mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-12 13:00:39 +00:00
Some checks failed
Integration Tests (Replay) / discover-tests (push) Successful in 9s
Python Package Build Test / build (3.12) (push) Failing after 4s
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 10s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 12s
Python Package Build Test / build (3.13) (push) Failing after 4s
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 10s
Test Llama Stack Build / generate-matrix (push) Successful in 8s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 13s
Test External API and Providers / test-external (venv) (push) Failing after 11s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 17s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 10s
Test Llama Stack Build / build-single-provider (push) Failing after 16s
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 8s
Unit Tests / unit-tests (3.12) (push) Failing after 10s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 26s
Vector IO Integration Tests / test-matrix (3.12, remote::qdrant) (push) Failing after 15s
Update ReadTheDocs / update-readthedocs (push) Failing after 9s
Integration Tests (Replay) / Integration Tests (, , , client=, vision=) (push) Failing after 7s
Vector IO Integration Tests / test-matrix (3.13, remote::weaviate) (push) Failing after 11s
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 23s
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 16s
Vector IO Integration Tests / test-matrix (3.12, remote::weaviate) (push) Failing after 18s
Test Llama Stack Build / build (push) Failing after 8s
Vector IO Integration Tests / test-matrix (3.13, remote::qdrant) (push) Failing after 17s
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 16s
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 8s
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 21s
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 47s
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 49s
Unit Tests / unit-tests (3.13) (push) Failing after 39s
Pre-commit / pre-commit (push) Successful in 1m37s
# What does this PR do? - Add new Vertex AI remote inference provider with litellm integration - Support for Gemini models through Google Cloud Vertex AI platform - Uses Google Cloud Application Default Credentials (ADC) for authentication - Added VertexAI models: gemini-2.5-flash, gemini-2.5-pro, gemini-2.0-flash. - Updated provider registry to include vertexai provider - Updated starter template to support Vertex AI configuration - Added comprehensive documentation and sample configuration <!-- If resolving an issue, uncomment and update the line below --> relates to https://github.com/meta-llama/llama-stack/issues/2747 ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> Signed-off-by: Eran Cohen <eranco@redhat.com> Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com>
228 lines
7.2 KiB
YAML
228 lines
7.2 KiB
YAML
version: 2
|
|
image_name: ci-tests
|
|
apis:
|
|
- agents
|
|
- datasetio
|
|
- eval
|
|
- files
|
|
- inference
|
|
- post_training
|
|
- safety
|
|
- scoring
|
|
- telemetry
|
|
- tool_runtime
|
|
- vector_io
|
|
providers:
|
|
inference:
|
|
- provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
|
|
provider_type: remote::cerebras
|
|
config:
|
|
base_url: https://api.cerebras.ai
|
|
api_key: ${env.CEREBRAS_API_KEY:=}
|
|
- provider_id: ${env.OLLAMA_URL:+ollama}
|
|
provider_type: remote::ollama
|
|
config:
|
|
url: ${env.OLLAMA_URL:=http://localhost:11434}
|
|
- provider_id: ${env.VLLM_URL:+vllm}
|
|
provider_type: remote::vllm
|
|
config:
|
|
url: ${env.VLLM_URL:=}
|
|
max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
|
|
api_token: ${env.VLLM_API_TOKEN:=fake}
|
|
tls_verify: ${env.VLLM_TLS_VERIFY:=true}
|
|
- provider_id: ${env.TGI_URL:+tgi}
|
|
provider_type: remote::tgi
|
|
config:
|
|
url: ${env.TGI_URL:=}
|
|
- provider_id: fireworks
|
|
provider_type: remote::fireworks
|
|
config:
|
|
url: https://api.fireworks.ai/inference/v1
|
|
api_key: ${env.FIREWORKS_API_KEY:=}
|
|
- provider_id: together
|
|
provider_type: remote::together
|
|
config:
|
|
url: https://api.together.xyz/v1
|
|
api_key: ${env.TOGETHER_API_KEY:=}
|
|
- provider_id: bedrock
|
|
provider_type: remote::bedrock
|
|
- provider_id: ${env.NVIDIA_API_KEY:+nvidia}
|
|
provider_type: remote::nvidia
|
|
config:
|
|
url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
|
|
api_key: ${env.NVIDIA_API_KEY:=}
|
|
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
|
|
- provider_id: openai
|
|
provider_type: remote::openai
|
|
config:
|
|
api_key: ${env.OPENAI_API_KEY:=}
|
|
base_url: ${env.OPENAI_BASE_URL:=https://api.openai.com/v1}
|
|
- provider_id: anthropic
|
|
provider_type: remote::anthropic
|
|
config:
|
|
api_key: ${env.ANTHROPIC_API_KEY:=}
|
|
- provider_id: gemini
|
|
provider_type: remote::gemini
|
|
config:
|
|
api_key: ${env.GEMINI_API_KEY:=}
|
|
- provider_id: ${env.VERTEX_AI_PROJECT:+vertexai}
|
|
provider_type: remote::vertexai
|
|
config:
|
|
project: ${env.VERTEX_AI_PROJECT:=}
|
|
location: ${env.VERTEX_AI_LOCATION:=us-central1}
|
|
- provider_id: groq
|
|
provider_type: remote::groq
|
|
config:
|
|
url: https://api.groq.com
|
|
api_key: ${env.GROQ_API_KEY:=}
|
|
- provider_id: sambanova
|
|
provider_type: remote::sambanova
|
|
config:
|
|
url: https://api.sambanova.ai/v1
|
|
api_key: ${env.SAMBANOVA_API_KEY:=}
|
|
- provider_id: sentence-transformers
|
|
provider_type: inline::sentence-transformers
|
|
vector_io:
|
|
- provider_id: faiss
|
|
provider_type: inline::faiss
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/faiss_store.db
|
|
- provider_id: sqlite-vec
|
|
provider_type: inline::sqlite-vec
|
|
config:
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/sqlite_vec.db
|
|
kvstore:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/sqlite_vec_registry.db
|
|
- provider_id: ${env.MILVUS_URL:+milvus}
|
|
provider_type: inline::milvus
|
|
config:
|
|
db_path: ${env.MILVUS_DB_PATH:=~/.llama/distributions/starter}/milvus.db
|
|
kvstore:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/milvus_registry.db
|
|
- provider_id: ${env.CHROMADB_URL:+chromadb}
|
|
provider_type: remote::chromadb
|
|
config:
|
|
url: ${env.CHROMADB_URL:=}
|
|
kvstore:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter/}/chroma_remote_registry.db
|
|
- provider_id: ${env.PGVECTOR_DB:+pgvector}
|
|
provider_type: remote::pgvector
|
|
config:
|
|
host: ${env.PGVECTOR_HOST:=localhost}
|
|
port: ${env.PGVECTOR_PORT:=5432}
|
|
db: ${env.PGVECTOR_DB:=}
|
|
user: ${env.PGVECTOR_USER:=}
|
|
password: ${env.PGVECTOR_PASSWORD:=}
|
|
kvstore:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/pgvector_registry.db
|
|
files:
|
|
- provider_id: meta-reference-files
|
|
provider_type: inline::localfs
|
|
config:
|
|
storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files}
|
|
metadata_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/files_metadata.db
|
|
safety:
|
|
- provider_id: llama-guard
|
|
provider_type: inline::llama-guard
|
|
config:
|
|
excluded_categories: []
|
|
agents:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
persistence_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/agents_store.db
|
|
responses_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/responses_store.db
|
|
telemetry:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
|
|
sinks: ${env.TELEMETRY_SINKS:=console,sqlite}
|
|
sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/trace_store.db
|
|
otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
|
|
post_training:
|
|
- provider_id: huggingface
|
|
provider_type: inline::huggingface
|
|
config:
|
|
checkpoint_format: huggingface
|
|
distributed_backend: null
|
|
device: cpu
|
|
dpo_output_dir: ~/.llama/distributions/ci-tests/dpo_output
|
|
eval:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/meta_reference_eval.db
|
|
datasetio:
|
|
- provider_id: huggingface
|
|
provider_type: remote::huggingface
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/huggingface_datasetio.db
|
|
- provider_id: localfs
|
|
provider_type: inline::localfs
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/localfs_datasetio.db
|
|
scoring:
|
|
- provider_id: basic
|
|
provider_type: inline::basic
|
|
- provider_id: llm-as-judge
|
|
provider_type: inline::llm-as-judge
|
|
- provider_id: braintrust
|
|
provider_type: inline::braintrust
|
|
config:
|
|
openai_api_key: ${env.OPENAI_API_KEY:=}
|
|
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: rag-runtime
|
|
provider_type: inline::rag-runtime
|
|
- provider_id: model-context-protocol
|
|
provider_type: remote::model-context-protocol
|
|
metadata_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/registry.db
|
|
inference_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/inference_store.db
|
|
models: []
|
|
shields:
|
|
- shield_id: llama-guard
|
|
provider_id: ${env.SAFETY_MODEL:+llama-guard}
|
|
provider_shield_id: ${env.SAFETY_MODEL:=}
|
|
vector_dbs: []
|
|
datasets: []
|
|
scoring_fns: []
|
|
benchmarks: []
|
|
tool_groups:
|
|
- toolgroup_id: builtin::websearch
|
|
provider_id: tavily-search
|
|
- toolgroup_id: builtin::rag
|
|
provider_id: rag-runtime
|
|
server:
|
|
port: 8321
|