llama-stack-mirror/llama_stack/templates/cerebras/run.yaml
Xi Yan 38009631bc
Remove llama-guard in Cerebras template & improve agent test (#798)
# What does this PR do?

- fix cerebras template
- fix agent test case without shields

## Test Plan

<img width="1261" alt="image"
src="https://github.com/user-attachments/assets/04381f85-9192-4fc6-984b-c9bec99bdb82"
/>

```
llama stack run ./llama_stack/templates/cerebras/run.yaml 

LLAMA_STACK_BASE_URL="http://localhost:8321" pytest -v tests/client-sdk/ --html=report.html --self-contained-html
```

## Sources

Please link relevant resources if necessary.


## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.
2025-01-16 18:11:35 -08:00

119 lines
3.1 KiB
YAML

version: '2'
image_name: cerebras
apis:
- agents
- datasetio
- eval
- inference
- memory
- safety
- scoring
- telemetry
- tool_runtime
providers:
inference:
- provider_id: cerebras
provider_type: remote::cerebras
config:
base_url: https://api.cerebras.ai
api_key: ${env.CEREBRAS_API_KEY}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
config: {}
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
memory:
- provider_id: faiss
provider_type: inline::faiss
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/cerebras}/faiss_store.db
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
persistence_store:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/cerebras}/agents_store.db
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
- provider_id: localfs
provider_type: inline::localfs
config: {}
scoring:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: llm-as-judge
provider_type: inline::llm-as-judge
config: {}
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:}
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/cerebras/trace_store.db}
tool_runtime:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:}
max_results: 3
- provider_id: tavily-search
provider_type: remote::tavily-search
config:
api_key: ${env.TAVILY_SEARCH_API_KEY:}
max_results: 3
- provider_id: code-interpreter
provider_type: inline::code-interpreter
config: {}
- provider_id: memory-runtime
provider_type: inline::memory-runtime
config: {}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/cerebras}/registry.db
models:
- metadata: {}
model_id: meta-llama/Llama-3.1-8B-Instruct
provider_id: cerebras
provider_model_id: llama3.1-8b
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.3-70B-Instruct
provider_id: cerebras
provider_model_id: llama-3.3-70b
model_type: llm
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
provider_id: sentence-transformers
model_type: embedding
shields: []
memory_banks: []
datasets: []
scoring_fns: []
eval_tasks: []
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: tavily-search
- toolgroup_id: builtin::memory
provider_id: memory-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter