forked from phoenix-oss/llama-stack-mirror
Some small updates to the inference types to make them more standard Specifically: - image data is now located in a "image" subkey - similarly tool call data is located in a "tool_call" subkey The pattern followed is `dict(type="foo", foo=<...>)` |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| embedding_mixin.py | ||
| model_registry.py | ||
| openai_compat.py | ||
| prompt_adapter.py | ||