APIError - Error 500 using API for Embeddings

I’m facing a recurring error while using the OpenAI API. After around some minutes of execution, I keep getting this frustrating message:

“APIError: The server had an error while processing your request. Sorry about that! You can retry your request, or contact us at help.openai.com if the error persists. (Request ID: 02dd410798435ad9fec54f15404dbb08)”

I tried implementing error handling and even added delays between requests, but the error keeps popping up.

Im using this function:

‘’’
import time

def add_embeddings_to_dataframe(df, label_column, model, delay=0.5):
embeddings =
for label in df[label_column]:
embedding = openai.Embedding.create(input=label, model=model)[“data”][0][“embedding”]
embeddings.append(embedding)
time.sleep(delay) # Agregar un retraso de tiempo antes de la siguiente solicitud
embedding_columns = [f"embedding_{i}" for i in range(len(embeddings[0]))]
embedding_df = pd.DataFrame(embeddings, columns=embedding_columns)
return pd.concat([df, embedding_df], axis=1)

df_embedings_1 = add_embeddings_to_dataframe(df1,‘clean_categoria’, “text-embedding-ada-002”)
‘’‘’

After a few minutes of execution, this error appears

My dataset has 15k records aprox.

1 Like

If you get the error of 429, try to implement the Retrying with exponential backoff

more information about the error numbers

I’m also getting this exact same error.
Any help would be greatly appreciated.