forked from phoenix-oss/llama-stack-mirror
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
```
122 lines
4.3 KiB
Python
122 lines
4.3 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.models import ModelType
|
|
from llama_stack.distribution.datatypes import (
|
|
ModelInput,
|
|
Provider,
|
|
ShieldInput,
|
|
ToolGroupInput,
|
|
)
|
|
from llama_stack.models.llama.sku_list import all_registered_models
|
|
from llama_stack.providers.inline.inference.sentence_transformers import (
|
|
SentenceTransformersInferenceConfig,
|
|
)
|
|
from llama_stack.providers.inline.vector_io.sqlite_vec.config import SQLiteVectorIOConfig
|
|
from llama_stack.providers.remote.inference.fireworks.config import FireworksImplConfig
|
|
from llama_stack.providers.remote.inference.fireworks.models import MODEL_ENTRIES
|
|
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
|
|
|
|
|
|
def get_distribution_template() -> DistributionTemplate:
|
|
providers = {
|
|
"inference": ["remote::fireworks", "inline::sentence-transformers"],
|
|
"vector_io": ["inline::sqlite-vec", "remote::chromadb", "remote::pgvector"],
|
|
"safety": ["inline::llama-guard"],
|
|
"agents": ["inline::meta-reference"],
|
|
"telemetry": ["inline::meta-reference"],
|
|
"eval": ["inline::meta-reference"],
|
|
"datasetio": ["remote::huggingface", "inline::localfs"],
|
|
"scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
|
|
"tool_runtime": [
|
|
"remote::brave-search",
|
|
"remote::tavily-search",
|
|
"inline::code-interpreter",
|
|
"inline::rag-runtime",
|
|
"remote::model-context-protocol",
|
|
],
|
|
}
|
|
name = "ci-tests"
|
|
inference_provider = Provider(
|
|
provider_id="fireworks",
|
|
provider_type="remote::fireworks",
|
|
config=FireworksImplConfig.sample_run_config(),
|
|
)
|
|
vector_io_provider = Provider(
|
|
provider_id="sqlite-vec",
|
|
provider_type="inline::sqlite-vec",
|
|
config=SQLiteVectorIOConfig.sample_run_config(f"distributions/{name}"),
|
|
)
|
|
embedding_provider = Provider(
|
|
provider_id="sentence-transformers",
|
|
provider_type="inline::sentence-transformers",
|
|
config=SentenceTransformersInferenceConfig.sample_run_config(),
|
|
)
|
|
|
|
default_tool_groups = [
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::websearch",
|
|
provider_id="tavily-search",
|
|
),
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::rag",
|
|
provider_id="rag-runtime",
|
|
),
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::code_interpreter",
|
|
provider_id="code-interpreter",
|
|
),
|
|
]
|
|
core_model_to_hf_repo = {m.descriptor(): m.huggingface_repo for m in all_registered_models()}
|
|
default_models = [
|
|
ModelInput(
|
|
model_id=core_model_to_hf_repo[m.llama_model] if m.llama_model else m.provider_model_id,
|
|
provider_id="fireworks",
|
|
model_type=m.model_type,
|
|
metadata=m.metadata,
|
|
)
|
|
for m in MODEL_ENTRIES
|
|
]
|
|
embedding_model = ModelInput(
|
|
model_id="all-MiniLM-L6-v2",
|
|
provider_id="sentence-transformers",
|
|
model_type=ModelType.embedding,
|
|
metadata={
|
|
"embedding_dimension": 384,
|
|
},
|
|
)
|
|
|
|
return DistributionTemplate(
|
|
name=name,
|
|
distro_type="self_hosted",
|
|
description="Distribution for running e2e tests in CI",
|
|
container_image=None,
|
|
template_path=None,
|
|
providers=providers,
|
|
default_models=default_models + [embedding_model],
|
|
run_configs={
|
|
"run.yaml": RunConfigSettings(
|
|
provider_overrides={
|
|
"inference": [inference_provider, embedding_provider],
|
|
"vector_io": [vector_io_provider],
|
|
},
|
|
default_models=default_models + [embedding_model],
|
|
default_tool_groups=default_tool_groups,
|
|
default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
|
|
),
|
|
},
|
|
run_config_env_vars={
|
|
"LLAMA_STACK_PORT": (
|
|
"5001",
|
|
"Port for the Llama Stack distribution server",
|
|
),
|
|
"FIREWORKS_API_KEY": (
|
|
"",
|
|
"Fireworks API Key",
|
|
),
|
|
},
|
|
)
|