phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-05 12:21:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

[api_updates_3] fix CLI for routing_table, bug fixes for memory & safety (#90)

Browse source 
* fix llama stack build

* fix configure

* fix configure for simple case

* configure w/ routing

* move examples config

* fix memory router naming

* issue w/ safety

* fix config w/ safety

* update memory endpoints

* allow providers in api_providers

* configure script works

* all endpoints w/ build->configure->run simple local works

* new example run.yaml

* run openapi generator
This commit is contained in:
Xi Yan 2024-09-23 08:46:33 -07:00 • committed by GitHub
parent 8cf634e615
commit ddebf9b6e7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
18 changed files with 725 additions and 605 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/distribution/utils/dynamic.py
View file

@ -8,6 +8,7 @@ import importlib
from typing import Any, Dict
from llama_stack.distribution.datatypes import * # noqa: F403
from termcolor import cprint
def instantiate_class_type(fully_qualified_name):
@ -43,12 +44,12 @@ async def instantiate_provider(
elif isinstance(provider_spec, RoutingTableProviderSpec):
method = "get_routing_table_impl"
assert isinstance(provider_config, RoutingTableConfig)
assert isinstance(provider_config, List)
routing_table = provider_config
inner_specs = {x.provider_id: x for x in provider_spec.inner_specs}
inner_impls = []
for routing_entry in routing_table.entries:
for routing_entry in routing_table:
impl = await instantiate_provider(
inner_specs[routing_entry.provider_id],
deps,