Spaces:
Running
Running
File size: 2,623 Bytes
72e6d3f 453fb62 72e6d3f 0a66a84 dc76c3e 0a66a84 72e6d3f 7d8d250 72e6d3f 7d8d250 72e6d3f 795b687 72e6d3f ca69c77 72e6d3f |
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 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 |
import requests
from bs4 import BeautifulSoup
from fastapi import FastAPI
from pydantic import BaseModel
import re
import os
app = FastAPI()
from transformers import AutoModelWithLMHead, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-summarize-news")
model = AutoModelWithLMHead.from_pretrained("mrm8488/t5-base-finetuned-summarize-news")
def summarize(text, max_length=150):
input_ids = tokenizer.encode(text, return_tensors="pt", add_special_tokens=True)
generated_ids = model.generate(input_ids=input_ids, num_beams=2, max_length=max_length, repetition_penalty=2.5, length_penalty=1.0, early_stopping=True)
preds = [tokenizer.decode(g, skip_special_tokens=True, clean_up_tokenization_spaces=True) for g in generated_ids]
return preds[0]
@app.get("/")
async def root():
return {"status": "OK"}
class Item(BaseModel):
url: str
percentage: int
def extract_article_content(url):
try:
# Fetch the HTML content of the article URL
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
results = soup.find_all(['h1', 'p'])
text = [result.text for result in results]
ARTICLE = ' '.join(text)
return ARTICLE
except Exception as e:
return ""
@app.post("/summarize-v2")
async def root(item: Item):
try:
article = extract_article_content(item.url)
if len(article) == 0:
return {'summary': ""}
response = requests.post('https://fumes-api.onrender.com/llama3',
json={'prompt': "{ 'User': 'Summarize the following news article: '" + article + "}",
"temperature":0.6,
"topP":0.9,
"maxTokens": 200}, stream=True)
response_content = response.content.decode('utf-8')
response_content = response_content.replace("Here is a summary of the news article:", "")
response_content = response_content.replace("YOU CAN BUY ME COFFE! https://buymeacoffee.com/mygx", "")
#return {clean_response}
return {
"summary":response_content}
except requests.RequestException as e:
return {"error": str(e), "status_code": 500}
@app.post("/extract-content")
async def root(item: Item):
try:
article = extract_article_content(item.url)
if len(article) == 0:
return {'ERROR': "AHHHHHHHHH"}
return {
"content":article}
except requests.RequestException as e:
return {"error": str(e), "status_code": 500}
|