phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-05 10:13:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update ollama register_model to follow aliases

Browse source
This commit is contained in:
Matthew Farrellee 2025-04-22 09:35:08 -04:00
parent 84351c2d67
commit c436269cd4
1 changed files with 7 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -8,7 +8,6 @@
from typing import Any, AsyncGenerator, AsyncIterator, Dict, List, Optional, Union from typing import Any, AsyncGenerator, AsyncIterator, Dict, List, Optional, Union
import httpx import httpx
from ollama import AsyncClient
from openai import AsyncOpenAI from openai import AsyncOpenAI
from llama_stack.apis.common.content_types import ( from llama_stack.apis.common.content_types import (
@ -73,6 +72,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
interleaved_content_as_str, interleaved_content_as_str,
request_has_media, request_has_media,
) )
from ollama import AsyncClient
from .models import model_entries from .models import model_entries
@ -342,9 +342,12 @@ class OllamaInferenceAdapter(
# - models not currently running are run by the ollama server as needed # - models not currently running are run by the ollama server as needed
response = await self.client.list() response = await self.client.list()
available_models = [m["model"] for m in response["models"]] available_models = [m["model"] for m in response["models"]]
if model.provider_resource_id not in available_models: provider_resource_id = self.register_helper.get_provider_model_id(model.provider_resource_id)
if provider_resource_id is None:
provider_resource_id = model.provider_resource_id
if provider_resource_id not in available_models:
available_models_latest = [m["model"].split(":latest")[0] for m in response["models"]] available_models_latest = [m["model"].split(":latest")[0] for m in response["models"]]
if model.provider_resource_id in available_models_latest: if provider_resource_id in available_models_latest:
logger.warning( logger.warning(
f"Imprecise provider resource id was used but 'latest' is available in Ollama - using '{model.provider_resource_id}:latest'" f"Imprecise provider resource id was used but 'latest' is available in Ollama - using '{model.provider_resource_id}:latest'"
) )
@ -352,6 +355,7 @@ class OllamaInferenceAdapter(
raise ValueError( raise ValueError(
f"Model '{model.provider_resource_id}' is not available in Ollama. Available models: {', '.join(available_models)}" f"Model '{model.provider_resource_id}' is not available in Ollama. Available models: {', '.join(available_models)}"
) )
model.provider_resource_id = provider_resource_id
return model return model