I’m a newbie and I need to make a request like in the example below, but my issue is that ‘my_dict’ far to big and I keep getting ‘400 Bad Request’ errors, and when I try to split it and make multiple calls I get ‘429 Too Many Requests’ errors. Another issue is that when I test it on smaller data samples it takes ages to finish.
This is the structure of ‘my_dict’, I get it from an Excel file using pandas:
my_dict = {
"key1": {
0: "value1.1",
1: "value2.1",
...
1999: "value2000.1"
},
"key2": {
0: "value1.2",
1: "value2.2",
...
1999: "value2000.2"
},
"key3": {
0: "value1.3",
1: "value2.3",
...
1999: "value2000.3"
},
"key4": {
0: "value1.4",
1: "value2.4",
...
1999: "value2000.4"
},
}
I need the ai to return a value based on the first items in each of the inner dictionaries, then based on the second items and so on.
import requests
endpoint = 'https://resource-name.openai.azure.com/openai/deployments/deployment-id/chat/completions?api-version=2024-02-01'
api_key = '1q2w3e4r5t6y7u8i9o0p'
headers = {
'Content-Type': 'application/json',
'api-key': api_key
}
payload = {
"messages": [
{
"role": "system",
"content": "Prompt..."
f"Dictionary: {my_dict}"
},
],
"temperature": 0.7
}
response = requests.post(endpoint , headers=headers, json=payload)
print(response.json())
I’d appreciate any help or advice.
4
I tried the below code to manage a large dictionary by splitting it into smaller chunks and making API requests to OpenAI’s GPT-4o model. The objective is to return values from each inner dictionary based on the order of indices (i.e., index 0, index 1, and index 1999).
-
chunk_dictFunction: Splits a large dictionary into smaller, manageable chunks based on a specified size for easier handling of large datasets. -
process_large_dictFunction: Iterates through each chunk, sending POST requests to the Azure OpenAI endpoint. The API prompt directs the model to process and return values for indices 0, 1, and 1999 in order.
Code :
import requests
import time
endpoint = 'https://<openai_name>.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2024-02-15-preview'
api_key = '<api_key>'
headers = {
'Content-Type': 'application/json',
'api-key': api_key
}
my_dict = {
"key1": {
0: "value1.1",
1: "value2.1",
# ...
1999: "value2000.1"
},
"key2": {
0: "value1.2",
1: "value2.2",
# ...
1999: "value2000.2"
},
"key3": {
0: "value1.3",
1: "value2.3",
# ...
1999: "value2000.3"
},
"key4": {
0: "value1.4",
1: "value2.4",
# ...
1999: "value2000.4"
},
}
def chunk_dict(d, chunk_size):
"""Split dictionary into smaller chunks."""
items = list(d.items())
for i in range(0, len(items), chunk_size):
yield dict(items[i:i + chunk_size])
def make_request(chunk):
"""Make API request with chunk of data."""
content = (
f"Please process the following dictionary and return the values based on the order of their indices:"
f"n{chunk}nn"
f"For each key, return the value for index 0 first, then for index 1, and finally for index 1999."
)
payload = {
"messages": [
{
"role": "system",
"content": content
}
],
"temperature": 0.7
}
try:
response = requests.post(endpoint, headers=headers, json=payload)
if response.status_code == 429:
print("Rate limit exceeded. Waiting before retrying...")
time.sleep(10)
return make_request(chunk)
elif response.status_code == 200:
return response.json()
else:
print(f"Error: {response.status_code} - {response.text}")
return None
except requests.RequestException as e:
print(f"Request exception: {e}")
return None
def process_large_dict(my_dict, chunk_size):
"""Process the large dictionary in chunks."""
chunks = chunk_dict(my_dict, chunk_size)
results = []
for chunk in chunks:
result = make_request(chunk)
if result:
results.append(result)
else:
print("Failed to get response for chunk.")
return results
chunk_size = 10
results = process_large_dict(my_dict, chunk_size)
for result in results:
print(result)
Output :