phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

feat(eval api): (2.2/n) delete eval / scoring / scoring_fn apis (#1700)

Browse source 
# What does this PR do?
- To make it easier, delete existing `eval/scoring/scoring_function`
apis. There will be a bunch of broken impls here. The sequence is:
1. migrate benchmark graders
2. clean up existing scoring functions

- Add a skeleton evaluation impl to make tests pass. 

## Test Plan
tested in following PRs

[//]: # (## Documentation)
This commit is contained in:
Xi Yan 2025-03-19 11:04:23 -07:00 • committed by GitHub
parent 0048274ec0
commit c1d18283d2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
113 changed files with 408 additions and 3900 deletions
Download patch file Download diff file Expand all files Collapse all files

36
llama_stack/templates/dev/dev.py
View file

@ -16,20 +16,38 @@ from llama_stack.distribution.datatypes import (
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
)
from llama_stack.providers.inline.vector_io.sqlite_vec.config import SQLiteVectorIOConfig
from llama_stack.providers.inline.vector_io.sqlite_vec.config import (
SQLiteVectorIOConfig,
)
from llama_stack.providers.remote.inference.anthropic.config import AnthropicConfig
from llama_stack.providers.remote.inference.anthropic.models import MODEL_ENTRIES as ANTHROPIC_MODEL_ENTRIES
from llama_stack.providers.remote.inference.anthropic.models import (
MODEL_ENTRIES as ANTHROPIC_MODEL_ENTRIES,
)
from llama_stack.providers.remote.inference.fireworks.config import FireworksImplConfig
from llama_stack.providers.remote.inference.fireworks.models import MODEL_ENTRIES as FIREWORKS_MODEL_ENTRIES
from llama_stack.providers.remote.inference.fireworks.models import (
MODEL_ENTRIES as FIREWORKS_MODEL_ENTRIES,
)
from llama_stack.providers.remote.inference.gemini.config import GeminiConfig
from llama_stack.providers.remote.inference.gemini.models import MODEL_ENTRIES as GEMINI_MODEL_ENTRIES
from llama_stack.providers.remote.inference.gemini.models import (
MODEL_ENTRIES as GEMINI_MODEL_ENTRIES,
)
from llama_stack.providers.remote.inference.groq.config import GroqConfig
from llama_stack.providers.remote.inference.groq.models import MODEL_ENTRIES as GROQ_MODEL_ENTRIES
from llama_stack.providers.remote.inference.groq.models import (
MODEL_ENTRIES as GROQ_MODEL_ENTRIES,
)
from llama_stack.providers.remote.inference.openai.config import OpenAIConfig
from llama_stack.providers.remote.inference.openai.models import MODEL_ENTRIES as OPENAI_MODEL_ENTRIES
from llama_stack.providers.remote.inference.openai.models import (
MODEL_ENTRIES as OPENAI_MODEL_ENTRIES,
)
from llama_stack.providers.remote.vector_io.chroma.config import ChromaVectorIOConfig
from llama_stack.providers.remote.vector_io.pgvector.config import PGVectorVectorIOConfig
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings, get_model_registry
from llama_stack.providers.remote.vector_io.pgvector.config import (
PGVectorVectorIOConfig,
)
from llama_stack.templates.template import (
DistributionTemplate,
RunConfigSettings,
get_model_registry,
)
def get_inference_providers() -> Tuple[List[Provider], List[ModelInput]]:
@ -83,9 +101,7 @@ def get_distribution_template() -> DistributionTemplate:
"safety": ["inline::llama-guard"],
"agents": ["inline::meta-reference"],
"telemetry": ["inline::meta-reference"],
"eval": ["inline::meta-reference"],
"datasetio": ["remote::huggingface", "inline::localfs"],
"scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
"tool_runtime": [
"remote::brave-search",
"remote::tavily-search",