File size: 2,054 Bytes
4c58071 |
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 |
'''Functions to summarize article content.'''
import os
import logging
from openai import OpenAI
def summarize_content(content: str) -> str:
'''Generates summary of article content using Modal inference endpoint.
Args:
content: string containing the text content to be summarized
Returns:
Summarized text as string
'''
logger = logging.getLogger(__name__ + '.summarize_content')
logger.info('Summarizing extracted content')
client = OpenAI(api_key=os.environ['MODAL_API_KEY'])
client.base_url = (
'https://gperdrizet--vllm-openai-compatible-summarization-serve.modal.run/v1'
)
# Default to first avalible model
model = client.models.list().data[0]
model_id = model.id
# messages = [
# {
# 'role': 'system',
# 'content': ('You are a research assistant, skilled in summarizing documents in just '+
# 'a few sentences. Your document summaries should be a maximum of 2 to 4 sentences long.'),
# 'role': 'user',
# 'content': content
# }
# ]
messages = [
{
'role': 'system',
'content': f'Summarize the following text in 50 words returning only the summary: {content}'
}
]
completion_args = {
'model': model_id,
'messages': messages,
# "frequency_penalty": args.frequency_penalty,
# "max_tokens": 128,
# "n": args.n,
# "presence_penalty": args.presence_penalty,
# "seed": args.seed,
# "stop": args.stop,
# "stream": args.stream,
# "temperature": args.temperature,
# "top_p": args.top_p,
}
try:
response = client.chat.completions.create(**completion_args)
except Exception as e: # pylint: disable=broad-exception-caught
response = None
logger.error('Error during Modal API call: %s', e)
if response is not None:
return response.choices[0].message.content
else:
return None
|