forked from phoenix-oss/llama-stack-mirror
04de2f84e9
Each model known to the system has two identifiers: - the `provider_resource_id` (what the provider calls it) -- e.g., `accounts/fireworks/models/llama-v3p1-8b-instruct` - the `identifier` (`model_id`) under which it is registered and gets routed to the appropriate provider. We have so far used the HuggingFace repo alias as the standardized identifier you can use to refer to the model. So in the above example, we'd use `meta-llama/Llama-3.1-8B-Instruct` as the name under which it gets registered. This makes it convenient for users to refer to these models across providers. However, we forgot to register the _actual_ provider model ID also. You should be able to route via `provider_resource_id` also, of course. This change fixes this (somewhat grave) omission. *Note*: this change is additive -- more aliases work now compared to before. ## Test Plan Run the following for distro=(ollama fireworks together) ``` LLAMA_STACK_CONFIG=$distro \ pytest -s -v tests/client-sdk/inference/test_text_inference.py \ --inference-model=meta-llama/Llama-3.1-8B-Instruct --vision-inference-model="" ```
156 lines
4 KiB
YAML
156 lines
4 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: {}
|
|
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
|
|
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/groq/trace_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:}
|
|
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: rag-runtime
|
|
provider_type: inline::rag-runtime
|
|
config: {}
|
|
metadata_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/registry.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:
|
|
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
|
|
- toolgroup_id: builtin::code_interpreter
|
|
provider_id: code-interpreter
|
|
server:
|
|
port: 8321
|