llama-stack-mirror/llama_stack
Dinesh Yeduguru 8e33db6015
add model type to APIs (#588)
# What does this PR do?

This PR adds a new model type field to support embedding models to be
registered. Summary of changes:
1) Each registered model by default is an llm model. 
2) User can specify an embedding model type, while registering.If
specified, the model bypass the llama model checks since embedding
models can by of any type and based on llama.
3) User needs to include the required embedding dimension in metadata.
This will be used by embedding generation to generate the requried size
of embeddings.


## Test Plan

This PR will go together will need to be merged with two follow up PRs
that will include test plans.
2024-12-11 10:16:53 -08:00
..
apis add model type to APIs (#588) 2024-12-11 10:16:53 -08:00
cli doc: llama-stack build --config help text references old directory (#596) 2024-12-10 17:42:02 -08:00
distribution add model type to APIs (#588) 2024-12-11 10:16:53 -08:00
providers add model type to APIs (#588) 2024-12-11 10:16:53 -08:00
scripts Integrate distro docs into the restructured docs 2024-11-20 23:20:05 -08:00
templates Fix issue 586 (#594) 2024-12-10 10:22:04 -08:00
__init__.py Miscellaneous fixes around telemetry, library client and run yaml autogen 2024-12-08 20:40:22 -08:00