Spaces:
Runtime error
Runtime error
File size: 4,326 Bytes
85c096c c8ec340 85c096c c8ec340 85c096c c8ec340 85c096c c8ec340 85c096c c8ec340 85c096c c8ec340 85c096c c8ec340 85c096c c8ec340 85c096c |
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 |
# app.py
import gradio as gr
import pandas as pd # Import pandas
from ocr_request import ocr_request
import os
from dotenv import load_dotenv
import openai
import json
def process_file(files):
response_arr = []
# Send the uploaded file to the function from ocr_request.py
for file in files:
response = ocr_request(file.name)
response_arr.append(response)
print("Main file :", response_arr)
#i= [[{'invoice_number': '349136', 'product_description': '1ST FLOOR WALLS', 'predicted_material': 'Framing', 'confidence': 0.8}, {'invoice_number': '349136', 'product_description': "11.875 X 16 ' Pro Lam 2.0 LVL 1.75 ( 7 @ 16 ' , 4 @\n8 ' )", 'predicted_material': 'Framing', 'confidence': 0.9}, {'invoice_number': '349136', 'product_description': "COLUMN\n11.875 X 10 ' Pro Lam 2.0 LVL 1.75", 'predicted_material': 'Framing', 'confidence': 0.9}, {'invoice_number': '3495565136', 'product_description': "Power Column 3 1/2 X 5 1/2 - 08 '", 'predicted_material': 'Framing', 'confidence': 0.9}],[{'invoice_number': '349136', 'product_description': ' FLOOR WALLS', 'predicted_material': 'Framing', 'confidence': 0.8}, {'invoice_number': '349136', 'product_description': "11.875 X 16 ' Pro Lam 2.0 LVL 1.75 ( 7 @ 16 ' , 4 @\n8 ' )", 'predicted_material': 'Framing', 'confidence': 0.9}, {'invoice_number': '349136', 'product_description': "COLUMN\n11.875 X 10 ' Pro Lam 2.0 LVL 1.75", 'predicted_material': 'Framing', 'confidence': 0.9}, {'invoice_number': '349136', 'product_description': "Power Column 3 1/2 X 5 1/2 - 08 '", 'predicted_material': 'Framing', 'confidence': 0.9}]]
# flat_list = []
# for item in response_arr:
# invoice_number = item['invoice_number']
# # Extracting product descriptions
# products = item.get('predictions', []) or item.get('product_description', [])
# for product in products:
# # Rename 'description' key to 'product_description' for uniformity across all products
# product_description = product.get('product_description', product.get('description'))
# predicted_material = product['predicted_material']
# confidence = product['confidence']
# flat_list.append({
# 'invoice_number': invoice_number,
# 'product_description': product_description,
# 'predicted_material': predicted_material,
# 'confidence': confidence
# })
load_dotenv()
# Initialize OpenAI with your API key
openai.api_key = os.getenv("OPENAI_API_KEY")
prompt =f"""
you are an excellent programmer and an anlyst. Given a json array or a json, you need to analyse it and convert into a json format which can be converted in dataframe of pandas easily. You have a singular task :
Once you have thought through, produce a json, easily convertible to a dataframe in python, which would contain invoice number, product description, predicted material, confidence. Remember: You just have to share the o/p json, no thought process or anything else.
Here is the json array/json : {json.dumps(response_arr)}
"""
messages=[{"role": "user", "content":prompt}]
# Use OpenAI to generate a completion using GPT-4 (replace 'gpt-4.0-turbo' with the correct engine ID once available)
response = openai.ChatCompletion.create(
model="gpt-4",
max_tokens=5000,
temperature=0,
messages = messages
)
# Extracting the result
result = response.choices[0]["message"]["content"]
print("After in min gpt")
print(json.loads(result))
df = pd.DataFrame(json.loads(result))
# df = pd.DataFrame(flat_list)
print("Df final : ", df)
# Save the dataframe to a CSV in-memory
result_csv = df.to_csv(index=False)
csv_filename = "categories.csv"
with open(csv_filename, "w") as f:
f.write(result_csv)
return df,csv_filename # Gradio will display this as a table
interface = gr.Interface(fn=process_file,
inputs=gr.inputs.File(label="Upload a File", file_count='multiple'),
outputs=["dataframe",gr.outputs.File(label="Download CSV")]) # Specify "dataframe" as output type
interface.launch(share=True)
|