62 lines
1.3 KiB
Python
62 lines
1.3 KiB
Python
from datetime import datetime
|
|
from typing import Annotated, Literal
|
|
from uuid import UUID
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
from app.schemas.catalog import Category, Input
|
|
|
|
QueryText = Annotated[str, Field(min_length=1, max_length=500)]
|
|
|
|
|
|
class RetrievalRequest(Input):
|
|
query: QueryText
|
|
mode: Literal["keyword"] = "keyword"
|
|
top_k: int = Field(default=5, ge=1, le=20)
|
|
category: Category | None = None
|
|
|
|
|
|
class RetrievalHit(BaseModel):
|
|
rank: int
|
|
knowledge_id: int
|
|
knowledge_version: int
|
|
document_id: int | None
|
|
document_version: int | None
|
|
source_id: int | None
|
|
source_version: int | None
|
|
source_name: str | None
|
|
source_url: str
|
|
title: str
|
|
category: str
|
|
snippet: str
|
|
snippet_start: int
|
|
snippet_end: int
|
|
score: float
|
|
matched_terms: list[str]
|
|
|
|
|
|
class RetrievalConfig(BaseModel):
|
|
tokenizer: str
|
|
scorer: str
|
|
k1: float
|
|
b: float
|
|
title_weight: int
|
|
stopwords_version: str
|
|
|
|
|
|
class RetrievalResponse(BaseModel):
|
|
run_id: UUID
|
|
query: str
|
|
mode: Literal["keyword"]
|
|
status: Literal["ok", "no_evidence"]
|
|
top_k: int
|
|
category: str | None
|
|
query_terms: list[str]
|
|
corpus_size: int
|
|
corpus_fingerprint: str
|
|
total_hits: int
|
|
results: list[RetrievalHit]
|
|
elapsed_ms: float
|
|
created_at: datetime
|
|
config: RetrievalConfig
|