llama-stack-mirror/llama_stack/providers/remote/inference/anthropic/models.py
Sébastien Han 11c912da0a
ci: test safety with starter
We are now testing the safety capability with the starter image. This
includes a few changes:

* Enable the safety integration test
* Relax the shield model requirements from llama-guard to make it work
  with llama-guard3:8b coming from Ollama
* Expose a shield for each inference provider in the starter distro. The
  shield will only be registered if the provider is enabled. Shields
  will be added if the provider claims to support a safety model
* Missing providers models have been added too
* Pointers to official documentation pages for provider models support
  have been added

Closes: https://github.com/meta-llama/llama-stack/issues/2528
Signed-off-by: Sébastien Han <seb@redhat.com>
2025-07-09 16:30:33 +02:00

40 lines
1.3 KiB
Python

# 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.apis.models import ModelType
from llama_stack.providers.utils.inference.model_registry import (
ProviderModelEntry,
)
LLM_MODEL_IDS = [
"anthropic/claude-3-5-sonnet-latest",
"anthropic/claude-3-7-sonnet-latest",
"anthropic/claude-3-5-haiku-latest",
]
SAFETY_MODELS_ENTRIES = []
MODEL_ENTRIES = (
[ProviderModelEntry(provider_model_id=m) for m in LLM_MODEL_IDS]
+ [
ProviderModelEntry(
provider_model_id="anthropic/voyage-3",
model_type=ModelType.embedding,
metadata={"embedding_dimension": 1024, "context_length": 32000},
),
ProviderModelEntry(
provider_model_id="anthropic/voyage-3-lite",
model_type=ModelType.embedding,
metadata={"embedding_dimension": 512, "context_length": 32000},
),
ProviderModelEntry(
provider_model_id="anthropic/voyage-code-3",
model_type=ModelType.embedding,
metadata={"embedding_dimension": 1024, "context_length": 32000},
),
]
+ SAFETY_MODELS_ENTRIES
)