forked from phoenix-oss/llama-stack-mirror
272d3359ee
# What does this PR do? The builtin implementation of code interpreter is not robust and has a really weak sandboxing shell (the `bubblewrap` container). Given the availability of better MCP code interpreter servers coming up, we should use them instead of baking an implementation into the Stack and expanding the vulnerability surface to the rest of the Stack. This PR only does the removal. We will add examples with how to integrate with MCPs in subsequent ones. ## Test Plan Existing tests.
142 lines
4.7 KiB
Python
142 lines
4.7 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.providers.inline.inference.sentence_transformers import (
|
|
SentenceTransformersInferenceConfig,
|
|
)
|
|
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
|
|
|
|
|
|
def get_distribution_template() -> DistributionTemplate:
|
|
providers = {
|
|
"inference": ["remote::tgi", "inline::sentence-transformers"],
|
|
"vector_io": ["inline::faiss", "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::rag-runtime",
|
|
],
|
|
}
|
|
name = "dell"
|
|
inference_provider = Provider(
|
|
provider_id="tgi0",
|
|
provider_type="remote::tgi",
|
|
config={
|
|
"url": "${env.DEH_URL}",
|
|
},
|
|
)
|
|
safety_inference_provider = Provider(
|
|
provider_id="tgi1",
|
|
provider_type="remote::tgi",
|
|
config={
|
|
"url": "${env.DEH_SAFETY_URL}",
|
|
},
|
|
)
|
|
embedding_provider = Provider(
|
|
provider_id="sentence-transformers",
|
|
provider_type="inline::sentence-transformers",
|
|
config=SentenceTransformersInferenceConfig.sample_run_config(),
|
|
)
|
|
chromadb_provider = Provider(
|
|
provider_id="chromadb",
|
|
provider_type="remote::chromadb",
|
|
config={
|
|
"url": "${env.CHROMA_URL}",
|
|
},
|
|
)
|
|
|
|
inference_model = ModelInput(
|
|
model_id="${env.INFERENCE_MODEL}",
|
|
provider_id="tgi0",
|
|
)
|
|
safety_model = ModelInput(
|
|
model_id="${env.SAFETY_MODEL}",
|
|
provider_id="tgi1",
|
|
)
|
|
embedding_model = ModelInput(
|
|
model_id="all-MiniLM-L6-v2",
|
|
provider_id="sentence-transformers",
|
|
model_type=ModelType.embedding,
|
|
metadata={
|
|
"embedding_dimension": 384,
|
|
},
|
|
)
|
|
default_tool_groups = [
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::websearch",
|
|
provider_id="brave-search",
|
|
),
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::rag",
|
|
provider_id="rag-runtime",
|
|
),
|
|
]
|
|
|
|
return DistributionTemplate(
|
|
name=name,
|
|
distro_type="self_hosted",
|
|
description="Dell's distribution of Llama Stack. TGI inference via Dell's custom container",
|
|
container_image=None,
|
|
providers=providers,
|
|
run_configs={
|
|
"run.yaml": RunConfigSettings(
|
|
provider_overrides={
|
|
"inference": [inference_provider, embedding_provider],
|
|
"vector_io": [chromadb_provider],
|
|
},
|
|
default_models=[inference_model, embedding_model],
|
|
default_tool_groups=default_tool_groups,
|
|
),
|
|
"run-with-safety.yaml": RunConfigSettings(
|
|
provider_overrides={
|
|
"inference": [
|
|
inference_provider,
|
|
safety_inference_provider,
|
|
embedding_provider,
|
|
],
|
|
"vector_io": [chromadb_provider],
|
|
},
|
|
default_models=[inference_model, safety_model, embedding_model],
|
|
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
|
|
default_tool_groups=default_tool_groups,
|
|
),
|
|
},
|
|
run_config_env_vars={
|
|
"DEH_URL": (
|
|
"http://0.0.0.0:8181",
|
|
"URL for the Dell inference server",
|
|
),
|
|
"DEH_SAFETY_URL": (
|
|
"http://0.0.0.0:8282",
|
|
"URL for the Dell safety inference server",
|
|
),
|
|
"CHROMA_URL": (
|
|
"http://localhost:6601",
|
|
"URL for the Chroma server",
|
|
),
|
|
"INFERENCE_MODEL": (
|
|
"meta-llama/Llama-3.2-3B-Instruct",
|
|
"Inference model loaded into the TGI server",
|
|
),
|
|
"SAFETY_MODEL": (
|
|
"meta-llama/Llama-Guard-3-1B",
|
|
"Name of the safety (Llama-Guard) model to use",
|
|
),
|
|
},
|
|
)
|