openai / evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
Other
14.36k stars 2.55k forks source link

Extending to Azure OpenAI implementation #1470

Open pkt1583 opened 4 months ago

pkt1583 commented 4 months ago

This PR allows to use Azure OpenAI implementation. Since the API structure in openAI and Azure openAI is same the client can be initialised by looking at environment variable presence of AZURE_OPENAI_ENDPOINT. If we rely on CompletionFn endpoint then the code will still be more or less copy paste of existing OpenAI completionfn's

SeryioGonzalez commented 2 months ago

Azure OpenAI support would be an ideal add-on to this great tool.