183 lines
4.4 KiB
Python
183 lines
4.4 KiB
Python
"""Adaptive RAG shared constants/types part."""
|
|
from __future__ import annotations
|
|
|
|
from .shared_imports import *
|
|
from .shared_utils import *
|
|
|
|
ARCHITECTURE_KEYWORDS = (
|
|
"系统架构",
|
|
"架构",
|
|
"运行机制",
|
|
"技术栈",
|
|
"模块",
|
|
"服务组成",
|
|
"docker",
|
|
"数据库",
|
|
"redis",
|
|
"后端",
|
|
"前端",
|
|
)
|
|
CODE_KEYWORDS = (
|
|
"代码",
|
|
"函数",
|
|
"方法",
|
|
"类",
|
|
"模块",
|
|
"文件",
|
|
"api",
|
|
"接口实现",
|
|
"service",
|
|
"model",
|
|
"schema",
|
|
"where defined",
|
|
)
|
|
URL_RE = re.compile(r"https?://\S+", flags=re.IGNORECASE)
|
|
SENTENCE_SPLIT_RE = re.compile(r"(?<=[。！？!?\n])")
|
|
PAGE_MARKER_RE = re.compile(r"\[\[PAGE:(\d{1,6})\]\]")
|
|
MAX_CONTEXT_TOKENS = 8000
|
|
DEFAULT_TOP_K = 5
|
|
DB_QUERY_TIMEOUT_SECONDS = 5.0
|
|
VECTOR_SEARCH_TIMEOUT_SECONDS = 10.0
|
|
GRAPH_QUERY_TIMEOUT_SECONDS = 4.0
|
|
AGENT_MAX_RETRIEVAL_STEPS = 3
|
|
SESSION_GAP_MINUTES = 30
|
|
SESSION_DEFAULT_TITLE = "新会话"
|
|
SESSION_TITLE_MIN_LEN = 5
|
|
THINKING_MODE_NORMAL = "normal"
|
|
THINKING_MODE_DEEP = "deep"
|
|
DEEP_RETRIEVAL_STEPS = _env_int("RAG_DEEP_RETRIEVAL_STEPS", 5, minimum=2, maximum=8)
|
|
DEEP_VECTOR_TOP_K = _env_int("RAG_DEEP_VECTOR_TOP_K", 12, minimum=6, maximum=40)
|
|
DEEP_CONTEXT_BLOCKS = _env_int("RAG_DEEP_CONTEXT_BLOCKS", 16, minimum=8, maximum=32)
|
|
DEEP_ANSWER_MAX_TOKENS = _env_int("RAG_DEEP_ANSWER_MAX_TOKENS", 1400, minimum=900, maximum=3000)
|
|
QUERY_TYPE_COUNT = "count"
|
|
QUERY_TYPE_LIST = "list"
|
|
QUERY_TYPE_STATUS = "status"
|
|
QUERY_TYPE_EXPLAIN = "explain"
|
|
QUERY_TYPE_UNKNOWN = "unknown"
|
|
ANSWER_MODE_FAST_PATH = "fast_path"
|
|
ANSWER_MODE_RETRIEVAL_NORMAL = "retrieval_normal"
|
|
ANSWER_MODE_RETRIEVAL_DEEP = "retrieval_deep"
|
|
ANSWER_MODE_CLARIFY = "clarify"
|
|
ANSWER_MODE_BLOCKED = "blocked"
|
|
GROUNDING_STATUS_GROUNDED = "grounded"
|
|
GROUNDING_STATUS_PARTIALLY_GROUNDED = "partially_grounded"
|
|
GROUNDING_STATUS_INSUFFICIENT_EVIDENCE = "insufficient_evidence"
|
|
GROUNDING_STATUS_BLOCKED = "blocked"
|
|
RETRIEVAL_POLICY_VERSION = "retrieval-v2.1"
|
|
ACTION_MODE_AUTO = "auto"
|
|
ACTION_MODE_READ = "read"
|
|
ACTION_MODE_WRITE = "write"
|
|
ACTION_MODE_READ_WRITE = "read_write"
|
|
REQUIREMENT_WRITE_VERB_KEYWORDS = (
|
|
"新增",
|
|
"增加",
|
|
"添加",
|
|
"接入",
|
|
"支持",
|
|
"实现",
|
|
"创建",
|
|
"新建",
|
|
"记录",
|
|
"入库",
|
|
"同步",
|
|
"补充",
|
|
)
|
|
REQUIREMENT_WRITE_OBJECT_KEYWORDS = (
|
|
"信号",
|
|
"需求",
|
|
"任务",
|
|
"项目",
|
|
"功能",
|
|
"接口",
|
|
"页面",
|
|
"按钮",
|
|
"规则",
|
|
"模块",
|
|
"卡路里",
|
|
"食谱",
|
|
)
|
|
WRITE_EXPRESSIONS = (
|
|
"给",
|
|
"帮我",
|
|
"请帮",
|
|
"请给",
|
|
"麻烦",
|
|
)
|
|
COUNT_HINTS = ("多少", "几个", "数量", "总数", "count")
|
|
LIST_HINTS = ("哪些", "列表", "清单", "列出", "列一下", "分别", "名单", "都有哪些")
|
|
STATUS_HINTS = ("进度", "状态", "阶段", "完成率", "完成度", "情况")
|
|
ENTITY_ALIAS_MAP: dict[str, str] = {
|
|
"能力": "skill",
|
|
"技能": "skill",
|
|
"ability": "skill",
|
|
"abilities": "skill",
|
|
"skill": "skill",
|
|
"skills": "skill",
|
|
"负责人": "owner",
|
|
"owner": "owner",
|
|
"assignee": "owner",
|
|
"成员": "member",
|
|
"人员": "member",
|
|
"member": "member",
|
|
"任务": "task",
|
|
"task": "task",
|
|
"tasks": "task",
|
|
"项目": "project",
|
|
"project": "project",
|
|
"projects": "project",
|
|
"信号": "signal",
|
|
"signal": "signal",
|
|
"signals": "signal",
|
|
"函数": "function",
|
|
"function": "function",
|
|
"method": "function",
|
|
"类": "class",
|
|
"class": "class",
|
|
"模块": "module",
|
|
"module": "module",
|
|
"智能配置": "ai_config",
|
|
"ai配置": "ai_config",
|
|
"配置中心": "ai_config",
|
|
"能力管理": "skills",
|
|
"技能管理": "skills",
|
|
"用户管理": "users",
|
|
"项目列表": "projects",
|
|
"团队负载": "workloads",
|
|
"ai管家": "ai_steward",
|
|
}
|
|
TS_SYMBOL_RE = re.compile(
|
|
r"(?:export\s+)?(?:async\s+)?(?:function|class|interface|type|const)\s+([A-Za-z_][A-Za-z0-9_]*)"
|
|
)
|
|
|
|
|
|
@dataclass
|
|
class RetrievedItem:
|
|
source: str
|
|
content: str
|
|
score: float
|
|
source_label: str
|
|
metadata: dict[str, Any]
|
|
|
|
|
|
@dataclass
|
|
class RetrievalBudget:
|
|
max_steps: int
|
|
vector_top_k: int
|
|
|
|
|
|
@dataclass
|
|
class QueryPlannerDecision:
|
|
answer_mode: str
|
|
thinking_mode: str
|
|
allow_fast_path: bool
|
|
retrieval_answer_mode: str
|
|
budget: RetrievalBudget
|
|
reason: Optional[str] = None
|
|
|
|
|
|
@dataclass
|
|
class GroundingVerdict:
|
|
status: str
|
|
missing_fields: list[str]
|
|
reason_code: Optional[str] = None
|