openai-multi-client
openai-multi-client copied to clipboard
cozodb
Making your requests to the OpenAI API go fast!
Hello, do you have any idea on how to catch openai.error.RateLimitError and have None in response ? What I did is a try and except block in make_requests(), but I...
I tried the Azure OpenAI for the embedding, but i don't think it's working. Any ideas on supporting ? The Azure website says it doesn't support batch yet. https://learn.microsoft.com/en-us/azure/cognitive-services/openai/reference#embeddings
using doc's example: ``` from openai_multi_client import OpenAIMultiClient # Remember to set the OPENAI_API_KEY environment variable to your API key api = OpenAIMultiClient(endpoint="chats", data_template={"model": "gpt-3.5-turbo"}) def make_requests(): for num in...
**Issue / Bug** Current implementation of OpenAIMultiClient is according to older version of OpenAI. For async calls `acreate` function was used to do asynchronous calls. Example from OpenAI repo: ```python...
Hello everyone, I've been using this wonderful library to parallelize API requests in a project. It's been working great, but I recently encountered a situation where one of the API...
Ie would batching (ChatCompletion) work with token streaming?
Just curious whether there's an integration with langchain for the OpenAI API calls.. It seems quite promising.
Thanks for this library. It's been very useful. I wonder if there's any way to reduce noise when running this? I don't need to see all the exceptions in the...
I was wondering if this works with the genAI platform on DigitalOcean. It would be a great help for me if it does.
