The content of the API is not accurate as Playground UI results

API Bugs
,
1

am using gpt-4o model
am trying to ask some ocr questions regarding that image.
When am using api , am getting some spelling mistakes.
But in the playground getting the correct answer.
May be i think this is because of the image resolution after converting to base 64
I need help regarding this problem.

import openai
import base64
import csv
import re
import json
# Set up your OpenAI API key
openai.api_key = 'sk-**************'

# Path to the image file
image_path = '/path_of_the_image.png'

# Function to read image and convert to base64
def image_to_base64(image_path):
    with open(image_path, "rb") as image_file:
        encoded_string = base64.b64encode(image_file.read()).decode('utf-8')
    return encoded_string

# Path to the image


# Convert image to base64
image_base64 = image_to_base64(image_path)

# Define the prompt
prompt = """PCN,Patient ID,Patient Full Name,Claim ID,Paid Amount,Extract the data of all the rows from the image and map with the above columns in json format.
```json
{ 
  "PCN": "", 
  "Patient ID": "32357", 
  "Patient Full Name": "xyz", 
  "Claim ID": "12345678", 
  "Paid Amount": "0.00", 
}
"""

# Make the API call
response = openai.ChatCompletion.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "Act as a Data Entry Agent and extract the data from the image."},
        {"role": "user", "content": prompt},
        {"role": "user", "content": [{"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{image_base64}"}}]}
    ],
    temperature=0,
    max_tokens=4095,
    top_p=1,
    frequency_penalty=0,
    presence_penalty=0
)

# Print the response
json_data = response['choices'][0]['message']['content']
# print(response['choices'][0]['message']['content'])
print(json_data)
2

BASE64 does not alter the contents of an image.

However on the API, you have top_p and temperature parameters, the ability to resize, the quality of the instructions you provide, and the “detail” setting when you place the message, some of which the Assistants playground doesn’t reveal.

3

@_j I had done with that change also.
Same parameters which am using on UI am using the same on API.
In UI not getting any spelling mistakes.But in API am facing spelling mistakes when am trying to ask questions regrading that image (ocr).