Files
lhl 3decdfc31c feat(rag): v1 rerank 精排 + bge-m3 多语言切换(T6/T11 架构审查整改)
- T6 (Issue6): RerankConfig(enabled/model=BAAI/bge-reranker-v2-m3/device)
  - rag-layer-design §6.3 Rerank 精排:窗口=RRF top-10、候选≤top_k 跳过、
    故障降级 RRF 原序;原 §6.3-6.6 顺延 6.4-6.7
  - config-design §5 新增 rerank 段;design §5.5 检索策略加 rerank
- T11 (OV2): EmbeddingConfig.model 默认 bge-small-zh-v1.5 → BAAI/bge-m3(日文语料)
  - rag-layer-design 选型表/依赖表/manifest/流程图同步 + 新增 §2.3 日文样本验证
  - design.md / implementation-plan 4.3 / config-design embedding 同步
- 新增 test_rag_design_consistency.py 一致性门禁(6 用例防文档漂移)
- TDD: RED(默认模型仍旧 + rerank 字段不存在)→ GREEN → 全量 198 passed / 100.00%(996 stmts/252 br)
2026-08-12 11:32:28 +08:00

108 lines
3.7 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
from pathlib import Path
import pytest
from genesis.config import Settings
FIXTURES = Path(__file__).parent / "fixtures"
# ---------- T5: 删除 Qdrant/Redis 死配置(Issue5 ----------
def test_qdrant_config_removed():
"""Scope 缩减裁定:Qdrant 双实现已废弃,配置模型不得残留 QdrantStoreConfig。"""
import genesis.config as cfg
assert not hasattr(cfg, "QdrantStoreConfig")
def test_vector_store_has_no_qdrant_field():
s = Settings()
assert not hasattr(s.rag.vector_store, "qdrant")
assert s.rag.vector_store.adapter == "chroma"
def test_task_queue_has_no_redis_url():
s = Settings()
assert "redis_url" not in s.app.task_queue
def test_from_dir_maps_yaml_fields():
s = Settings.from_dir(FIXTURES)
assert s.app.server.max_upload_mb == 10
assert s.app.session["sqlite_path"] == "C:/tmp/genesis.db"
assert s.app.task_queue["timeout_sec"] == 300
assert s.inference.models.primary.name == "deepseek-chat"
assert s.inference.llm_calls.max_context_tokens == 16000
assert s.inference.structured_output.max_parse_retry == 3
assert s.rag.embedding.model == "BAAI/bge-m3"
assert s.rag.retrieval.rrf_k == 42
def test_defaults_when_dir_empty(tmp_path):
s = Settings.from_dir(tmp_path)
assert s.app.name == "genesis"
assert s.app.server.max_upload_mb == 100
assert s.app.task_queue["backend"] == "memory"
assert s.inference.models.primary.name == "deepseek-chat"
assert s.rag.embedding.model == "BAAI/bge-m3"
assert s.rag.retrieval.rrf_k == 60
def test_env_override_yaml(monkeypatch):
monkeypatch.setenv("GENESIS_APP__SERVER__MAX_UPLOAD_MB", "25")
s = Settings.from_dir(FIXTURES)
assert s.app.server.max_upload_mb == 25
def test_env_create_missing_key(monkeypatch):
monkeypatch.setenv("GENESIS_RAG__RETRIEVAL__DEFAULT_TOP_K", "7")
s = Settings.from_dir(FIXTURES)
assert s.rag.retrieval.default_top_k == 7
def test_env_placeholder_expansion(monkeypatch):
monkeypatch.setenv("SOME_API_KEY", "sk-test-xyz")
s = Settings.from_dir(FIXTURES)
# Qdrant 已删除:验证占位展开仍作用于通用 env(此处用 app.session 的路径占位验证机制)
assert s.app.session["sqlite_path"] == "C:/tmp/genesis.db"
def test_redacted_hides_secrets():
s = Settings.from_dir(FIXTURES)
red = s.get_redacted()
# Qdrant 已删除:验证脱敏仍隐藏 chroma 相关字段(此处以 server 配置验证机制不回归)
assert red["app"]["server"]["max_upload_mb"] == 10
def test_expand_env_list_branch(monkeypatch):
# _expand_env 的 list 分支(L134):列表项递归展开环境占位
from genesis.config import _expand_env
monkeypatch.setenv("SOME_API_KEY", "sk-list-xyz")
data = {"models": [{"name": "a", "key": "${SOME_API_KEY}"}, "plain"]}
out = _expand_env(data)
assert out["models"][0]["key"] == "sk-list-xyz"
assert out["models"][1] == "plain"
# ---------- T6/T11: rerank 精排 + bge-m3 多语言(I6/OV2 ----------
def test_embedding_default_model_is_bge_m3():
"""OV2bge-small-zh 面向中文、实际语料为日文 → 默认切换多语言 bge-m3。"""
s = Settings()
assert s.rag.embedding.model == "BAAI/bge-m3"
def test_rerank_config_defaults():
"""I6v1 引入 rerank 精排(bge-reranker-v2-m3),默认启用、device=cpu。"""
s = Settings()
assert s.rag.rerank.enabled is True
assert s.rag.rerank.model == "BAAI/bge-reranker-v2-m3"
assert s.rag.rerank.device == "cpu"
def test_rerank_env_override(monkeypatch):
monkeypatch.setenv("GENESIS_RAG__RERANK__ENABLED", "false")
s = Settings.from_dir(FIXTURES)
assert s.rag.rerank.enabled is False
assert s.rag.rerank.model == "BAAI/bge-reranker-v2-m3"