Upload 10 files

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,23 @@
+# read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+#Added from here
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app
+#COPY . .
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,10 +1,11 @@
----
-title: FinTech Mistral
-emoji: ⚡
-colorFrom: green
-colorTo: yellow
-sdk: static
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: FinTech
+emoji: 🌖
+colorFrom: green
+colorTo: indigo
+sdk: docker
+pinned: false
+license: apache-2.0
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

calling_script.py

@@ -0,0 +1,46 @@
+from pydantic import BaseModel
+import requests
+import json
+
+class Item(BaseModel):
+    FileURL: str = "https://www.bseindia.com/stockinfo/AnnPdfOpen.aspx?Pname=d141ef4f-7856-4236-8f6f-efe09592df40.pdf"
+    memo: str = "Please find attached RTA Certificate u/r 74(5) of SEBI (DP) Regulations 2018 for QE March 2024"
+    TypeofAnnouncement: str = "General_Announcements"
+    Descriptor: str = "Certificate under Reg. 74 (5) of SEBI (DP) Regulations 2018"
+    caption: str = "Compliances-Certificate under Reg. 74 (5) of SEBI (DP) Regulations 2018"
+    newsdate: str = "2024-04-08T13:05:27"
+    symbol: str = "null"
+
+url = "http://jwttoken.cmots.com/cotovia/api/BSEAnnouncement"
+
+header = {"Content-Type":"application/json",
+"Authorization":"Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1bmlxdWVfbmFtZSI6ImNvdG92aWEiLCJyb2xlIjoiQWRtaW4iLCJuYmYiOjE3MTIxNDgzMzMsImV4cCI6MTcxMzAxMjMzMywiaWF0IjoxNzEyMTQ4MzMzLCJpc3MiOiJodHRwOi8vbG9jYWxob3N0OjUwMTkxIiwiYXVkIjoiaHR0cDovL2xvY2FsaG9zdDo1MDE5MSJ9.kvy4kv29zl0OkmpNXe5hZS2cHdCXF7OrShOFnxzyQfU"}
+
+output = requests.get(url,headers=header)
+data = json.loads(output.text)
+
+sample = data['data'][0]
+
+input_data = Item(
+    FileURL = sample['FileURL'] or "",
+    memo = sample['memo'] or "",
+    TypeofAnnouncement = sample['TypeofAnnouncement'] or "",
+    Descriptor = sample['Descriptor'] or "",
+    caption = sample['caption'] or "",
+    newsdate = sample['newsdate'] or "",
+    symbol = sample['symbol'] or ""
+)
+
+url = "https://tensorgirl-fintech.hf.space/Summarize/"
+
+response = requests.post(url, json = input_data.dict())
+print(response.text)
+'''
+The response would be 0 if the json doesn't pass the filter.
+Else it will return data in the form of dictionary who's keys would be as follows:
+1. mobile - For 280 words summary
+2. web - For 680 words summary
+3. tag - Single Tag
+4. headline - It will give the headline
+5. date-time - It will give the time and date when the summary was created
+'''

main.py

@@ -0,0 +1,27 @@
+from fastapi import FastAPI
+from pydantic import BaseModel, validator
+from utils import summary
+import os
+from huggingface_hub import login
+
+os.environ['HF_HOME'] = '/hug/cache/'
+os.environ['TRANSFORMERS_CACHE'] = '/blabla/cache/'
+
+class Item(BaseModel):
+    FileURL: str = "https://www.bseindia.com/stockinfo/AnnPdfOpen.aspx?Pname=d141ef4f-7856-4236-8f6f-efe09592df40.pdf"
+    memo: str  = "Please find attached RTA Certificate u/r 74(5) of SEBI (DP) Regulations 2018 for QE March 2024"
+    TypeofAnnouncement: str   = "General_Announcements"
+    Descriptor: str   = "Certificate under Reg. 74 (5) of SEBI (DP) Regulations 2018"
+    caption: str  = "Compliances-Certificate under Reg. 74 (5) of SEBI (DP) Regulations 2018"
+    newsdate: str  = "2024-04-08T13:05:27"
+    symbol: str = "EDELWEISS"
+
+app = FastAPI()
+
+@app.get("/")
+async def root():
+ return {"Summarize":"Version 1.5 'Images Added'"}
+
+@app.post("/Summarize/")
+def read_user(input_json: Item):
+    return summary(input_json.dict())

requirements.txt

@@ -0,0 +1,13 @@
+groq
+requests
+pypdf
+pandas
+datetime
+fastapi
+pydantic
+uvicorn
+openpyxl
+huggingface_hub
+torch
+transformers 
+openai

utils.py

@@ -0,0 +1,156 @@
+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://Mistral-large-tmhcg-serverless.eastus2.inference.ai.azure.com"
+    api_key = "LB0ha1R4k3pNpHl68P3VtUZ3sMLr3wT7"
+    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