mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
feat: add static embedding metadata to dynamic model listings for providers using OpenAIMixin (#3547)
# What does this PR do? - remove auto-download of ollama embedding models - add embedding model metadata to dynamic listing w/ unit test - add support and tests for allowed_models - removed inference provider models.py files where dynamic listing is enabled - store embedding metadata in embedding_model_metadata field on inference providers - make model_entries optional on ModelRegistryHelper and LiteLLMOpenAIMixin - make OpenAIMixin a ModelRegistryHelper - skip base64 embedding test for remote::ollama, always returns floats - only use OpenAI client for ollama model listing - remove unused build_model_entry function - remove unused get_huggingface_repo function ## Test Plan ci w/ new tests
This commit is contained in:
parent
a50b63906c
commit
b67aef2fc4
43 changed files with 368 additions and 1015 deletions
|
@ -1,28 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from llama_stack.models.llama.sku_types import CoreModelId
|
||||
from llama_stack.providers.utils.inference.model_registry import (
|
||||
build_hf_repo_model_entry,
|
||||
)
|
||||
|
||||
SAFETY_MODELS_ENTRIES = []
|
||||
|
||||
|
||||
MODEL_ENTRIES = [
|
||||
build_hf_repo_model_entry(
|
||||
"Meta-Llama-3.1-8B-Instruct",
|
||||
CoreModelId.llama3_1_8b_instruct.value,
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"Meta-Llama-3.3-70B-Instruct",
|
||||
CoreModelId.llama3_3_70b_instruct.value,
|
||||
),
|
||||
build_hf_repo_model_entry(
|
||||
"Llama-4-Maverick-17B-128E-Instruct",
|
||||
CoreModelId.llama4_maverick_17b_128e_instruct.value,
|
||||
),
|
||||
] + SAFETY_MODELS_ENTRIES
|
|
@ -9,7 +9,6 @@ from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOp
|
|||
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
|
||||
|
||||
from .config import SambaNovaImplConfig
|
||||
from .models import MODEL_ENTRIES
|
||||
|
||||
|
||||
class SambaNovaInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
|
||||
|
@ -29,7 +28,6 @@ class SambaNovaInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
|
|||
self.environment_available_models = []
|
||||
LiteLLMOpenAIMixin.__init__(
|
||||
self,
|
||||
model_entries=MODEL_ENTRIES,
|
||||
litellm_provider_name="sambanova",
|
||||
api_key_from_config=self.config.api_key.get_secret_value() if self.config.api_key else None,
|
||||
provider_data_api_key_field="sambanova_api_key",
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue