forked from phoenix-oss/llama-stack-mirror
7301403ce3
# What does this PR do? - add /eval, /scoring, /datasetio API providers to distribution templates - regenerate build.yaml / run.yaml files - fix `template.py` to take in list of providers instead of only first one - override memory provider as faiss default for all distro (as only 1 memory provider is needed to start basic flow, chromadb/pgvector need additional setup step). ``` python llama_stack/scripts/distro_codegen.py ``` - updated README to start UI via conda builds. ## Test Plan ``` python llama_stack/scripts/distro_codegen.py ``` - Use newly generated `run.yaml` to start server ``` llama stack run ./llama_stack/templates/together/run.yaml ``` <img width="1191" alt="image" src="https://github.com/user-attachments/assets/62f7d179-0cd0-427c-b6e8-e087d4648f09"> #### Registration ``` ❯ llama-stack-client datasets register \ --dataset-id "mmlu" \ --provider-id "huggingface" \ --url "https://huggingface.co/datasets/llamastack/evals" \ --metadata '{"path": "llamastack/evals", "name": "evals__mmlu__details", "split": "train"}' \ --schema '{"input_query": {"type": "string"}, "expected_answer": {"type": "string", "chat_completion_input": {"type": "string"}}}' ❯ llama-stack-client datasets list ┏━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━┓ ┃ identifier ┃ provider_id ┃ metadata ┃ type ┃ ┡━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━┩ │ mmlu │ huggingface │ {'path': 'llamastack/evals', 'name': │ dataset │ │ │ │ 'evals__mmlu__details', 'split': │ │ │ │ │ 'train'} │ │ └────────────┴─────────────┴─────────────────────────────────────────┴─────────┘ ``` ``` ❯ llama-stack-client datasets register \ --dataset-id "simpleqa" \ --provider-id "huggingface" \ --url "https://huggingface.co/datasets/llamastack/evals" \ --metadata '{"path": "llamastack/evals", "name": "evals__simpleqa", "split": "train"}' \ --schema '{"input_query": {"type": "string"}, "expected_answer": {"type": "string", "chat_completion_input": {"type": "string"}}}' ❯ llama-stack-client datasets list ┏━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━┓ ┃ identifier ┃ provider_id ┃ metadata ┃ type ┃ ┡━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━┩ │ mmlu │ huggingface │ {'path': 'llamastack/evals', 'name': 'evals__mmlu__details', │ dataset │ │ │ │ 'split': 'train'} │ │ │ simpleqa │ huggingface │ {'path': 'llamastack/evals', 'name': 'evals__simpleqa', │ dataset │ │ │ │ 'split': 'train'} │ │ └────────────┴─────────────┴───────────────────────────────────────────────────────────────┴─────────┘ ``` ``` ❯ llama-stack-client eval_tasks register \ > --eval-task-id meta-reference-mmlu \ > --provider-id meta-reference \ > --dataset-id mmlu \ > --scoring-functions basic::regex_parser_multiple_choice_answer ❯ llama-stack-client eval_tasks register \ --eval-task-id meta-reference-simpleqa \ --provider-id meta-reference \ --dataset-id simpleqa \ --scoring-functions llm-as-judge::405b-simpleqa ❯ llama-stack-client eval_tasks list ┏━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┓ ┃ dataset_id ┃ identifier ┃ metadata ┃ provider_id ┃ provider_resour… ┃ scoring_functio… ┃ type ┃ ┡━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━┩ │ mmlu │ meta-reference-… │ {} │ meta-reference │ meta-reference-… │ ['basic::regex_… │ eval_task │ │ simpleqa │ meta-reference-… │ {} │ meta-reference │ meta-reference-… │ ['llm-as-judge:… │ eval_task │ └────────────┴──────────────────┴──────────┴────────────────┴──────────────────┴──────────────────┴───────────┘ ``` #### Test with UI ``` streamlit run app.py ``` ## 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.
82 lines
2 KiB
YAML
82 lines
2 KiB
YAML
version: '2'
|
|
image_name: meta-reference-quantized-gpu
|
|
docker_image: null
|
|
conda_env: meta-reference-quantized-gpu
|
|
apis:
|
|
- agents
|
|
- datasetio
|
|
- eval
|
|
- inference
|
|
- memory
|
|
- safety
|
|
- scoring
|
|
- telemetry
|
|
providers:
|
|
inference:
|
|
- provider_id: meta-reference-inference
|
|
provider_type: inline::meta-reference-quantized
|
|
config:
|
|
model: ${env.INFERENCE_MODEL}
|
|
max_seq_len: 4096
|
|
checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
|
|
quantization:
|
|
type: fp8
|
|
memory:
|
|
- provider_id: faiss
|
|
provider_type: inline::faiss
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/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/meta-reference-quantized-gpu}/agents_store.db
|
|
telemetry:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config: {}
|
|
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: {}
|
|
metadata_store:
|
|
namespace: null
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/registry.db
|
|
models:
|
|
- metadata: {}
|
|
model_id: ${env.INFERENCE_MODEL}
|
|
provider_id: meta-reference-inference
|
|
provider_model_id: null
|
|
shields: []
|
|
memory_banks: []
|
|
datasets: []
|
|
scoring_fns: []
|
|
eval_tasks: []
|