phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-01 11:20:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

pre-commit fixes

Browse source
This commit is contained in:
Chantal D Gama Rose 2025-03-14 13:56:05 -07:00
parent 967dd0aa08
commit 7e211f8553
314 changed files with 5574 additions and 11369 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/templates/bedrock/bedrock.py
View file

@ -34,7 +34,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
)
available_models = {

18
llama_stack/templates/bedrock/run.yaml
View file

@ -45,14 +45,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/bedrock}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/bedrock}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/bedrock}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic

2
llama_stack/templates/cerebras/cerebras.py
View file

@ -62,7 +62,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
)
default_tool_groups = [
ToolGroupInput(

21
llama_stack/templates/cerebras/run.yaml
View file

@ -23,7 +23,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
vector_io:
- provider_id: faiss
provider_type: inline::faiss
@ -43,14 +44,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/cerebras}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/cerebras}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/cerebras}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic

2
llama_stack/templates/ci-tests/ci_tests.py
View file

@ -48,7 +48,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="sqlite-vec",
provider_type="inline::sqlite-vec",
config=SQLiteVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=SQLiteVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
)
embedding_provider = Provider(
provider_id="sentence-transformers",

31
llama_stack/templates/ci-tests/run.yaml
View file

@ -28,7 +28,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -47,14 +48,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ci-tests}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ci-tests}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ci-tests}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
@ -120,16 +133,6 @@ models:
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p2-1b-instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p2-1b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-1B-Instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p2-1b-instruct
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
provider_id: fireworks

21
llama_stack/templates/dell/run-with-safety.yaml
View file

@ -31,7 +31,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -50,14 +51,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic

21
llama_stack/templates/dell/run.yaml
View file

@ -27,7 +27,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -46,14 +47,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic

2
llama_stack/templates/dev/dev.py
View file

@ -100,7 +100,7 @@ def get_distribution_template() -> DistributionTemplate:
Provider(
provider_id="sqlite-vec",
provider_type="inline::sqlite-vec",
config=SQLiteVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=SQLiteVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
),
Provider(
provider_id="${env.ENABLE_CHROMADB+chromadb}",

31
llama_stack/templates/dev/run.yaml
View file

@ -57,7 +57,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -76,14 +77,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dev}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dev}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dev}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
@ -178,16 +191,6 @@ models:
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p2-1b-instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p2-1b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-1B-Instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p2-1b-instruct
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
provider_id: fireworks

1
llama_stack/templates/fireworks/build.yaml
View file

@ -27,6 +27,7 @@ distribution_spec:
tool_runtime:
- remote::brave-search
- remote::tavily-search
- remote::wolfram-alpha
- inline::code-interpreter
- inline::rag-runtime
- remote::model-context-protocol

7
llama_stack/templates/fireworks/fireworks.py
View file

@ -35,6 +35,7 @@ def get_distribution_template() -> DistributionTemplate:
"tool_runtime": [
"remote::brave-search",
"remote::tavily-search",
"remote::wolfram-alpha",
"inline::code-interpreter",
"inline::rag-runtime",
"remote::model-context-protocol",
@ -56,7 +57,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
)
available_models = {
@ -77,6 +78,10 @@ def get_distribution_template() -> DistributionTemplate:
toolgroup_id="builtin::websearch",
provider_id="tavily-search",
),
ToolGroupInput(
toolgroup_id="builtin::wolfram_alpha",
provider_id="wolfram-alpha",
),
ToolGroupInput(
toolgroup_id="builtin::rag",
provider_id="rag-runtime",

34
llama_stack/templates/fireworks/run-with-safety.yaml
View file

@ -56,14 +56,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
@ -86,6 +98,10 @@ providers:
config:
api_key: ${env.TAVILY_SEARCH_API_KEY:}
max_results: 3
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
- provider_id: code-interpreter
provider_type: inline::code-interpreter
config: {}
@ -129,16 +145,6 @@ models:
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p2-1b-instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p2-1b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-1B-Instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p2-1b-instruct
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
provider_id: fireworks
@ -225,6 +231,8 @@ benchmarks: []
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: tavily-search
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
- toolgroup_id: builtin::rag
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter

37
llama_stack/templates/fireworks/run.yaml
View file

@ -31,7 +31,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -50,14 +51,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
@ -80,6 +93,10 @@ providers:
config:
api_key: ${env.TAVILY_SEARCH_API_KEY:}
max_results: 3
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
- provider_id: code-interpreter
provider_type: inline::code-interpreter
config: {}
@ -123,16 +140,6 @@ models:
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p2-1b-instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p2-1b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.2-1B-Instruct
provider_id: fireworks
provider_model_id: accounts/fireworks/models/llama-v3p2-1b-instruct
model_type: llm
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
provider_id: fireworks
@ -214,6 +221,8 @@ benchmarks: []
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: tavily-search
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
- toolgroup_id: builtin::rag
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter

21
llama_stack/templates/groq/run.yaml
View file

@ -31,7 +31,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -50,14 +51,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic

2
llama_stack/templates/hf-endpoint/hf_endpoint.py
View file

@ -51,7 +51,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
)
inference_model = ModelInput(

21
llama_stack/templates/hf-endpoint/run-with-safety.yaml
View file

@ -36,7 +36,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -55,14 +56,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic

21
llama_stack/templates/hf-endpoint/run.yaml
View file

@ -31,7 +31,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -50,14 +51,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic

2
llama_stack/templates/hf-serverless/hf_serverless.py
View file

@ -52,7 +52,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
)
inference_model = ModelInput(

21
llama_stack/templates/hf-serverless/run-with-safety.yaml
View file

@ -36,7 +36,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -55,14 +56,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic

21
llama_stack/templates/hf-serverless/run.yaml
View file

@ -31,7 +31,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -50,14 +51,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic

2
llama_stack/templates/meta-reference-gpu/meta_reference.py
View file

@ -58,7 +58,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
)
inference_model = ModelInput(

21
llama_stack/templates/meta-reference-gpu/run-with-safety.yaml
View file

@ -38,7 +38,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -57,14 +58,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic

21
llama_stack/templates/meta-reference-gpu/run.yaml
View file

@ -32,7 +32,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -51,14 +52,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic

2
llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py
View file

@ -67,7 +67,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
)
inference_model = ModelInput(

21
llama_stack/templates/meta-reference-quantized-gpu/run.yaml
View file

@ -34,7 +34,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -53,14 +54,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic

12
llama_stack/templates/nvidia/run-with-safety.yaml
View file

@ -54,11 +54,19 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/meta_reference_eval.db
datasetio:
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic

12
llama_stack/templates/nvidia/run.yaml
View file

@ -49,11 +49,19 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/meta_reference_eval.db
datasetio:
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic

3
llama_stack/templates/ollama/build.yaml
View file

@ -5,7 +5,7 @@ distribution_spec:
inference:
- remote::ollama
vector_io:
- inline::sqlite-vec
- inline::faiss
- remote::chromadb
- remote::pgvector
safety:
@ -29,4 +29,5 @@ distribution_spec:
- inline::code-interpreter
- inline::rag-runtime
- remote::model-context-protocol
- remote::wolfram-alpha
image_type: conda

2
llama_stack/templates/ollama/doc_template.md
View file

@ -119,7 +119,7 @@ llama stack run ./run-with-safety.yaml \
### (Optional) Update Model Serving Configuration
```{note}
Please check the [model_entries](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/inference/ollama/ollama.py#L45) for the supported Ollama models.
Please check the [model_entries](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/inference/ollama/models.py) for the supported Ollama models.
```
To serve a new model with `ollama`

21
llama_stack/templates/ollama/ollama.py
View file

@ -13,7 +13,7 @@ from llama_stack.distribution.datatypes import (
ShieldInput,
ToolGroupInput,
)
from llama_stack.providers.inline.vector_io.sqlite_vec.config import SQLiteVectorIOConfig
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.providers.remote.inference.ollama import OllamaImplConfig
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -21,7 +21,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
def get_distribution_template() -> DistributionTemplate:
providers = {
"inference": ["remote::ollama"],
"vector_io": ["inline::sqlite-vec", "remote::chromadb", "remote::pgvector"],
"vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
"safety": ["inline::llama-guard"],
"agents": ["inline::meta-reference"],
"telemetry": ["inline::meta-reference"],
@ -34,6 +34,7 @@ def get_distribution_template() -> DistributionTemplate:
"inline::code-interpreter",
"inline::rag-runtime",
"remote::model-context-protocol",
"remote::wolfram-alpha",
],
}
name = "ollama"
@ -42,10 +43,10 @@ def get_distribution_template() -> DistributionTemplate:
provider_type="remote::ollama",
config=OllamaImplConfig.sample_run_config(),
)
vector_io_provider_sqlite = Provider(
provider_id="sqlite-vec",
provider_type="inline::sqlite-vec",
config=SQLiteVectorIOConfig.sample_run_config(f"distributions/{name}"),
vector_io_provider_faiss = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
)
inference_model = ModelInput(
@ -78,6 +79,10 @@ def get_distribution_template() -> DistributionTemplate:
toolgroup_id="builtin::code_interpreter",
provider_id="code-interpreter",
),
ToolGroupInput(
toolgroup_id="builtin::wolfram_alpha",
provider_id="wolfram-alpha",
),
]
return DistributionTemplate(
@ -91,7 +96,7 @@ def get_distribution_template() -> DistributionTemplate:
"run.yaml": RunConfigSettings(
provider_overrides={
"inference": [inference_provider],
"vector_io": [vector_io_provider_sqlite],
"vector_io": [vector_io_provider_faiss],
},
default_models=[inference_model, embedding_model],
default_tool_groups=default_tool_groups,
@ -99,7 +104,7 @@ def get_distribution_template() -> DistributionTemplate:
"run-with-safety.yaml": RunConfigSettings(
provider_overrides={
"inference": [inference_provider],
"vector_io": [vector_io_provider_sqlite],
"vector_io": [vector_io_provider_faiss],
"safety": [
Provider(
provider_id="llama-guard",

33
llama_stack/templates/ollama/run-with-safety.yaml
View file

@ -17,10 +17,13 @@ providers:
config:
url: ${env.OLLAMA_URL:http://localhost:11434}
vector_io:
- provider_id: sqlite-vec
provider_type: inline::sqlite-vec
- provider_id: faiss
provider_type: inline::faiss
config:
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/sqlite_vec.db
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/faiss_store.db
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
@ -46,14 +49,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
@ -85,6 +100,10 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/registry.db
@ -119,5 +138,7 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
server:
port: 8321

36
llama_stack/templates/ollama/run.yaml
View file

@ -17,14 +17,18 @@ providers:
config:
url: ${env.OLLAMA_URL:http://localhost:11434}
vector_io:
- provider_id: sqlite-vec
provider_type: inline::sqlite-vec
- provider_id: faiss
provider_type: inline::faiss
config:
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/sqlite_vec.db
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/faiss_store.db
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -43,14 +47,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
@ -82,6 +98,10 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/registry.db
@ -108,5 +128,7 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
server:
port: 8321

1
llama_stack/templates/remote-vllm/build.yaml
View file

@ -30,4 +30,5 @@ distribution_spec:
- inline::code-interpreter
- inline::rag-runtime
- remote::model-context-protocol
- remote::wolfram-alpha
image_type: conda

27
llama_stack/templates/remote-vllm/run-with-safety.yaml
View file

@ -38,7 +38,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -50,14 +51,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
@ -96,6 +109,10 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db
@ -126,5 +143,7 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
server:
port: 8321

27
llama_stack/templates/remote-vllm/run.yaml
View file

@ -32,7 +32,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -44,14 +45,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
@ -90,6 +103,10 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db
@ -115,5 +132,7 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
server:
port: 8321

7
llama_stack/templates/remote-vllm/vllm.py
View file

@ -37,6 +37,7 @@ def get_distribution_template() -> DistributionTemplate:
"inline::code-interpreter",
"inline::rag-runtime",
"remote::model-context-protocol",
"remote::wolfram-alpha",
],
}
name = "remote-vllm"
@ -55,7 +56,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
)
inference_model = ModelInput(
@ -87,6 +88,10 @@ def get_distribution_template() -> DistributionTemplate:
toolgroup_id="builtin::code_interpreter",
provider_id="code-interpreter",
),
ToolGroupInput(
toolgroup_id="builtin::wolfram_alpha",
provider_id="wolfram-alpha",
),
]
return DistributionTemplate(

3
llama_stack/templates/sambanova/run.yaml
View file

@ -37,7 +37,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference

2
llama_stack/templates/sambanova/sambanova.py
View file

@ -46,7 +46,7 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(
__distro_dir__=f"distributions/{name}",
__distro_dir__=f"~/.llama/distributions/{name}",
),
),
Provider(

16
llama_stack/templates/template.py
View file

@ -14,7 +14,9 @@ from pydantic import BaseModel, Field
from llama_stack.apis.models.models import ModelType
from llama_stack.distribution.datatypes import (
Api,
BenchmarkInput,
BuildConfig,
DatasetInput,
DistributionSpec,
ModelInput,
Provider,
@ -28,7 +30,9 @@ from llama_stack.providers.utils.inference.model_registry import ProviderModelEn
from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
def get_model_registry(available_models: Dict[str, List[ProviderModelEntry]]) -> List[ModelInput]:
def get_model_registry(
available_models: Dict[str, List[ProviderModelEntry]],
) -> List[ModelInput]:
models = []
for provider_id, entries in available_models.items():
for entry in entries:
@ -56,6 +60,8 @@ class RunConfigSettings(BaseModel):
default_models: Optional[List[ModelInput]] = None
default_shields: Optional[List[ShieldInput]] = None
default_tool_groups: Optional[List[ToolGroupInput]] = None
default_datasets: Optional[List[DatasetInput]] = None
default_benchmarks: Optional[List[BenchmarkInput]] = None
def run_config(
self,
@ -86,7 +92,7 @@ class RunConfigSettings(BaseModel):
config_class = instantiate_class_type(config_class)
if hasattr(config_class, "sample_run_config"):
config = config_class.sample_run_config(__distro_dir__=f"distributions/{name}")
config = config_class.sample_run_config(__distro_dir__=f"~/.llama/distributions/{name}")
else:
config = {}
@ -107,12 +113,14 @@ class RunConfigSettings(BaseModel):
apis=apis,
providers=provider_configs,
metadata_store=SqliteKVStoreConfig.sample_run_config(
__distro_dir__=f"distributions/{name}",
__distro_dir__=f"~/.llama/distributions/{name}",
db_name="registry.db",
),
models=self.default_models or [],
shields=self.default_shields or [],
tool_groups=self.default_tool_groups or [],
datasets=self.default_datasets or [],
benchmarks=self.default_benchmarks or [],
)
@ -187,7 +195,7 @@ class DistributionTemplate(BaseModel):
default_models.append(
DefaultModel(
model_id=model_entry.provider_model_id,
doc_string=f"({' -- '.join(doc_parts)})" if doc_parts else "",
doc_string=(f"({' -- '.join(doc_parts)})" if doc_parts else ""),
)
)

21
llama_stack/templates/tgi/run-with-safety.yaml
View file

@ -31,7 +31,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -50,14 +51,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic

21
llama_stack/templates/tgi/run.yaml
View file

@ -30,7 +30,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -49,14 +50,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic

4
llama_stack/templates/tgi/tgi.py
View file

@ -55,7 +55,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
)
inference_model = ModelInput(
@ -137,7 +137,7 @@ def get_distribution_template() -> DistributionTemplate:
"Inference model loaded into the TGI server",
),
"TGI_URL": (
"http://127.0.0.1:8080}/v1",
"http://127.0.0.1:8080/v1",
"URL of the TGI server with the main inference model",
),
"TGI_SAFETY_URL": (

1
llama_stack/templates/together/build.yaml
View file

@ -30,4 +30,5 @@ distribution_spec:
- inline::code-interpreter
- inline::rag-runtime
- remote::model-context-protocol
- remote::wolfram-alpha
image_type: conda

26
llama_stack/templates/together/run-with-safety.yaml
View file

@ -16,7 +16,7 @@ providers:
provider_type: remote::together
config:
url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY}
api_key: ${env.TOGETHER_API_KEY:}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}
@ -56,14 +56,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
@ -95,6 +107,10 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/registry.db
@ -226,5 +242,7 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
server:
port: 8321

29
llama_stack/templates/together/run.yaml
View file

@ -16,7 +16,7 @@ providers:
provider_type: remote::together
config:
url: https://api.together.xyz/v1
api_key: ${env.TOGETHER_API_KEY}
api_key: ${env.TOGETHER_API_KEY:}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}
@ -31,7 +31,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -50,14 +51,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
@ -89,6 +102,10 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/registry.db
@ -215,5 +232,7 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
server:
port: 8321

7
llama_stack/templates/together/together.py
View file

@ -38,6 +38,7 @@ def get_distribution_template() -> DistributionTemplate:
"inline::code-interpreter",
"inline::rag-runtime",
"remote::model-context-protocol",
"remote::wolfram-alpha",
],
}
name = "together"
@ -49,7 +50,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
)
embedding_provider = Provider(
provider_id="sentence-transformers",
@ -73,6 +74,10 @@ def get_distribution_template() -> DistributionTemplate:
toolgroup_id="builtin::code_interpreter",
provider_id="code-interpreter",
),
ToolGroupInput(
toolgroup_id="builtin::wolfram_alpha",
provider_id="wolfram-alpha",
),
]
embedding_model = ModelInput(
model_id="all-MiniLM-L6-v2",

26
llama_stack/templates/vllm-gpu/run.yaml
View file

@ -15,11 +15,12 @@ providers:
- provider_id: vllm
provider_type: inline::vllm
config:
model: ${env.INFERENCE_MODEL:Llama3.2-3B-Instruct}
tensor_parallel_size: ${env.TENSOR_PARALLEL_SIZE:1}
max_tokens: ${env.MAX_TOKENS:4096}
max_model_len: ${env.MAX_MODEL_LEN:4096}
max_num_seqs: ${env.MAX_NUM_SEQS:4}
enforce_eager: ${env.ENFORCE_EAGER:False}
gpu_memory_utilization: ${env.GPU_MEMORY_UTILIZATION:0.7}
gpu_memory_utilization: ${env.GPU_MEMORY_UTILIZATION:0.3}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}
@ -34,7 +35,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -53,14 +55,26 @@ providers:
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/vllm-gpu}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/vllm-gpu}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/vllm-gpu}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic

2
llama_stack/templates/vllm-gpu/vllm.py
View file

@ -46,7 +46,7 @@ def get_distribution_template() -> DistributionTemplate:
vector_io_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissVectorIOConfig.sample_run_config(f"distributions/{name}"),
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
)
embedding_provider = Provider(
provider_id="sentence-transformers",