phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 22:12:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'refs/heads/main' into preprocessors

Browse source 
# Conflicts:
#	llama_stack/distribution/routers/routers.py
#	llama_stack/templates/ollama/build.yaml
#	llama_stack/templates/ollama/run-with-safety.yaml
#	llama_stack/templates/ollama/run.yaml
#	llama_stack/templates/remote-vllm/build.yaml
#	llama_stack/templates/remote-vllm/run-with-safety.yaml
#	llama_stack/templates/remote-vllm/run.yaml
#	llama_stack/templates/together/build.yaml
#	llama_stack/templates/together/run-with-safety.yaml
#	llama_stack/templates/together/run.yaml
This commit is contained in:
ilya-kolchinsky 2025-03-07 16:20:30 +01:00
commit 6b9f673fdb
313 changed files with 181388 additions and 7064 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -30,6 +30,7 @@ distribution_spec:
- inline::code-interpreter
- inline::rag-runtime
- remote::model-context-protocol
- remote::wolfram-alpha
preprocessing:
- inline::basic
- inline::simple_chunking

5
llama_stack/templates/together/run-with-safety.yaml
View file

@ -96,6 +96,9 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
@ -234,6 +237,8 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic

5
llama_stack/templates/together/run.yaml
View file

@ -90,6 +90,9 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config: {}
preprocessing:
- provider_id: basic
provider_type: inline::basic
@ -223,6 +226,8 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
preprocessors:
- preprocessor_id: builtin::basic
provider_id: basic

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

@ -39,6 +39,7 @@ def get_distribution_template() -> DistributionTemplate:
"inline::code-interpreter",
"inline::rag-runtime",
"remote::model-context-protocol",
"remote::wolfram-alpha",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
@ -51,7 +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}"),
)
embedding_provider = Provider(
provider_id="sentence-transformers",
@ -75,6 +76,10 @@ def get_distribution_template() -> DistributionTemplate:
toolgroup_id="builtin::code_interpreter",
provider_id="code-interpreter",
),
ToolGroupInput(
toolgroup_id="builtin::wolfram_alpha",
provider_id="wolfram-alpha",
),
]
default_preprocessors = [
PreprocessorInput(