GPT-4o through Azure OpenAI is now generally available on all enrollments that are either not geographically-restricted, or are geographically restricted to the United States or European Union.
To use GPT-4o, you will need to have Azure OpenAI models enabled through the AIP Settings Control Panel extension.
GPT-4o is targeted to be the new flagship model provided by OpenAI. Existing workflows which use GPT-4 are recommended to use GPT-4o as it is cheaper, faster, with more capacity available than existing models provided by Azure OpenAI, and supports multi-modal input such as image and text.
The expansion of supported regions is in development.
Review a list of LLMs supported in Palantir.
Is it possible to use GPT-4o to create typescript/python functions by simply giving a text prompt? something that Anthropic recently released with Claude 3.5 sonnet.
Anthropic’s Claude 3.5 is not currently available through Palantir-provided large language models but Claude 3 Sonnet is. The list of supported LLMs is expanding with the latest addition being GPT-4o.
There are numerous ways you can interact with these LLMs on the platform; some examples include direct API use through Jupyter notebooks in Code workspaces, a chat interface through AIP Assist and low-code applications like AIP Logic.
If you are interested in specific capability differences between models, that information is publicly available and Hugging face provides popular benchmarks. For what is worth, most LLMs, including GPT-4o can engage in coding tasks with reasonable competency.
