mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
# What does this PR do? This is not part of the official OpenAI API, but we'll use this for the logs UI. In order to support more filtering options, I'm adopting the newly introduced sql store in in place of the kv store. ## Test Plan Added integration/unit tests.
210 lines
5.9 KiB
YAML
210 lines
5.9 KiB
YAML
version: '2'
|
|
image_name: groq
|
|
apis:
|
|
- agents
|
|
- datasetio
|
|
- eval
|
|
- inference
|
|
- safety
|
|
- scoring
|
|
- telemetry
|
|
- tool_runtime
|
|
- vector_io
|
|
providers:
|
|
inference:
|
|
- provider_id: groq
|
|
provider_type: remote::groq
|
|
config:
|
|
url: https://api.groq.com
|
|
api_key: ${env.GROQ_API_KEY}
|
|
- provider_id: sentence-transformers
|
|
provider_type: inline::sentence-transformers
|
|
config: {}
|
|
vector_io:
|
|
- provider_id: faiss
|
|
provider_type: inline::faiss
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/faiss_store.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
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/agents_store.db
|
|
responses_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/responses_store.db
|
|
telemetry:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
service_name: ${env.OTEL_SERVICE_NAME:}
|
|
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
|
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/trace_store.db
|
|
eval:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/meta_reference_eval.db
|
|
datasetio:
|
|
- provider_id: huggingface
|
|
provider_type: remote::huggingface
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/huggingface_datasetio.db
|
|
- provider_id: localfs
|
|
provider_type: inline::localfs
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/localfs_datasetio.db
|
|
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:}
|
|
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
|
|
config: {}
|
|
metadata_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/registry.db
|
|
inference_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/inference_store.db
|
|
models:
|
|
- metadata: {}
|
|
model_id: groq/llama3-8b-8192
|
|
provider_id: groq
|
|
provider_model_id: groq/llama3-8b-8192
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.1-8B-Instruct
|
|
provider_id: groq
|
|
provider_model_id: groq/llama3-8b-8192
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: groq/llama-3.1-8b-instant
|
|
provider_id: groq
|
|
provider_model_id: groq/llama-3.1-8b-instant
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: groq/llama3-70b-8192
|
|
provider_id: groq
|
|
provider_model_id: groq/llama3-70b-8192
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3-70B-Instruct
|
|
provider_id: groq
|
|
provider_model_id: groq/llama3-70b-8192
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: groq/llama-3.3-70b-versatile
|
|
provider_id: groq
|
|
provider_model_id: groq/llama-3.3-70b-versatile
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.3-70B-Instruct
|
|
provider_id: groq
|
|
provider_model_id: groq/llama-3.3-70b-versatile
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: groq/llama-3.2-3b-preview
|
|
provider_id: groq
|
|
provider_model_id: groq/llama-3.2-3b-preview
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.2-3B-Instruct
|
|
provider_id: groq
|
|
provider_model_id: groq/llama-3.2-3b-preview
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: groq/llama-4-scout-17b-16e-instruct
|
|
provider_id: groq
|
|
provider_model_id: groq/llama-4-scout-17b-16e-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
|
|
provider_id: groq
|
|
provider_model_id: groq/llama-4-scout-17b-16e-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
|
|
provider_id: groq
|
|
provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
|
|
provider_id: groq
|
|
provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: groq/llama-4-maverick-17b-128e-instruct
|
|
provider_id: groq
|
|
provider_model_id: groq/llama-4-maverick-17b-128e-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
|
|
provider_id: groq
|
|
provider_model_id: groq/llama-4-maverick-17b-128e-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
|
|
provider_id: groq
|
|
provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
|
|
provider_id: groq
|
|
provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
|
|
model_type: llm
|
|
- metadata:
|
|
embedding_dimension: 384
|
|
model_id: all-MiniLM-L6-v2
|
|
provider_id: sentence-transformers
|
|
model_type: embedding
|
|
shields: []
|
|
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
|