1855a35 e6125fa 4ac76b6 e6125fa 4ac76b6 678c780 1855a35 4ac76b6 00f663f |
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 |
import gradio as gr
from db import get_db
from chain import get_chain
import logging
logger = logging.getLogger(__name__)
#logger.info('Instantiating vectordb')
#vectordb = get_db(
# chunk_size=1000,
# chunk_overlap=200,
# model_name = 'intfloat/multilingual-e5-large-instruct',
#)
#logger.info('Instantiating chain')
#chain = get_chain(
# vectordb,
# repo_id="HuggingFaceH4/zephyr-7b-beta",
# task="text-generation",
# max_new_tokens=512,
# top_k=30,
# temperature=0.1,
# repetition_penalty=1.03,
# search_type="mmr",
# k=3,
# fetch_k=5,
# template="""Use the following sentences of context to answer the question at the end.
#If you don't know the answer, that is if the answer is not in the context, then just say that you don't know, don't try to make up an answer.
#Always say "Thanks for asking!" at the end of the answer.
#
#{context}
#
#Question: {question}
#Helpful Answer:"""
#)
def respond(
question,
_, # Ignore the message history parameter since we are doing one-off invocations
system_message,
max_tokens,
temperature,
top_p,
):
print(f'respond called by Gradio ChatInterface with question={question}')
#return chain.invoke({'question': question})
return "hello!"
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.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)",
),
],
)
if __name__ == "__main__":
demo.launch()
|