57 lines
2.4 KiB
Python
57 lines
2.4 KiB
Python
"""Integration test: committed zh cache files load cleanly onto real RAGAS metric instances."""
|
|
|
|
from pathlib import Path
|
|
|
|
from rag_eval.metrics.judge_prompts import CACHE_ROOT, METRIC_PROMPT_ATTRS
|
|
|
|
|
|
def test_zh_cache_files_all_present():
|
|
"""All expected zh cache files are committed and present on disk."""
|
|
zh_dir = CACHE_ROOT / "zh"
|
|
for metric, attrs in METRIC_PROMPT_ATTRS.items():
|
|
for attr in attrs:
|
|
path = zh_dir / f"{metric}__{attr}.json"
|
|
assert path.exists(), f"Missing committed cache: {path}"
|
|
|
|
|
|
def test_zh_cache_loads_onto_real_metrics():
|
|
"""Localize all registry metrics to zh — zero skips, zero errors."""
|
|
from unittest.mock import MagicMock
|
|
from ragas.llms.base import InstructorBaseRagasLLM
|
|
from ragas.embeddings.base import BaseRagasEmbedding
|
|
from rag_eval.metrics.factory import build_metric_registry
|
|
from rag_eval.metrics.judge_prompts import localize_pipeline_prompts, reset_cache
|
|
|
|
reset_cache()
|
|
llm = MagicMock(spec=InstructorBaseRagasLLM)
|
|
emb = MagicMock(spec=BaseRagasEmbedding)
|
|
registry = build_metric_registry(llm, emb)
|
|
report = localize_pipeline_prompts(registry, "zh")
|
|
|
|
expected_count = sum(len(attrs) for attrs in METRIC_PROMPT_ATTRS.values())
|
|
assert len(report.applied) == expected_count, (
|
|
f"Expected {expected_count} applied, got {len(report.applied)}; "
|
|
f"skipped={report.skipped}, warnings={report.warnings}"
|
|
)
|
|
assert not report.skipped, f"Unexpected skips: {report.skipped}"
|
|
|
|
|
|
def test_zh_cache_instructions_are_chinese():
|
|
"""After localization, faithfulness instruction starts with Chinese characters."""
|
|
from unittest.mock import MagicMock
|
|
from ragas.llms.base import InstructorBaseRagasLLM
|
|
from ragas.embeddings.base import BaseRagasEmbedding
|
|
from rag_eval.metrics.factory import build_metric_registry
|
|
from rag_eval.metrics.judge_prompts import localize_pipeline_prompts, reset_cache
|
|
|
|
reset_cache()
|
|
llm = MagicMock(spec=InstructorBaseRagasLLM)
|
|
emb = MagicMock(spec=BaseRagasEmbedding)
|
|
registry = build_metric_registry(llm, emb)
|
|
localize_pipeline_prompts(registry, "zh")
|
|
|
|
instr = registry["faithfulness"].statement_generator_prompt.instruction
|
|
# Chinese instruction should contain at least one CJK character.
|
|
has_chinese = any("\u4e00" <= ch <= "\u9fff" for ch in instr)
|
|
assert has_chinese, f"Instruction does not contain Chinese: {instr[:60]}"
|