phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-07 02:58:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

dell template + codegen for others

Browse source
This commit is contained in:
Hardik Shah 2025-02-04 17:33:29 -08:00
parent 981bb52b59
commit 65e8f5bfaf
14 changed files with 749 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

62
distributions/dependencies.json
View file

@ -27,7 +27,7 @@
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"hf-serverless": [
"aiohttp",
@ -62,7 +62,7 @@
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"together": [
"aiosqlite",
@ -96,7 +96,7 @@
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"vllm-gpu": [
"aiosqlite",
@ -130,7 +130,7 @@
"uvicorn",
"vllm",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"remote-vllm": [
"aiosqlite",
@ -163,7 +163,7 @@
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"fireworks": [
"aiosqlite",
@ -197,7 +197,7 @@
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"tgi": [
"aiohttp",
@ -232,7 +232,41 @@
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"dell": [
"aiohttp",
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"huggingface_hub",
"matplotlib",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pypdf",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"bedrock": [
"aiosqlite",
@ -266,7 +300,7 @@
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"meta-reference-gpu": [
"accelerate",
@ -306,7 +340,7 @@
"uvicorn",
"zmq",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"nvidia": [
"aiosqlite",
@ -338,7 +372,7 @@
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"meta-reference-quantized-gpu": [
"accelerate",
@ -380,7 +414,7 @@
"uvicorn",
"zmq",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"cerebras": [
"aiosqlite",
@ -413,7 +447,7 @@
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"ollama": [
"aiohttp",
@ -447,7 +481,7 @@
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"hf-endpoint": [
"aiohttp",
@ -482,6 +516,6 @@
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch --index-url https://download.pytorch.org/whl/cpu"
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
]
}

144
docs/source/distributions/self_hosted_distro/dell.md Normal file
View file

@ -0,0 +1,144 @@
---
orphan: true
---
# Dell Distribution of Llama Stack
```{toctree}
:maxdepth: 2
:hidden:
self
```
The `llamastack/distribution-dell` distribution consists of the following provider configurations.
| API | Provider(s) |
|-----|-------------|
| agents | `inline::meta-reference` |
| datasetio | `remote::huggingface`, `inline::localfs` |
| eval | `inline::meta-reference` |
| inference | `remote::tgi` |
| safety | `inline::llama-guard` |
| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
| telemetry | `inline::meta-reference` |
| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime` |
| vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
You can use this distribution if you have GPUs and want to run an independent TGI server container for running inference.
### Environment Variables
The following environment variables can be configured:
- `DEH_URL`: URL for the Dell inference server (default: `http://0.0.0.0:8080`)
- `DEH_SAFETY_URL`: URL for the Dell safety inference server (default: `http://0.0.0.0:8081`)
- `CHROMA_URL`: URL for the Chroma server (default: `http://0.0.0.0:8000`)
- `INFERENCE_MODEL`: Inference model loaded into the TGI server (default: `meta-llama/Llama-3.2-3B-Instruct`)
- `SAFETY_MODEL`: Name of the safety (Llama-Guard) model to use (default: `meta-llama/Llama-Guard-3-1B`)
## Setting up TGI server
Please check the [TGI Getting Started Guide](https://github.com/huggingface/text-generation-inference?tab=readme-ov-file#get-started) to get a TGI endpoint. Here is a sample script to start a TGI server locally via Docker:
```bash
export INFERENCE_PORT=8080
export INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
export CUDA_VISIBLE_DEVICES=0
docker run --rm -it \
-v $HOME/.cache/huggingface:/data \
-p $INFERENCE_PORT:$INFERENCE_PORT \
--gpus $CUDA_VISIBLE_DEVICES \
ghcr.io/huggingface/text-generation-inference:2.3.1 \
--dtype bfloat16 \
--usage-stats off \
--sharded false \
--cuda-memory-fraction 0.7 \
--model-id $INFERENCE_MODEL \
--port $INFERENCE_PORT
```
If you are using Llama Stack Safety / Shield APIs, then you will need to also run another instance of a TGI with a corresponding safety model like `meta-llama/Llama-Guard-3-1B` using a script like:
```bash
export SAFETY_PORT=8081
export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
export CUDA_VISIBLE_DEVICES=1
docker run --rm -it \
-v $HOME/.cache/huggingface:/data \
-p $SAFETY_PORT:$SAFETY_PORT \
--gpus $CUDA_VISIBLE_DEVICES \
ghcr.io/huggingface/text-generation-inference:2.3.1 \
--dtype bfloat16 \
--usage-stats off \
--sharded false \
--model-id $SAFETY_MODEL \
--port $SAFETY_PORT
```
## Running Llama Stack
Now you are ready to run Llama Stack with TGI as the inference provider. You can do this via Conda (build code) or Docker which has a pre-built image.
### Via Docker
This method allows you to get started quickly without having to build the distribution code.
```bash
LLAMA_STACK_PORT=5001
docker run \
-it \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
llamastack/distribution-dell \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env TGI_URL=http://host.docker.internal:$INFERENCE_PORT
```
If you are using Llama Stack Safety / Shield APIs, use:
```bash
# You need a local checkout of llama-stack to run this, get it using
# git clone https://github.com/meta-llama/llama-stack.git
cd /path/to/llama-stack
docker run \
-it \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
-v ./llama_stack/templates/tgi/run-with-safety.yaml:/root/my-run.yaml \
llamastack/distribution-dell \
--yaml-config /root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env TGI_URL=http://host.docker.internal:$INFERENCE_PORT \
--env SAFETY_MODEL=$SAFETY_MODEL \
--env TGI_SAFETY_URL=http://host.docker.internal:$SAFETY_PORT
```
### Via Conda
Make sure you have done `pip install llama-stack` and have the Llama Stack CLI available.
```bash
llama stack build --template dell --image-type conda
llama stack run ./run.yaml
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env TGI_URL=http://127.0.0.1:$INFERENCE_PORT
```
If you are using Llama Stack Safety / Shield APIs, use:
```bash
llama stack run ./run-with-safety.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env TGI_URL=http://127.0.0.1:$INFERENCE_PORT \
--env SAFETY_MODEL=$SAFETY_MODEL \
--env TGI_SAFETY_URL=http://127.0.0.1:$SAFETY_PORT
```

2
docs/source/distributions/self_hosted_distro/meta-reference-gpu.md
View file

@ -82,7 +82,7 @@ docker run \
### Via Conda
Make sure you have done `pip install llama-stack` and have the Llama Stack CLI available.
Make sure you have done `uv pip install llama-stack` and have the Llama Stack CLI available.
```bash
llama stack build --template meta-reference-gpu --image-type conda

2
docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md
View file

@ -82,7 +82,7 @@ docker run \
### Via Conda
Make sure you have done `pip install llama-stack` and have the Llama Stack CLI available.
Make sure you have done `uv pip install llama-stack` and have the Llama Stack CLI available.
```bash
llama stack build --template meta-reference-quantized-gpu --image-type conda

2
docs/source/distributions/self_hosted_distro/ollama.md
View file

@ -101,7 +101,7 @@ docker run \
### Via Conda
Make sure you have done `pip install llama-stack` and have the Llama Stack CLI available.
Make sure you have done `uv pip install llama-stack` and have the Llama Stack CLI available.
```bash
export LLAMA_STACK_PORT=5001

2
docs/source/distributions/self_hosted_distro/remote-vllm.md
View file

@ -131,7 +131,7 @@ docker run \
### Via Conda
Make sure you have done `pip install llama-stack` and have the Llama Stack CLI available.
Make sure you have done `uv pip install llama-stack` and have the Llama Stack CLI available.
```bash
export INFERENCE_PORT=8000

2
docs/source/distributions/self_hosted_distro/tgi.md
View file

@ -122,7 +122,7 @@ docker run \
### Via Conda
Make sure you have done `pip install llama-stack` and have the Llama Stack CLI available.
Make sure you have done `uv pip install llama-stack` and have the Llama Stack CLI available.
```bash
llama stack build --template tgi --image-type conda

1
llama_stack/providers/remote/inference/nvidia/nvidia.py
View file

@ -26,6 +26,7 @@ from llama_stack.apis.inference import (
Message,
ResponseFormat,
ToolChoice,
ToolConfig,
)
from llama_stack.providers.utils.inference.model_registry import (
build_model_alias,

7
llama_stack/templates/dell/__init__.py Normal file
View file

@ -0,0 +1,7 @@
# 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 .dell import get_distribution_template # noqa: F401

32
llama_stack/templates/dell/build.yaml Normal file
View file

@ -0,0 +1,32 @@
version: '2'
distribution_spec:
description: Dell's distribution of Llama Stack. TGI inference via Dell's custom
container
providers:
inference:
- remote::tgi
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::code-interpreter
- inline::rag-runtime
image_type: conda

152
llama_stack/templates/dell/dell.py Normal file
View file

@ -0,0 +1,152 @@
# 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 pathlib import Path
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"],
"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::code-interpreter",
"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="${env.SAFETY_MODEL}",
provider_id="tgi1",
)
embedding_model = ModelInput(
model_id="all-MiniLM-L6-v2",
provider_id="sentence-transformers",
model_type=ModelType.embedding,
metadata={
"embedding_dimension": 384,
},
)
default_tool_groups = [
ToolGroupInput(
toolgroup_id="builtin::websearch",
provider_id="brave-search",
),
ToolGroupInput(
toolgroup_id="builtin::rag",
provider_id="rag-runtime",
),
ToolGroupInput(
toolgroup_id="builtin::code_interpreter",
provider_id="code-interpreter",
),
]
return DistributionTemplate(
name=name,
distro_type="self_hosted",
description="Dell's distribution of Llama Stack. TGI inference via Dell's custom container",
container_image=None,
template_path=Path(__file__).parent / "doc_template.md",
providers=providers,
default_models=[inference_model, embedding_model],
run_configs={
"run.yaml": RunConfigSettings(
provider_overrides={
"inference": [inference_provider, embedding_provider],
"vector_io": [chromadb_provider],
},
default_models=[inference_model, embedding_model],
default_tool_groups=default_tool_groups,
),
"run-with-safety.yaml": RunConfigSettings(
provider_overrides={
"inference": [
inference_provider,
safety_inference_provider,
embedding_provider,
],
"vector_io": [chromadb_provider],
},
default_models=[inference_model, safety_model, embedding_model],
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
default_tool_groups=default_tool_groups,
),
},
run_config_env_vars={
"DEH_URL": (
"http://0.0.0.0:8080",
"URL for the Dell inference server",
),
"DEH_SAFETY_URL": (
"http://0.0.0.0:8081",
"URL for the Dell safety inference server",
),
"CHROMA_URL": (
# http://host.containers.internal:8000 if running via docker
"http://0.0.0.0:8000",
"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",
),
},
)

133
llama_stack/templates/dell/doc_template.md Normal file
View file

@ -0,0 +1,133 @@
---
orphan: true
---
# Dell Distribution of Llama Stack
```{toctree}
:maxdepth: 2
:hidden:
self
```
The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations.
{{ providers_table }}
You can use this distribution if you have GPUs and want to run an independent TGI server container for running inference.
{% if run_config_env_vars %}
### Environment Variables
The following environment variables can be configured:
{% for var, (default_value, description) in run_config_env_vars.items() %}
- `{{ var }}`: {{ description }} (default: `{{ default_value }}`)
{% endfor %}
{% endif %}
## Setting up TGI server
Please check the [TGI Getting Started Guide](https://github.com/huggingface/text-generation-inference?tab=readme-ov-file#get-started) to get a TGI endpoint. Here is a sample script to start a TGI server locally via Docker:
```bash
export INFERENCE_PORT=8080
export INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
export CUDA_VISIBLE_DEVICES=0
docker run --rm -it \
-v $HOME/.cache/huggingface:/data \
-p $INFERENCE_PORT:$INFERENCE_PORT \
--gpus $CUDA_VISIBLE_DEVICES \
ghcr.io/huggingface/text-generation-inference:2.3.1 \
--dtype bfloat16 \
--usage-stats off \
--sharded false \
--cuda-memory-fraction 0.7 \
--model-id $INFERENCE_MODEL \
--port $INFERENCE_PORT
```
If you are using Llama Stack Safety / Shield APIs, then you will need to also run another instance of a TGI with a corresponding safety model like `meta-llama/Llama-Guard-3-1B` using a script like:
```bash
export SAFETY_PORT=8081
export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
export CUDA_VISIBLE_DEVICES=1
docker run --rm -it \
-v $HOME/.cache/huggingface:/data \
-p $SAFETY_PORT:$SAFETY_PORT \
--gpus $CUDA_VISIBLE_DEVICES \
ghcr.io/huggingface/text-generation-inference:2.3.1 \
--dtype bfloat16 \
--usage-stats off \
--sharded false \
--model-id $SAFETY_MODEL \
--port $SAFETY_PORT
```
## Running Llama Stack
Now you are ready to run Llama Stack with TGI as the inference provider. You can do this via Conda (build code) or Docker which has a pre-built image.
### Via Docker
This method allows you to get started quickly without having to build the distribution code.
```bash
LLAMA_STACK_PORT=5001
docker run \
-it \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env TGI_URL=http://host.docker.internal:$INFERENCE_PORT
```
If you are using Llama Stack Safety / Shield APIs, use:
```bash
# You need a local checkout of llama-stack to run this, get it using
# git clone https://github.com/meta-llama/llama-stack.git
cd /path/to/llama-stack
docker run \
-it \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
-v ./llama_stack/templates/tgi/run-with-safety.yaml:/root/my-run.yaml \
llamastack/distribution-{{ name }} \
--yaml-config /root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env TGI_URL=http://host.docker.internal:$INFERENCE_PORT \
--env SAFETY_MODEL=$SAFETY_MODEL \
--env TGI_SAFETY_URL=http://host.docker.internal:$SAFETY_PORT
```
### Via Conda
Make sure you have done `pip install llama-stack` and have the Llama Stack CLI available.
```bash
llama stack build --template {{ name }} --image-type conda
llama stack run ./run.yaml
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env TGI_URL=http://127.0.0.1:$INFERENCE_PORT
```
If you are using Llama Stack Safety / Shield APIs, use:
```bash
llama stack run ./run-with-safety.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env TGI_URL=http://127.0.0.1:$INFERENCE_PORT \
--env SAFETY_MODEL=$SAFETY_MODEL \
--env TGI_SAFETY_URL=http://127.0.0.1:$SAFETY_PORT
```

118
llama_stack/templates/dell/run-with-safety.yaml Normal file
View file

@ -0,0 +1,118 @@
version: '2'
image_name: dell
apis:
- agents
- datasetio
- eval
- inference
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
providers:
inference:
- provider_id: tgi0
provider_type: remote::tgi
config:
url: ${env.DEH_URL}
- provider_id: tgi1
provider_type: remote::tgi
config:
url: ${env.DEH_SAFETY_URL}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}
vector_io:
- provider_id: chromadb
provider_type: remote::chromadb
config:
url: ${env.CHROMA_URL}
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
persistence_store:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/agents_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/dell/trace_store.db}
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
- provider_id: localfs
provider_type: inline::localfs
config: {}
scoring:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: llm-as-judge
provider_type: inline::llm-as-judge
config: {}
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:}
tool_runtime:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:}
max_results: 3
- provider_id: tavily-search
provider_type: remote::tavily-search
config:
api_key: ${env.TAVILY_SEARCH_API_KEY:}
max_results: 3
- provider_id: code-interpreter
provider_type: inline::code-interpreter
config: {}
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/registry.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}
provider_id: tgi0
model_type: llm
- metadata: {}
model_id: ${env.SAFETY_MODEL}
provider_id: tgi1
model_type: llm
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
provider_id: sentence-transformers
model_type: embedding
shields:
- shield_id: ${env.SAFETY_MODEL}
vector_dbs: []
datasets: []
scoring_fns: []
eval_tasks: []
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: brave-search
- toolgroup_id: builtin::rag
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter

109
llama_stack/templates/dell/run.yaml Normal file
View file

@ -0,0 +1,109 @@
version: '2'
image_name: dell
apis:
- agents
- datasetio
- eval
- inference
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
providers:
inference:
- provider_id: tgi0
provider_type: remote::tgi
config:
url: ${env.DEH_URL}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}
vector_io:
- provider_id: chromadb
provider_type: remote::chromadb
config:
url: ${env.CHROMA_URL}
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
persistence_store:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/agents_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/dell/trace_store.db}
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
- provider_id: localfs
provider_type: inline::localfs
config: {}
scoring:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: llm-as-judge
provider_type: inline::llm-as-judge
config: {}
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:}
tool_runtime:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:}
max_results: 3
- provider_id: tavily-search
provider_type: remote::tavily-search
config:
api_key: ${env.TAVILY_SEARCH_API_KEY:}
max_results: 3
- provider_id: code-interpreter
provider_type: inline::code-interpreter
config: {}
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/registry.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}
provider_id: tgi0
model_type: llm
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
provider_id: sentence-transformers
model_type: embedding
shields: []
vector_dbs: []
datasets: []
scoring_fns: []
eval_tasks: []
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: brave-search
- toolgroup_id: builtin::rag
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter