phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

migrate model to Resource and new registration signature (#410)

Browse source 
* resource oriented object design for models

* add back llama_model field

* working tests

* register singature fix

* address feedback

---------

Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
This commit is contained in:
Dinesh Yeduguru 2024-11-08 16:12:57 -08:00 • committed by GitHub
parent bd0622ef10
commit ec644d3418
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
17 changed files with 99 additions and 90 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -15,7 +15,7 @@ from llama_models.llama3.api.tokenizer import Tokenizer
from ollama import AsyncClient
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.providers.datatypes import ModelsProtocolPrivate
from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
from llama_stack.providers.utils.inference.openai_compat import (
get_sampling_options,
@ -65,10 +65,11 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
async def shutdown(self) -> None:
pass
async def register_model(self, model: ModelDef) -> None:
raise ValueError("Dynamic model registration is not supported")
async def register_model(self, model: Model) -> None:
if model.identifier not in OLLAMA_SUPPORTED_MODELS:
raise ValueError(f"Model {model.identifier} is not supported by Ollama")
async def list_models(self) -> List[ModelDef]:
async def list_models(self) -> List[Model]:
ollama_to_llama = {v: k for k, v in OLLAMA_SUPPORTED_MODELS.items()}
ret = []
@ -80,9 +81,8 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
llama_model = ollama_to_llama[r["model"]]
ret.append(
ModelDef(
Model(
identifier=llama_model,
llama_model=llama_model,
metadata={
"ollama_model": r["model"],
},