phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-27 22:11:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: Some missed env variable changes from PR 2490

Browse source 
Some templates were still using the old environment variable
substition syntax instead of the new one and were not getting
substituted properly.

Also, some places didn't handle the new None vs old empty string ("")
values that come from the conditional environment variable
substitution.

This gets the starter and remote-vllm distributions starting again,
and I tested various permutations of the starter as chroma and
pgvector needed some adjustments to their config classes to handle the
new possible `None` values. And, I had to tweak our `Provider` class
to also handle `None` values, for cases where we disable providers in
the starter config via environment variables.

This may not have caught everything that was missed, but I did grep
around quite a bit to try and find anything lingering.

Signed-off-by: Ben Browning <bbrownin@redhat.com>
This commit is contained in:
Ben Browning 2025-06-26 17:27:17 -04:00
parent 68d8f2186f
commit b69bfab019
19 changed files with 49 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

18
llama_stack/templates/experimental-post-training/run.yaml
View file

@ -24,7 +24,7 @@ providers:
- provider_id: ollama
provider_type: remote::ollama
config:
url: ${env.OLLAMA_URL:http://localhost:11434}
url: ${env.OLLAMA_URL:=http://localhost:11434}
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -32,7 +32,7 @@ providers:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/meta_reference_eval.db
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/meta_reference_eval.db
scoring:
- provider_id: basic
provider_type: inline::basic
@ -40,7 +40,7 @@ providers:
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:}
openai_api_key: ${env.OPENAI_API_KEY:+}
datasetio:
- provider_id: localfs
provider_type: inline::localfs
@ -48,14 +48,14 @@ providers:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/experimental-post-training}/localfs_datasetio.db
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/experimental-post-training}/localfs_datasetio.db
- provider_id: huggingface
provider_type: remote::huggingface
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/huggingface}/huggingface_datasetio.db
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/huggingface}/huggingface_datasetio.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -74,7 +74,7 @@ providers:
persistence_store:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/experimental-post-training}/agents_store.db
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/experimental-post-training}/agents_store.db
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
@ -86,19 +86,19 @@ providers:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/experimental-post-training}/faiss_store.db
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/experimental-post-training}/faiss_store.db
tool_runtime:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:}
api_key: ${env.BRAVE_SEARCH_API_KEY:+}
max_results: 3
metadata_store:
namespace: null
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/experimental-post-training}/registry.db
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/experimental-post-training}/registry.db
models: []
shields: []
vector_dbs: []

4
llama_stack/templates/meta-reference-gpu/meta_reference.py
View file

@ -46,7 +46,7 @@ def get_distribution_template() -> DistributionTemplate:
provider_type="inline::meta-reference",
config=MetaReferenceInferenceConfig.sample_run_config(
model="${env.INFERENCE_MODEL}",
checkpoint_dir="${env.INFERENCE_CHECKPOINT_DIR:null}",
checkpoint_dir="${env.INFERENCE_CHECKPOINT_DIR:=null}",
),
)
embedding_provider = Provider(
@ -112,7 +112,7 @@ def get_distribution_template() -> DistributionTemplate:
provider_type="inline::meta-reference",
config=MetaReferenceInferenceConfig.sample_run_config(
model="${env.SAFETY_MODEL}",
checkpoint_dir="${env.SAFETY_CHECKPOINT_DIR:null}",
checkpoint_dir="${env.SAFETY_CHECKPOINT_DIR:=null}",
),
),
],

4
llama_stack/templates/meta-reference-gpu/run-with-safety.yaml
View file

@ -16,7 +16,7 @@ providers:
provider_type: inline::meta-reference
config:
model: ${env.INFERENCE_MODEL}
checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:=null}
quantization:
type: ${env.QUANTIZATION_TYPE:=bf16}
model_parallel_size: ${env.MODEL_PARALLEL_SIZE:=0}
@ -29,7 +29,7 @@ providers:
provider_type: inline::meta-reference
config:
model: ${env.SAFETY_MODEL}
checkpoint_dir: ${env.SAFETY_CHECKPOINT_DIR:null}
checkpoint_dir: ${env.SAFETY_CHECKPOINT_DIR:=null}
quantization:
type: ${env.QUANTIZATION_TYPE:=bf16}
model_parallel_size: ${env.MODEL_PARALLEL_SIZE:=0}

2
llama_stack/templates/meta-reference-gpu/run.yaml
View file

@ -16,7 +16,7 @@ providers:
provider_type: inline::meta-reference
config:
model: ${env.INFERENCE_MODEL}
checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:=null}
quantization:
type: ${env.QUANTIZATION_TYPE:=bf16}
model_parallel_size: ${env.MODEL_PARALLEL_SIZE:=0}

10
llama_stack/templates/open-benchmark/open_benchmark.py
View file

@ -46,7 +46,7 @@ def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderMo
model_type=ModelType.llm,
)
],
OpenAIConfig.sample_run_config(api_key="${env.OPENAI_API_KEY:}"),
OpenAIConfig.sample_run_config(api_key="${env.OPENAI_API_KEY:+}"),
),
(
"anthropic",
@ -56,7 +56,7 @@ def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderMo
model_type=ModelType.llm,
)
],
AnthropicConfig.sample_run_config(api_key="${env.ANTHROPIC_API_KEY:}"),
AnthropicConfig.sample_run_config(api_key="${env.ANTHROPIC_API_KEY:+}"),
),
(
"gemini",
@ -66,17 +66,17 @@ def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderMo
model_type=ModelType.llm,
)
],
GeminiConfig.sample_run_config(api_key="${env.GEMINI_API_KEY:}"),
GeminiConfig.sample_run_config(api_key="${env.GEMINI_API_KEY:+}"),
),
(
"groq",
[],
GroqConfig.sample_run_config(api_key="${env.GROQ_API_KEY:}"),
GroqConfig.sample_run_config(api_key="${env.GROQ_API_KEY:+}"),
),
(
"together",
[],
TogetherImplConfig.sample_run_config(api_key="${env.TOGETHER_API_KEY:}"),
TogetherImplConfig.sample_run_config(api_key="${env.TOGETHER_API_KEY:+}"),
),
]
inference_providers = []

8
llama_stack/templates/open-benchmark/run.yaml
View file

@ -15,20 +15,20 @@ providers:
- provider_id: openai
provider_type: remote::openai
config:
api_key: ${env.OPENAI_API_KEY:}
api_key: ${env.OPENAI_API_KEY:+}
- provider_id: anthropic
provider_type: remote::anthropic
config:
api_key: ${env.ANTHROPIC_API_KEY:}
api_key: ${env.ANTHROPIC_API_KEY:+}
- provider_id: gemini
provider_type: remote::gemini
config:
api_key: ${env.GEMINI_API_KEY:}
api_key: ${env.GEMINI_API_KEY:+}
- provider_id: groq
provider_type: remote::groq
config:
url: https://api.groq.com
api_key: ${env.GROQ_API_KEY:}
api_key: ${env.GROQ_API_KEY:+}
- provider_id: together
provider_type: remote::together
config:

2
llama_stack/templates/postgres-demo/postgres_demo.py
View file

@ -29,7 +29,7 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="vllm-inference",
provider_type="remote::vllm",
config=VLLMInferenceAdapterConfig.sample_run_config(
url="${env.VLLM_URL:http://localhost:8000/v1}",
url="${env.VLLM_URL:=http://localhost:8000/v1}",
),
),
]

2
llama_stack/templates/postgres-demo/run.yaml
View file

@ -12,7 +12,7 @@ providers:
- provider_id: vllm-inference
provider_type: remote::vllm
config:
url: ${env.VLLM_URL:http://localhost:8000/v1}
url: ${env.VLLM_URL:=http://localhost:8000/v1}
max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
api_token: ${env.VLLM_API_TOKEN:=fake}
tls_verify: ${env.VLLM_TLS_VERIFY:=true}

2
llama_stack/templates/remote-vllm/run-with-safety.yaml
View file

@ -15,7 +15,7 @@ providers:
- provider_id: vllm-inference
provider_type: remote::vllm
config:
url: ${env.VLLM_URL:http://localhost:8000/v1}
url: ${env.VLLM_URL:=http://localhost:8000/v1}
max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
api_token: ${env.VLLM_API_TOKEN:=fake}
tls_verify: ${env.VLLM_TLS_VERIFY:=true}

2
llama_stack/templates/remote-vllm/run.yaml
View file

@ -15,7 +15,7 @@ providers:
- provider_id: vllm-inference
provider_type: remote::vllm
config:
url: ${env.VLLM_URL:http://localhost:8000/v1}
url: ${env.VLLM_URL:=http://localhost:8000/v1}
max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
api_token: ${env.VLLM_API_TOKEN:=fake}
tls_verify: ${env.VLLM_TLS_VERIFY:=true}

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

@ -44,7 +44,7 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="vllm-inference",
provider_type="remote::vllm",
config=VLLMInferenceAdapterConfig.sample_run_config(
url="${env.VLLM_URL:http://localhost:8000/v1}",
url="${env.VLLM_URL:=http://localhost:8000/v1}",
),
)
embedding_provider = Provider(

2
llama_stack/templates/starter/run.yaml
View file

@ -68,7 +68,7 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/faiss_store.db
- provider_id: ${env.ENABLE_SQLITE_VEC+sqlite-vec}
- provider_id: ${env.ENABLE_SQLITE_VEC:+sqlite-vec}
provider_type: inline::sqlite-vec
config:
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/sqlite_vec.db

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

@ -175,7 +175,7 @@ def get_distribution_template() -> DistributionTemplate:
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
),
Provider(
provider_id="${env.ENABLE_SQLITE_VEC+sqlite-vec}",
provider_id="${env.ENABLE_SQLITE_VEC:+sqlite-vec}",
provider_type="inline::sqlite-vec",
config=SQLiteVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
),