mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
63e6acd0c3
# What does this PR do?
This PR introduces more non-llama model support to llama stack.
Providers introduced: openai, anthropic and gemini. All of these
providers use essentially the same piece of code -- the implementation
works via the `litellm` library.
We will expose only specific models for providers we enable making sure
they all work well and pass tests. This setup (instead of automatically
enabling _all_ providers and models allowed by LiteLLM) ensures we can
also perform any needed prompt tuning on a per-model basis as needed
(just like we do it for llama models.)
## Test Plan
```bash
#!/bin/bash
args=("$@")
for model in openai/gpt-4o anthropic/claude-3-5-sonnet-latest gemini/gemini-1.5-flash; do
LLAMA_STACK_CONFIG=dev pytest -s -v tests/client-sdk/inference/test_text_inference.py \
--embedding-model=all-MiniLM-L6-v2 \
--vision-inference-model="" \
--inference-model=$model "${args[@]}"
done
```
30 lines
892 B
Python
30 lines
892 B
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.models import ModelType
|
|
from llama_stack.providers.utils.inference.model_registry import (
|
|
ProviderModelEntry,
|
|
)
|
|
|
|
LLM_MODEL_IDS = [
|
|
"openai/gpt-4o",
|
|
"openai/gpt-4o-mini",
|
|
"openai/chatgpt-4o-latest",
|
|
]
|
|
|
|
|
|
MODEL_ENTRIES = [ProviderModelEntry(provider_model_id=m) for m in LLM_MODEL_IDS] + [
|
|
ProviderModelEntry(
|
|
provider_model_id="openai/text-embedding-3-small",
|
|
model_type=ModelType.embedding,
|
|
metadata={"embedding_dimension": 1536},
|
|
),
|
|
ProviderModelEntry(
|
|
provider_model_id="openai/text-embedding-3-large",
|
|
model_type=ModelType.embedding,
|
|
metadata={"embedding_dimension": 3072},
|
|
),
|
|
]
|