change

.env

@@ -0,0 +1 @@
+OPENAI_API_KEY = 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

.gitignore

@@ -0,0 +1,5 @@
+venv
+flagged
+__pycache__
+.gitignore
+.env

ai_json.py

@@ -0,0 +1,35 @@
+import openai
+import json
+from dotenv import load_dotenv
+import os
+
+
+def handle_creating_json(output_1):
+    print("Before GPT: " , output_1)
+    #output_1= [{'invoice_number': '349136', 'table_data': [{'label': 'Product_Code', 'text': ''}, {'label': 'Description', 'text': '1ST FLOOR WALLS'}, {'label': 'Price', 'text': ''}, {'label': 'Line_Amount', 'text': ''}, {'label': 'Product_Code', 'text': 'CPL1216'}, {'label': 'Description', 'text': "11.875 X 16 ' Pro Lam 2.0 LVL 1.75 ( 7 @ 16 ' , 4 @\n8 ' )"}, {'label': 'Price', 'text': '139.09'}, {'label': 'Line_Amount', 'text': '1,251.81'}, {'label': 'Product_Code', 'text': 'CPL1210'}, {'label': 'Description', 'text': "COLUMN\n11.875 X 10 ' Pro Lam 2.0 LVL 1.75"}, {'label': 'Price', 'text': '87.56'}, {'label': 'Line_Amount', 'text': '525.36'}, {'label': 'Product_Code', 'text': 'CPCB35558'}, {'label': 'Description', 'text': "Power Column 3 1/2 X 5 1/2 - 08 '"}, {'label': 'Price', 'text': '82.51'}, {'label': 'Line_Amount', 'text': '330.04'}]}]
+    load_dotenv()
+    # Initialize OpenAI with your API key
+    openai.api_key = os.getenv("OPENAI_API_KEY")
+
+    prompt = f""" You are an excellent programmer and specialize in the construction industry, knowing everything about building a house. Given a JSON which resembles a table, you have two tasks:
+    1.  extract product description and determine or predict whether product descriptions is Exterior Door/Finish/ Framing/Siding/Windows or Roofing. Think well and do some self reflection. Do not share your thought process with me though.
+    2. 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 ( b/w 0-1, your confidence score which shows how sure are you about your prediction)
+    Remember: You just have to share the output json, no thought process or extra words or anything else. If you are not able to identify the invoice number just write NA.
+    No apologies or regret. Always produce an output.
+    
+    
+    Here is the json: {json.dumps(output_1)}
+    """
+    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 gpt")
+    print(json.loads(result))
+    return json.loads(result)

app.py

@@ -0,0 +1,59 @@
+# app.py
+import gradio as gr
+import pandas as pd  # Import pandas
+from ocr_request import ocr_request
+import io
+
+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
+            })
+
+    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)
+
+

example_pg3.json

@@ -0,0 +1,274 @@
+{
+  "message": "Success",
+  "result": [
+    {
+      "message": "Success",
+      "input": "page-3.pdf",
+      "prediction": [
+        {
+          "id": "d263e93d-be6b-4642-b246-5bb8a90b8ba2",
+          "label": "table",
+          "xmin": 216,
+          "ymin": 1137,
+          "xmax": 2445,
+          "ymax": 1594,
+          "score": 1,
+          "ocr_text": "table",
+          "type": "table",
+          "cells": [],
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": ""
+        },
+        {
+          "id": "57ef19ae-73b9-4e60-92af-5d15bbe13e32",
+          "label": "buyer_address",
+          "xmin": 100,
+          "ymin": 582,
+          "xmax": 491,
+          "ymax": 663,
+          "score": 0.766381,
+          "ocr_text": "174 DORCHESTER ST\nBOSTON , MA , 02127",
+          "type": "field",
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": "12808214-6c3c-4c6f-bcff-01ce5a7596c6"
+        },
+        {
+          "id": "615d6c14-60fe-4f7c-9e84-9c5cbbc2649e",
+          "label": "subtotal",
+          "xmin": 2304,
+          "ymin": 2611,
+          "xmax": 2416,
+          "ymax": 2638,
+          "score": 0.48327795,
+          "ocr_text": "2,107.21",
+          "type": "field",
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": "0ea778c5-d7e9-46cc-b212-577f099babd8"
+        },
+        {
+          "id": "fb669362-edbe-4f49-a4f9-126f7fe255d6",
+          "label": "total_tax",
+          "xmin": 2313,
+          "ymin": 2707,
+          "xmax": 2419,
+          "ymax": 2732,
+          "score": 0.8847264,
+          "ocr_text": "$ 131.70",
+          "type": "field",
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": "cc9cf54f-e3f6-4898-b82b-3a10002bfdc6"
+        },
+        {
+          "id": "aa4c1de7-7c31-4b21-bd8a-8930adcf6cac",
+          "label": "invoice_date",
+          "xmin": 2299,
+          "ymin": 307,
+          "xmax": 2446,
+          "ymax": 329,
+          "score": 0.9948618,
+          "ocr_text": "04/12/2023",
+          "type": "field",
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": "ded9e5da-118c-48dd-bae1-97cb95df0976"
+        },
+        {
+          "id": "d99687df-518a-4e7a-bbb3-38fcb4a192f7",
+          "label": "net_d",
+          "xmin": 2323,
+          "ymin": 358,
+          "xmax": 2444,
+          "ymax": 379,
+          "score": 0.47389212,
+          "ocr_text": "2nd EOM",
+          "type": "field",
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": "790b65b6-25ef-41d7-a8ad-a93a36d02dd4"
+        },
+        {
+          "id": "6e73864b-4d34-4e49-9f4f-a010b2b771a7",
+          "label": "shipto_address",
+          "xmin": 850,
+          "ymin": 485,
+          "xmax": 1228,
+          "ymax": 562,
+          "score": 0.42755184,
+          "ocr_text": "BENNINGTON ST\n490 BENNINGTON ST",
+          "type": "field",
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": "fc485f02-f2f1-4975-9096-579508235896"
+        },
+        {
+          "id": "3b148335-3c00-4559-8e45-901f66700ebe",
+          "label": "shipto_address",
+          "xmin": 1004,
+          "ymin": 581,
+          "xmax": 1013,
+          "ymax": 613,
+          "score": 0.4113207,
+          "ocr_text": ",",
+          "type": "field",
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": "fc485f02-f2f1-4975-9096-579508235896"
+        },
+        {
+          "id": "2d7f8055-8a9d-435e-9c68-6bc86deb44bd",
+          "label": "currency",
+          "xmin": 0,
+          "ymin": 0,
+          "xmax": 0,
+          "ymax": 0,
+          "score": 1,
+          "ocr_text": "USD",
+          "type": "field",
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": "7f166b2d-ed55-47eb-bc4b-510121dd1772"
+        },
+        {
+          "id": "e11052f5-eb47-473c-914b-ced66972a18c",
+          "label": "seller_name",
+          "xmin": 951,
+          "ymin": 145,
+          "xmax": 1420,
+          "ymax": 183,
+          "score": 0.97490394,
+          "ocr_text": "Dartmouth Building Supply",
+          "type": "field",
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": "47b8254f-2bdf-4834-89d2-8c4e824f5351"
+        },
+        {
+          "id": "4b4b2b95-50ac-4ca2-bba4-2366b6cd7d15",
+          "label": "invoice_number",
+          "xmin": 2252,
+          "ymin": 231,
+          "xmax": 2446,
+          "ymax": 274,
+          "score": 0.99667007,
+          "ocr_text": "349136",
+          "type": "field",
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": "59b94f5f-ac8f-4cb6-8c54-41cb14528f58"
+        },
+        {
+          "id": "0a9f5423-bfd7-4f0a-a904-fd87fe98d8ad",
+          "label": "payment_due_date",
+          "xmin": 461,
+          "ymin": 2612,
+          "xmax": 620,
+          "ymax": 2635,
+          "score": 0.98759484,
+          "ocr_text": "06/30/2023",
+          "type": "field",
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": "cd67bda9-5ec4-44b6-a93f-67319f4b9105"
+        },
+        {
+          "id": "14c59f5a-86bc-420b-95b6-e199c9c4a7e1",
+          "label": "buyer_name",
+          "xmin": 100,
+          "ymin": 485,
+          "xmax": 460,
+          "ymax": 561,
+          "score": 0.95362574,
+          "ocr_text": "Elevated Construction\nLLC",
+          "type": "field",
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": "59ca9238-c882-4108-842b-3ac09ea1ec32"
+        },
+        {
+          "id": "ab0bff8d-8d25-42b1-8d45-ada931b131f1",
+          "label": "invoice_amount",
+          "xmin": 2288,
+          "ymin": 2614,
+          "xmax": 2303,
+          "ymax": 2638,
+          "score": 0.42010704,
+          "ocr_text": "$",
+          "type": "field",
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": "39a22a11-370c-401c-bf6e-b4f4fb14bdea"
+        },
+        {
+          "id": "ffa71a20-d784-48bb-9f5e-0af113c22375",
+          "label": "invoice_amount",
+          "xmin": 2289,
+          "ymin": 2808,
+          "xmax": 2416,
+          "ymax": 2833,
+          "score": 0.80036026,
+          "ocr_text": "$ 2,238.91",
+          "type": "field",
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": "39a22a11-370c-401c-bf6e-b4f4fb14bdea"
+        },
+        {
+          "id": "e3c8f3db-b8d1-426e-a0f6-3e793a52da25",
+          "label": "seller_address",
+          "xmin": 949,
+          "ymin": 211,
+          "xmax": 1425,
+          "ymax": 288,
+          "score": 0.72980326,
+          "ocr_text": "958 Reed Road\nNorth Dartmouth , MA 02747",
+          "type": "field",
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": "22eda91b-4613-4122-afbe-e1db97103f83"
+        },
+        {
+          "id": "7c41042b-42a4-4e6b-83ea-ecb3aab57f87",
+          "label": "seller_phone",
+          "xmin": 949,
+          "ymin": 308,
+          "xmax": 1181,
+          "ymax": 334,
+          "score": 0.6113706,
+          "ocr_text": "508-990-2389",
+          "type": "field",
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": "5e5d4507-bdab-4d74-b215-b1abf1834caf"
+        },
+        {
+          "id": "b1f5e03d-8d9a-4637-b261-01017200f3ab",
+          "label": "client_id",
+          "xmin": 2383,
+          "ymin": 408,
+          "xmax": 2449,
+          "ymax": 429,
+          "score": 0.81289464,
+          "ocr_text": "6529",
+          "type": "field",
+          "status": "correctly_predicted",
+          "page_no": 0,
+          "label_id": "913a5f4d-30f0-41fa-80fd-fe5cd49c8660"
+        }
+      ],
+      "page": 0,
+      "request_file_id": "6f6d4af0-9b10-4df4-96ab-d2d60273d9bc",
+      "filepath": "uploadedfiles/99a96f48-fa67-461d-a17d-8475af701b17/PredictionImages/8f144b01-7377-4fd9-8cd3-474ce8fa5ec1-1.jpeg",
+      "id": "12d51dd1-6155-11ee-b209-f2f6095ec3b8",
+      "rotation": 0,
+      "file_url": "uploadedfiles/99a96f48-fa67-461d-a17d-8475af701b17/RawPredictions/6f6d4af0-9b10-4df4-96ab-d2d60273d9bc.pdf",
+      "request_metadata": "",
+      "processing_type": "sync",
+      "size": { "width": 2550, "height": 3300 }
+    }
+  ]
+  
+}

ocr_request.py

@@ -0,0 +1,44 @@
+# t.py
+import requests
+import openai
+import json
+import ai_json
+
+
+def ocr_request(file_path):
+    url = 'https://app.nanonets.com/api/v2/OCR/Model/99a96f48-fa67-461d-a17d-8475af701b17/LabelFile/?async=false'
+    data = {'file': open(file_path, 'rb')}
+    response = requests.post(url, auth=requests.auth.HTTPBasicAuth('12ac2745-5e44-11ee-bb98-ea6b2bf28c31', ''), files=data)
+    response = response.json()    
+    response_data = response["result"][0]["prediction"]
+    
+    for element in response_data:
+        if element['label'] == 'table':
+            table_data = element['cells']
+        elif element['label'] == 'invoice_number':
+            invoice_number = element['ocr_text']
+
+    output_1 = {
+        'invoice_number': invoice_number,
+        'table_data':table_data
+    }
+    
+    keys_to_remove = [
+    'xmin', 'ymin', 'xmax', 'ymax', 'id', 'label_id', 'verification_status', 
+    'failed_validation', 'status', 'score', 'row_label', 'col_span', 
+    'row_span', 'row', 'col']
+
+    for item in output_1["table_data"]:
+        for key in keys_to_remove:
+            item.pop(key, None)
+    
+    print("Before sending to gpt", output_1)
+    gpt_response = ai_json.handle_creating_json(output_1)
+
+    return gpt_response
+
+    
+
+
+
+