The Self-Hosted Distribution documentation contain steps
to start llama server via conda environment. If the user
generates conda environment using llaama build command and template,
it generate an environment with name of the distribution and not
defaulyt name of local as per the example run yaml file. It
will thereore fail when user tried to run the server.
This PR fixes the conda env name in the run yaml file.
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
Splits the meta-reference safety implementation into three distinct providers:
- inline::llama-guard
- inline::prompt-guard
- inline::code-scanner
Note that this PR is a backward incompatible change to the llama stack server. I have added deprecation_error field to ProviderSpec -- the server reads it and immediately barfs. This is used to direct the user with a specific message on what action to perform. An automagical "config upgrade" is a bit too much work to implement right now :/
(Note that we will be gradually prefixing all inline providers with inline:: -- I am only doing this for this set of new providers because otherwise existing configuration files will break even more badly.)
