mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-10-27 05:30:39 +00:00
201b9840cd
* feat(knowledge): unify read-only retrieval and source contracts * fix(knowledge): address citation and contract review feedback * fix(knowledge): resolve citations in delegated task reports * docs(frontend): keep agent guidance within CI size budget * docs(backend): preserve merged guidance chain headroom
69 lines
2.4 KiB
Python
69 lines
2.4 KiB
Python
"""Provider-neutral retrieval evidence and operation-level capabilities."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import hashlib
|
|
import json
|
|
from typing import Literal, Protocol
|
|
|
|
from pydantic import BaseModel, ConfigDict, Field, HttpUrl, computed_field, field_validator
|
|
|
|
|
|
class KnowledgeCapabilities(BaseModel):
|
|
"""An operation is supported only when explicitly advertised.
|
|
|
|
Search-only providers need no catalog, scope, or management implementation.
|
|
Scope admission and adapters for these optional operations belong to phase 2.
|
|
"""
|
|
|
|
operations: frozenset[Literal["search", "sources", "catalog", "documents", "dataset_filter", "document_filter"]] = frozenset({"search"})
|
|
|
|
def supports(self, operation: str) -> bool:
|
|
return operation in self.operations
|
|
|
|
|
|
class KnowledgeSource(BaseModel):
|
|
"""One attributable excerpt actually returned by a retrieval tool.
|
|
|
|
Titles and optional locators are provider evidence, never inferred links,
|
|
page numbers, or local reference ordinals. IDs expose no provider internals.
|
|
"""
|
|
|
|
model_config = ConfigDict(frozen=True, extra="ignore", str_strip_whitespace=True)
|
|
|
|
provider: str = Field(min_length=1, max_length=100)
|
|
title: str = Field(min_length=1, max_length=500)
|
|
excerpt: str = Field(min_length=1, max_length=100_000)
|
|
dataset_name: str | None = Field(default=None, max_length=500)
|
|
url: HttpUrl | None = None
|
|
page: int | None = Field(default=None, gt=0, le=9_007_199_254_740_991, strict=True)
|
|
|
|
@field_validator("url")
|
|
@classmethod
|
|
def reject_credentials(cls, value: HttpUrl | None) -> HttpUrl | None:
|
|
if value is not None and (value.username is not None or value.password is not None):
|
|
raise ValueError("source URL must not contain credentials")
|
|
return value
|
|
|
|
@computed_field
|
|
@property
|
|
def id(self) -> str:
|
|
identity = [self.provider, self.title, self.excerpt, self.dataset_name, str(self.url) if self.url else None, self.page]
|
|
return hashlib.sha256(json.dumps(identity, ensure_ascii=False).encode("utf-8")).hexdigest()[:32]
|
|
|
|
|
|
class RetrievalHit(BaseModel):
|
|
content: str
|
|
source: KnowledgeSource | None = None
|
|
score: float | None = Field(default=None, allow_inf_nan=False)
|
|
|
|
|
|
class RetrievalResult(BaseModel):
|
|
hits: list[RetrievalHit] = Field(default_factory=list)
|
|
|
|
|
|
class RetrievalProvider(Protocol):
|
|
capabilities: KnowledgeCapabilities
|
|
|
|
async def search(self, query: str) -> RetrievalResult: ...
|