Spaces:
Running
Running
File size: 4,643 Bytes
35efc3d d2f3072 816350a 35efc3d 816350a 19c4fb0 816350a 1d0438a 816350a 35efc3d a87e18a 35efc3d 32532af 62528eb 32532af 35efc3d 62528eb a697828 488609d 8d4b4fb 62528eb 35efc3d 19c4fb0 a3f4b98 b7889d4 19c4fb0 a3f4b98 b7889d4 19c4fb0 35efc3d 19c4fb0 a3f4b98 b7889d4 19c4fb0 35efc3d 9265cfc a3f4b98 b7889d4 a3f4b98 35efc3d 488609d 35efc3d 816350a 32532af 816350a 35efc3d 62528eb 35efc3d |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 |
import datetime
from urllib.request import Request, urlopen
from pypdf import PdfReader
from io import StringIO
import io
import pandas as pd
import os
import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification
from transformers import pipeline
from openai import OpenAI
from groq import Groq
import time
from openai import OpenAI
#openai_key = "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"
#client = OpenAI(api_key = openai_key)
desc = pd.read_excel('Descriptor.xlsx',header = None)
desc_list = desc.iloc[:,0].to_list()
def callAzure(prompt,text):
url = "https://Meta-Llama-3-70B-Instruct-fkqip-serverless.eastus2.inference.ai.azure.com"
api_key = "o5yaLhTIvg0s5zuYVInBpyneEZO8oonY"
client = OpenAI(base_url=url, api_key=api_key)
msg = "{} {}".format(prompt, text)
msg = msg[:7000]
response = client.chat.completions.create(
messages=[
{
"role": "user",
"content": msg,
}
],
model="azureai",
)
return response.choices[0].message.content
def call(prompt, text):
client = Groq(api_key=os.getenv("key"),)
prompt = prompt + " Answer only the summary, no instructions"
chat_completion = client.chat.completions.create(
messages=[
{
"role": "user",
"content": "{} {}".format(prompt, text),
}
],
model=model,
)
return chat_completion.choices[0].message.content
def filter(input_json):
sym = pd.read_excel('symbol.xlsx',header = None)
sym_list = sym.iloc[:,0].to_list()
if input_json['FileURL']==None or input_json['FileURL'].lower()=='null':
return [0,"File_URL"]
if input_json['symbol']== 'null' or input_json['symbol'] not in sym_list:
return [0,"symbol"]
if input_json['TypeofAnnouncement'] not in ['General_Announcements','Outcome','General']:
return [0,"Annoucement"]
if input_json['Descriptor'] not in desc_list:
return [0,"Desc"]
url = 'https://www.bseindia.com/xml-data/corpfiling/AttachLive/'+ input_json['FileURL'].split('Pname=')[-1]
req = Request(url, headers={'User-Agent': 'Mozilla/5.0'})
html = urlopen(req)
cont = html.read()
reader = PdfReader(io.BytesIO(cont))
content = ''
for i in range(len(reader.pages)):
content+= reader.pages[i].extract_text()
document = content
return [1, document]
def summary(input_json):
prompt = pd.read_excel('DescriptorPrompt.xlsx')
promptShort = prompt.iloc[:,1].to_list()
promptLong = prompt.iloc[:,2].to_list()
output = {}
filtering_results = filter(input_json)
if filtering_results[0] == 0:
#return 0
return filtering_results[1]
id = desc_list.index(input_json['Descriptor'])
long_text = filtering_results[1]
url = 'https://www.bseindia.com/xml-data/corpfiling/AttachLive/'+ input_json['FileURL'].split('Pname=')[-1]
output["Link to BSE website"] = url
output["Date of time of receiving data from BSE"] = input_json["newsdate"] + "Z"
output["Stock Ticker"] = input_json['symbol']
answer = callAzure(promptShort[id], long_text)
try:
idx = answer.index("\n")
except:
idx = -2
output['Short Summary'] = answer[idx+2:]
answer = callAzure(promptLong[id], long_text)
try:
idx = answer.index("\n")
except:
idx = -2
output['Long summary'] = answer[idx+2:]
prompt = "1 word Financial SEO tag for this news article"
answer = callAzure(prompt, output['Short Summary'])
try:
idx = answer.index("\n")
except:
idx = -2
output['Tag'] = answer[idx+2:]
prompt = "Give a single headline for this News Article"
answer = callAzure(prompt, output['Short Summary'])
try:
idx = answer.index("\n")
except:
idx = -2
output['Headline'] = answer[idx+2:]
utc_now = datetime.datetime.utcnow()
ist_now = utc_now.astimezone(datetime.timezone(datetime.timedelta(hours=5, minutes=30)))
Date = ist_now.strftime("%Y-%m-%d")
time = ist_now.strftime("%X")
output['Date and time of data delivery from Skylark'] = Date+"T"+time+"Z"
prompt = "Answer in one word the sentiment of this News out of Positive, Negative or Neutral {}"
output['Sentiment'] = callAzure(prompt, output['Short Summary'])
#time.sleep(60)
# response = client.images.generate(
# model="dall-e-3",
# prompt=headline.text,
# size="1024x1024",
# quality="standard",
# n=1
# )
# output["Link to Infographic (data visualization only)] = response.data[0].url
return output |