Spaces:
Sleeping
Sleeping
File size: 2,546 Bytes
210dbcf 1a39e80 210dbcf 3543ab2 0147a25 210dbcf 00483df 2517fcf b5e592d 4ce42df 00483df d9888b5 210dbcf 3543ab2 210dbcf 745d465 0147a25 5f188cd 210dbcf 3543ab2 210dbcf 745d465 210dbcf 233c0df 745d465 0147a25 210dbcf 0147a25 210dbcf 745d465 210dbcf 745d465 |
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 |
import gradio as gr
from langchain.prompts import PromptTemplate
from langchain_huggingface import HuggingFaceEndpoint
from langchain_core.output_parsers import JsonOutputParser
from langdetect import detect
import time
# Initialize the LLM and other components
llm = HuggingFaceEndpoint(
repo_id="mistralai/Mistral-7B-Instruct-v0.3",
task="text-generation",
max_new_tokens=128,
temperature=0.7,
do_sample=False,
)
template_classify = '''
You are a topic detector bot. Your task is to determine the main topic of given text phrase.
Answer general main topic not specific words.
Your answer does not contain specific information from given text.
Answer just one general main topic. Do not answer two or more topic.
Answer shortly with two or three word phrase. Do not answer with long sentence.
Answer topic with context. Example, if it says "My delivery is late", its topic is late delivery.
If you do not know the topic just answer as General.
What is the main topic of given text?:
<text>
{TEXT}
</text>
convert it to json format using 'Answer' as key and return it.
Your final response MUST contain only the response, no other text.
Example:
{{"Answer":["General"]}}
'''
json_output_parser = JsonOutputParser()
# Define the classify_text function
def classify_text(text):
global llm
start = time.time()
try:
lang = detect(text)
except:
lang = "en"
prompt_classify = PromptTemplate(
template=template_classify,
input_variables=["LANG", "TEXT"]
)
formatted_prompt = prompt_classify.format(TEXT=text, LANG=lang)
classify = llm.invoke(formatted_prompt)
parsed_output = json_output_parser.parse(classify)
end = time.time()
duration = end - start
return lang, parsed_output["Answer"][0], duration #['Answer']
# Create the Gradio interface
def create_gradio_interface():
with gr.Blocks() as iface:
text_input = gr.Textbox(label="Text")
lang_output = gr.Textbox(label="Detected Language")
output_text = gr.Textbox(label="Detected Topics")
time_taken = gr.Textbox(label="Time Taken (seconds)")
submit_btn = gr.Button("Detect topic")
def on_submit(text):
lang, classification, duration = classify_text(text)
return lang, classification, f"Time taken: {duration:.2f} seconds"
submit_btn.click(fn=on_submit, inputs=text_input, outputs=[lang_output, output_text, time_taken])
iface.launch()
if __name__ == "__main__":
create_gradio_interface() |