phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-03 08:52:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Restrict the changes to the new preprocessing API only.

Browse source
This commit is contained in:
ilya-kolchinsky 2025-04-03 12:19:08 +02:00
parent 2008cd7921
commit 863f87aa15
90 changed files with 104 additions and 1138 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama_stack/templates/bedrock/bedrock.py
View file

@ -6,7 +6,6 @@
from pathlib import Path
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import Provider, ToolGroupInput
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.providers.remote.inference.bedrock.models import MODEL_ENTRIES
@ -34,7 +33,6 @@ def get_distribution_template() -> DistributionTemplate:
"inline::rag-runtime",
"remote::model-context-protocol",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
name = "bedrock"
vector_io_provider = Provider(
@ -63,17 +61,6 @@ def get_distribution_template() -> DistributionTemplate:
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
return DistributionTemplate(
name=name,
distro_type="self_hosted",
@ -89,7 +76,6 @@ def get_distribution_template() -> DistributionTemplate:
},
default_models=default_models,
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={

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

@ -29,7 +29,4 @@ distribution_spec:
- inline::code-interpreter
- inline::rag-runtime
- remote::model-context-protocol
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

14
llama_stack/templates/bedrock/run.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -97,13 +96,6 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/bedrock}/registry.db
@ -150,10 +142,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

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

@ -29,7 +29,4 @@ distribution_spec:
- remote::tavily-search
- inline::code-interpreter
- inline::rag-runtime
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

13
llama_stack/templates/cerebras/cerebras.py
View file

@ -7,7 +7,6 @@
from pathlib import Path
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupInput
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
@ -38,7 +37,6 @@ def get_distribution_template() -> DistributionTemplate:
"inline::code-interpreter",
"inline::rag-runtime",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
name = "cerebras"
@ -84,16 +82,6 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="code-interpreter",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
return DistributionTemplate(
name="cerebras",
@ -112,7 +100,6 @@ def get_distribution_template() -> DistributionTemplate:
default_models=default_models + [embedding_model],
default_shields=[],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={

14
llama_stack/templates/cerebras/run.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -100,13 +99,6 @@ providers:
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/cerebras}/registry.db
@ -148,10 +140,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

3
llama_stack/templates/ci-tests/build.yaml
View file

@ -30,7 +30,4 @@ distribution_spec:
- inline::code-interpreter
- inline::rag-runtime
- remote::model-context-protocol
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

13
llama_stack/templates/ci-tests/ci_tests.py
View file

@ -6,7 +6,6 @@
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import (
ModelInput,
Provider,
@ -45,7 +44,6 @@ def get_distribution_template() -> DistributionTemplate:
"inline::rag-runtime",
"remote::model-context-protocol",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
name = "ci-tests"
inference_provider = Provider(
@ -78,16 +76,6 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="code-interpreter",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
available_models = {
"fireworks": MODEL_ENTRIES,
}
@ -117,7 +105,6 @@ def get_distribution_template() -> DistributionTemplate:
},
default_models=default_models + [embedding_model],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
),
},

14
llama_stack/templates/ci-tests/run.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -100,13 +99,6 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ci-tests}/registry.db
@ -226,10 +218,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

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

@ -30,7 +30,4 @@ distribution_spec:
- remote::tavily-search
- inline::code-interpreter
- inline::rag-runtime
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

14
llama_stack/templates/dell/dell.py
View file

@ -5,7 +5,6 @@
# the root directory of this source tree.
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import (
ModelInput,
Provider,
@ -34,7 +33,6 @@ def get_distribution_template() -> DistributionTemplate:
"inline::code-interpreter",
"inline::rag-runtime",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
name = "dell"
inference_provider = Provider(
@ -94,16 +92,6 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="code-interpreter",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
return DistributionTemplate(
name=name,
@ -119,7 +107,6 @@ def get_distribution_template() -> DistributionTemplate:
},
default_models=[inference_model, embedding_model],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
"run-with-safety.yaml": RunConfigSettings(
provider_overrides={
@ -133,7 +120,6 @@ def get_distribution_template() -> DistributionTemplate:
default_models=[inference_model, safety_model, embedding_model],
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={

14
llama_stack/templates/dell/run-with-safety.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -100,13 +99,6 @@ providers:
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/registry.db
@ -137,10 +129,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

14
llama_stack/templates/dell/run.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -96,13 +95,6 @@ providers:
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/registry.db
@ -128,10 +120,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

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

@ -34,7 +34,4 @@ distribution_spec:
- inline::code-interpreter
- inline::rag-runtime
- remote::model-context-protocol
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

13
llama_stack/templates/dev/dev.py
View file

@ -7,7 +7,6 @@
from typing import List, Tuple
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import (
ModelInput,
Provider,
@ -112,7 +111,6 @@ def get_distribution_template() -> DistributionTemplate:
"inline::rag-runtime",
"remote::model-context-protocol",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
name = "dev"
@ -157,16 +155,6 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="code-interpreter",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
embedding_model = ModelInput(
model_id="all-MiniLM-L6-v2",
provider_id=embedding_provider.provider_id,
@ -193,7 +181,6 @@ def get_distribution_template() -> DistributionTemplate:
},
default_models=default_models + [embedding_model],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
),
},

14
llama_stack/templates/dev/run.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -129,13 +128,6 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dev}/registry.db
@ -382,10 +374,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

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

@ -31,7 +31,4 @@ distribution_spec:
- inline::code-interpreter
- inline::rag-runtime
- remote::model-context-protocol
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

14
llama_stack/templates/fireworks/fireworks.py
View file

@ -7,7 +7,6 @@
from pathlib import Path
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import (
ModelInput,
Provider,
@ -45,7 +44,6 @@ def get_distribution_template() -> DistributionTemplate:
"inline::rag-runtime",
"remote::model-context-protocol",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
name = "fireworks"
@ -97,16 +95,6 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="code-interpreter",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
return DistributionTemplate(
name=name,
@ -125,7 +113,6 @@ def get_distribution_template() -> DistributionTemplate:
default_models=default_models + [embedding_model],
default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
"run-with-safety.yaml": RunConfigSettings(
provider_overrides={
@ -171,7 +158,6 @@ def get_distribution_template() -> DistributionTemplate:
),
],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={

14
llama_stack/templates/fireworks/run-with-safety.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -112,13 +111,6 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/registry.db
@ -245,10 +237,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

14
llama_stack/templates/fireworks/run.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -107,13 +106,6 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/registry.db
@ -235,10 +227,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

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

@ -26,7 +26,4 @@ distribution_spec:
- remote::tavily-search
- inline::code-interpreter
- inline::rag-runtime
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

13
llama_stack/templates/groq/groq.py
View file

@ -7,7 +7,6 @@
from pathlib import Path
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupInput
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
@ -37,7 +36,6 @@ def get_distribution_template() -> DistributionTemplate:
"inline::code-interpreter",
"inline::rag-runtime",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
name = "groq"
@ -79,16 +77,6 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="code-interpreter",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
return DistributionTemplate(
name=name,
@ -105,7 +93,6 @@ def get_distribution_template() -> DistributionTemplate:
},
default_models=default_models + [embedding_model],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={

14
llama_stack/templates/groq/run.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -100,13 +99,6 @@ providers:
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/registry.db
@ -173,10 +165,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

3
llama_stack/templates/hf-endpoint/build.yaml
View file

@ -29,7 +29,4 @@ distribution_spec:
- inline::code-interpreter
- inline::rag-runtime
- remote::model-context-protocol
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

14
llama_stack/templates/hf-endpoint/hf_endpoint.py
View file

@ -5,7 +5,6 @@
# the root directory of this source tree.
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import (
ModelInput,
Provider,
@ -37,7 +36,6 @@ def get_distribution_template() -> DistributionTemplate:
"inline::rag-runtime",
"remote::model-context-protocol",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
name = "hf-endpoint"
inference_provider = Provider(
@ -86,16 +84,6 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="code-interpreter",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
return DistributionTemplate(
name=name,
@ -112,7 +100,6 @@ def get_distribution_template() -> DistributionTemplate:
},
default_models=[inference_model, embedding_model],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
"run-with-safety.yaml": RunConfigSettings(
provider_overrides={
@ -136,7 +123,6 @@ def get_distribution_template() -> DistributionTemplate:
],
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={

14
llama_stack/templates/hf-endpoint/run-with-safety.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -108,13 +107,6 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/registry.db
@ -145,10 +137,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

14
llama_stack/templates/hf-endpoint/run.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -103,13 +102,6 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/registry.db
@ -135,10 +127,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

3
llama_stack/templates/hf-serverless/build.yaml
View file

@ -30,7 +30,4 @@ distribution_spec:
- inline::code-interpreter
- inline::rag-runtime
- remote::model-context-protocol
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

14
llama_stack/templates/hf-serverless/hf_serverless.py
View file

@ -5,7 +5,6 @@
# the root directory of this source tree.
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import (
ModelInput,
Provider,
@ -37,7 +36,6 @@ def get_distribution_template() -> DistributionTemplate:
"inline::rag-runtime",
"remote::model-context-protocol",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
name = "hf-serverless"
@ -87,16 +85,6 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="code-interpreter",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
return DistributionTemplate(
name=name,
@ -113,7 +101,6 @@ def get_distribution_template() -> DistributionTemplate:
},
default_models=[inference_model, embedding_model],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
"run-with-safety.yaml": RunConfigSettings(
provider_overrides={
@ -137,7 +124,6 @@ def get_distribution_template() -> DistributionTemplate:
],
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={

14
llama_stack/templates/hf-serverless/run-with-safety.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -108,13 +107,6 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/registry.db
@ -145,10 +137,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

14
llama_stack/templates/hf-serverless/run.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -103,13 +102,6 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/registry.db
@ -135,10 +127,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

3
llama_stack/templates/meta-reference-gpu/build.yaml
View file

@ -29,7 +29,4 @@ distribution_spec:
- inline::code-interpreter
- inline::rag-runtime
- remote::model-context-protocol
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

14
llama_stack/templates/meta-reference-gpu/meta_reference.py
View file

@ -7,7 +7,6 @@
from pathlib import Path
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import (
ModelInput,
Provider,
@ -41,7 +40,6 @@ def get_distribution_template() -> DistributionTemplate:
"inline::rag-runtime",
"remote::model-context-protocol",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
name = "meta-reference-gpu"
inference_provider = Provider(
@ -93,16 +91,6 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="code-interpreter",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
return DistributionTemplate(
name=name,
@ -118,7 +106,6 @@ def get_distribution_template() -> DistributionTemplate:
},
default_models=[inference_model, embedding_model],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
"run-with-safety.yaml": RunConfigSettings(
provider_overrides={
@ -143,7 +130,6 @@ def get_distribution_template() -> DistributionTemplate:
],
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={

14
llama_stack/templates/meta-reference-gpu/run-with-safety.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -110,13 +109,6 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/registry.db
@ -147,10 +139,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

14
llama_stack/templates/meta-reference-gpu/run.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -104,13 +103,6 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/registry.db
@ -136,10 +128,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

3
llama_stack/templates/meta-reference-quantized-gpu/build.yaml
View file

@ -29,7 +29,4 @@ distribution_spec:
- inline::code-interpreter
- inline::rag-runtime
- remote::model-context-protocol
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

13
llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py
View file

@ -7,7 +7,6 @@
from pathlib import Path
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupInput
from llama_stack.providers.inline.inference.meta_reference import (
MetaReferenceQuantizedInferenceConfig,
@ -36,7 +35,6 @@ def get_distribution_template() -> DistributionTemplate:
"inline::rag-runtime",
"remote::model-context-protocol",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
default_tool_groups = [
ToolGroupInput(
@ -52,16 +50,6 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="code-interpreter",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
name = "meta-reference-quantized-gpu"
inference_provider = Provider(
provider_id="meta-reference-inference",
@ -108,7 +96,6 @@ def get_distribution_template() -> DistributionTemplate:
},
default_models=[inference_model, embedding_model],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={

14
llama_stack/templates/meta-reference-quantized-gpu/run.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -106,13 +105,6 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/registry.db
@ -138,10 +130,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

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

@ -22,7 +22,4 @@ distribution_spec:
- inline::basic
tool_runtime:
- inline::rag-runtime
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

14
llama_stack/templates/nvidia/nvidia.py
View file

@ -6,7 +6,6 @@
from pathlib import Path
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput, ToolGroupInput
from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
from llama_stack.providers.remote.inference.nvidia.models import MODEL_ENTRIES
@ -26,7 +25,6 @@ def get_distribution_template() -> DistributionTemplate:
"datasetio": ["inline::localfs"],
"scoring": ["inline::basic"],
"tool_runtime": ["inline::rag-runtime"],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
inference_provider = Provider(
@ -57,16 +55,6 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="rag-runtime",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
default_models = get_model_registry(available_models)
return DistributionTemplate(
@ -84,7 +72,6 @@ def get_distribution_template() -> DistributionTemplate:
},
default_models=default_models,
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
"run-with-safety.yaml": RunConfigSettings(
provider_overrides={
@ -96,7 +83,6 @@ def get_distribution_template() -> DistributionTemplate:
default_models=[inference_model, safety_model],
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}", provider_id="nvidia")],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={

14
llama_stack/templates/nvidia/run-with-safety.yaml
View file

@ -6,7 +6,6 @@ apis:
- eval
- inference
- post_training
- preprocessing
- safety
- scoring
- telemetry
@ -85,13 +84,6 @@ providers:
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db
@ -114,10 +106,6 @@ benchmarks: []
tool_groups:
- toolgroup_id: builtin::rag
provider_id: rag-runtime
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

14
llama_stack/templates/nvidia/run.yaml
View file

@ -6,7 +6,6 @@ apis:
- eval
- inference
- post_training
- preprocessing
- safety
- scoring
- telemetry
@ -80,13 +79,6 @@ providers:
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db
@ -217,10 +209,6 @@ benchmarks: []
tool_groups:
- toolgroup_id: builtin::rag
provider_id: rag-runtime
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

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

@ -30,7 +30,4 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
- remote::wolfram-alpha
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

14
llama_stack/templates/ollama/ollama.py
View file

@ -7,7 +7,6 @@
from pathlib import Path
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import (
ModelInput,
Provider,
@ -37,7 +36,6 @@ def get_distribution_template() -> DistributionTemplate:
"remote::model-context-protocol",
"remote::wolfram-alpha",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
name = "ollama"
inference_provider = Provider(
@ -86,16 +84,6 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="wolfram-alpha",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
return DistributionTemplate(
name=name,
@ -112,7 +100,6 @@ def get_distribution_template() -> DistributionTemplate:
},
default_models=[inference_model, embedding_model],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
"run-with-safety.yaml": RunConfigSettings(
provider_overrides={
@ -147,7 +134,6 @@ def get_distribution_template() -> DistributionTemplate:
),
],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={

14
llama_stack/templates/ollama/run-with-safety.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -105,13 +104,6 @@ providers:
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/registry.db
@ -148,10 +140,6 @@ tool_groups:
provider_id: code-interpreter
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

14
llama_stack/templates/ollama/run.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -103,13 +102,6 @@ providers:
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/registry.db
@ -138,10 +130,6 @@ tool_groups:
provider_id: code-interpreter
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

3
llama_stack/templates/remote-vllm/build.yaml
View file

@ -31,7 +31,4 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
- remote::wolfram-alpha
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

14
llama_stack/templates/remote-vllm/run-with-safety.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -116,13 +115,6 @@ providers:
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db
@ -155,10 +147,6 @@ tool_groups:
provider_id: code-interpreter
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

14
llama_stack/templates/remote-vllm/run.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -109,13 +108,6 @@ providers:
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db
@ -143,10 +135,6 @@ tool_groups:
provider_id: code-interpreter
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

14
llama_stack/templates/remote-vllm/vllm.py
View file

@ -7,7 +7,6 @@
from pathlib import Path
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import (
ModelInput,
Provider,
@ -40,7 +39,6 @@ def get_distribution_template() -> DistributionTemplate:
"remote::model-context-protocol",
"remote::wolfram-alpha",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
name = "remote-vllm"
inference_provider = Provider(
@ -95,16 +93,6 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="wolfram-alpha",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
return DistributionTemplate(
name=name,
@ -120,7 +108,6 @@ def get_distribution_template() -> DistributionTemplate:
},
default_models=[inference_model, embedding_model],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
"run-with-safety.yaml": RunConfigSettings(
provider_overrides={
@ -144,7 +131,6 @@ def get_distribution_template() -> DistributionTemplate:
],
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={

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

@ -19,7 +19,4 @@ distribution_spec:
- remote::tavily-search
- inline::code-interpreter
- inline::rag-runtime
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

14
llama_stack/templates/sambanova/run.yaml
View file

@ -3,7 +3,6 @@ image_name: sambanova
apis:
- agents
- inference
- preprocessing
- safety
- telemetry
- tool_runtime
@ -72,13 +71,6 @@ providers:
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/sambanova}/registry.db
@ -186,10 +178,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

13
llama_stack/templates/sambanova/sambanova.py
View file

@ -6,7 +6,6 @@
from pathlib import Path
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import Provider, ShieldInput, ToolGroupInput
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
from llama_stack.providers.remote.inference.sambanova import SambaNovaImplConfig
@ -35,7 +34,6 @@ def get_distribution_template() -> DistributionTemplate:
"inline::code-interpreter",
"inline::rag-runtime",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
name = "sambanova"
@ -87,16 +85,6 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="code-interpreter",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
return DistributionTemplate(
name=name,
@ -115,7 +103,6 @@ def get_distribution_template() -> DistributionTemplate:
default_models=default_models,
default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={

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

@ -30,7 +30,4 @@ distribution_spec:
- inline::code-interpreter
- inline::rag-runtime
- remote::model-context-protocol
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

14
llama_stack/templates/tgi/run-with-safety.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -103,13 +102,6 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/registry.db
@ -135,10 +127,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

14
llama_stack/templates/tgi/run.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -102,13 +101,6 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/registry.db
@ -134,10 +126,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

14
llama_stack/templates/tgi/tgi.py
View file

@ -7,7 +7,6 @@
from pathlib import Path
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import (
ModelInput,
Provider,
@ -39,7 +38,6 @@ def get_distribution_template() -> DistributionTemplate:
"inline::rag-runtime",
"remote::model-context-protocol",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
name = "tgi"
inference_provider = Provider(
@ -90,16 +88,6 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="code-interpreter",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
return DistributionTemplate(
name=name,
@ -116,7 +104,6 @@ def get_distribution_template() -> DistributionTemplate:
},
default_models=[inference_model, embedding_model],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
"run-with-safety.yaml": RunConfigSettings(
provider_overrides={
@ -138,7 +125,6 @@ def get_distribution_template() -> DistributionTemplate:
],
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={

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

@ -31,7 +31,4 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
- remote::wolfram-alpha
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

14
llama_stack/templates/together/run-with-safety.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -112,13 +111,6 @@ providers:
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/registry.db
@ -252,10 +244,6 @@ tool_groups:
provider_id: code-interpreter
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

14
llama_stack/templates/together/run.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -107,13 +106,6 @@ providers:
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/registry.db
@ -242,10 +234,6 @@ tool_groups:
provider_id: code-interpreter
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

14
llama_stack/templates/together/together.py
View file

@ -7,7 +7,6 @@
from pathlib import Path
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import (
ModelInput,
Provider,
@ -45,7 +44,6 @@ def get_distribution_template() -> DistributionTemplate:
"remote::model-context-protocol",
"remote::wolfram-alpha",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
name = "together"
inference_provider = Provider(
@ -85,16 +83,6 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="wolfram-alpha",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
embedding_model = ModelInput(
model_id="all-MiniLM-L6-v2",
provider_id="sentence-transformers",
@ -120,7 +108,6 @@ def get_distribution_template() -> DistributionTemplate:
},
default_models=default_models + [embedding_model],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
),
"run-with-safety.yaml": RunConfigSettings(
@ -167,7 +154,6 @@ def get_distribution_template() -> DistributionTemplate:
),
],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={

3
llama_stack/templates/vllm-gpu/build.yaml
View file

@ -30,7 +30,4 @@ distribution_spec:
- inline::code-interpreter
- inline::rag-runtime
- remote::model-context-protocol
preprocessing:
- inline::basic
- inline::simple_chunking
image_type: conda

14
llama_stack/templates/vllm-gpu/run.yaml
View file

@ -5,7 +5,6 @@ apis:
- datasetio
- eval
- inference
- preprocessing
- safety
- scoring
- telemetry
@ -107,13 +106,6 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: simple_chunking
provider_type: inline::simple_chunking
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/vllm-gpu}/registry.db
@ -139,10 +131,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic
- preprocessor_id: builtin::chunking
provider_id: simple_chunking
preprocessors: []
server:
port: 8321

13
llama_stack/templates/vllm-gpu/vllm.py
View file

@ -5,7 +5,6 @@
# the root directory of this source tree.
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import ModelInput, Provider
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
@ -36,7 +35,6 @@ def get_distribution_template() -> DistributionTemplate:
"inline::rag-runtime",
"remote::model-context-protocol",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
name = "vllm-gpu"
@ -82,16 +80,6 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="code-interpreter",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
return DistributionTemplate(
name=name,
@ -108,7 +96,6 @@ def get_distribution_template() -> DistributionTemplate:
},
default_models=[inference_model, embedding_model],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={