refactor(api): migrate console/service_api.dataset.hit_testing to BaseModel (#36533)

This commit is contained in:
chariri
2026-05-27 15:51:42 +09:00
committed by GitHub
parent a8d380bcaf
commit b034449a0c
13 changed files with 732 additions and 441 deletions

View File

@@ -1,15 +1,12 @@
from __future__ import annotations
from datetime import datetime
from typing import Any
from uuid import UUID
from flask_restx import Resource
from pydantic import Field, field_validator
from controllers.common.schema import register_schema_models
from fields.base import ResponseModel
from libs.helper import to_timestamp
from controllers.common.schema import register_response_schema_models, register_schema_models
from fields.hit_testing_fields import HitTestingResponse
from libs.helper import dump_response
from libs.login import login_required
from .. import console_ns
@@ -20,86 +17,8 @@ from ..wraps import (
setup_required,
)
class HitTestingDocument(ResponseModel):
id: str | None = None
data_source_type: str | None = None
name: str | None = None
doc_type: str | None = None
doc_metadata: Any | None = None
class HitTestingSegment(ResponseModel):
id: str | None = None
position: int | None = None
document_id: str | None = None
content: str | None = None
sign_content: str | None = None
answer: str | None = None
word_count: int | None = None
tokens: int | None = None
keywords: list[str] = Field(default_factory=list)
index_node_id: str | None = None
index_node_hash: str | None = None
hit_count: int | None = None
enabled: bool | None = None
disabled_at: int | None = None
disabled_by: str | None = None
status: str | None = None
created_by: str | None = None
created_at: int | None = None
indexing_at: int | None = None
completed_at: int | None = None
error: str | None = None
stopped_at: int | None = None
document: HitTestingDocument | None = None
@field_validator("disabled_at", "created_at", "indexing_at", "completed_at", "stopped_at", mode="before")
@classmethod
def _normalize_timestamp(cls, value: datetime | int | None) -> int | None:
return to_timestamp(value)
class HitTestingChildChunk(ResponseModel):
id: str | None = None
content: str | None = None
position: int | None = None
score: float | None = None
class HitTestingFile(ResponseModel):
id: str | None = None
name: str | None = None
size: int | None = None
extension: str | None = None
mime_type: str | None = None
source_url: str | None = None
class HitTestingRecord(ResponseModel):
segment: HitTestingSegment | None = None
child_chunks: list[HitTestingChildChunk] = Field(default_factory=list)
score: float | None = None
tsne_position: Any | None = None
files: list[HitTestingFile] = Field(default_factory=list)
summary: str | None = None
class HitTestingResponse(ResponseModel):
query: str
records: list[HitTestingRecord] = Field(default_factory=list)
register_schema_models(
console_ns,
HitTestingPayload,
HitTestingDocument,
HitTestingSegment,
HitTestingChildChunk,
HitTestingFile,
HitTestingRecord,
HitTestingResponse,
)
register_schema_models(console_ns, HitTestingPayload)
register_response_schema_models(console_ns, HitTestingResponse)
@console_ns.route("/datasets/<uuid:dataset_id>/hit-testing")
@@ -119,12 +38,11 @@ class HitTestingApi(Resource, DatasetsHitTestingBase):
@login_required
@account_initialization_required
@cloud_edition_billing_rate_limit_check("knowledge")
def post(self, dataset_id: UUID):
def post(self, dataset_id: UUID) -> dict[str, object]:
dataset_id_str = str(dataset_id)
dataset = self.get_and_validate_dataset(dataset_id_str)
payload = HitTestingPayload.model_validate(console_ns.payload or {})
args = payload.model_dump(exclude_none=True)
args = self.parse_args(console_ns.payload)
self.hit_testing_args_check(args)
return HitTestingResponse.model_validate(self.perform_hit_testing(dataset, args)).model_dump(mode="json")
return dump_response(HitTestingResponse, self.perform_hit_testing(dataset, args))

View File

@@ -1,7 +1,6 @@
import logging
from typing import Any
from typing import Any, cast
from flask_restx import marshal
from pydantic import BaseModel, Field
from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
@@ -19,10 +18,10 @@ from core.errors.error import (
ProviderTokenNotInitError,
QuotaExceededError,
)
from fields.hit_testing_fields import hit_testing_record_fields
from graphon.model_runtime.errors.invoke import InvokeError
from libs.login import current_user
from models.account import Account
from models.dataset import Dataset
from services.dataset_service import DatasetService
from services.entities.knowledge_entities.knowledge_entities import RetrievalModel
from services.hit_testing_service import HitTestingService
@@ -38,16 +37,6 @@ class HitTestingPayload(BaseModel):
class DatasetsHitTestingBase:
@staticmethod
def _extract_hit_testing_query(query: Any) -> str:
"""Return the query string from the service response shape."""
if isinstance(query, dict):
content = query.get("content")
if isinstance(content, str):
return content
raise ValueError("Invalid hit testing query response")
@staticmethod
def _prepare_hit_testing_records(records: Any) -> list[dict[str, Any]]:
"""Ensure collection fields match the API schema before response validation."""
@@ -63,6 +52,7 @@ class DatasetsHitTestingBase:
segment = normalized_record.get("segment")
if isinstance(segment, dict):
normalized_segment = dict(segment)
normalized_segment.setdefault("sign_content", None)
if normalized_segment.get("keywords") is None:
normalized_segment["keywords"] = []
normalized_record["segment"] = normalized_segment
@@ -73,12 +63,15 @@ class DatasetsHitTestingBase:
if normalized_record.get("files") is None:
normalized_record["files"] = []
normalized_record.setdefault("tsne_position", None)
normalized_record.setdefault("summary", None)
normalized_records.append(normalized_record)
return normalized_records
@staticmethod
def get_and_validate_dataset(dataset_id: str):
def get_and_validate_dataset(dataset_id: str) -> Dataset:
assert isinstance(current_user, Account)
dataset = DatasetService.get_dataset(dataset_id)
if dataset is None:
@@ -92,33 +85,35 @@ class DatasetsHitTestingBase:
return dataset
@staticmethod
def hit_testing_args_check(args: dict[str, Any]):
def hit_testing_args_check(args: dict[str, Any]) -> None:
HitTestingService.hit_testing_args_check(args)
@staticmethod
def parse_args(payload: dict[str, Any]) -> dict[str, Any]:
def parse_args(payload: dict[str, Any] | None) -> dict[str, Any]:
"""Validate and return hit-testing arguments from an incoming payload."""
hit_testing_payload = HitTestingPayload.model_validate(payload or {})
return hit_testing_payload.model_dump(exclude_none=True)
@staticmethod
def perform_hit_testing(dataset, args):
def perform_hit_testing(dataset: Dataset, args: dict[str, Any]) -> dict[str, Any]:
assert isinstance(current_user, Account)
try:
response = HitTestingService.retrieve(
dataset=dataset,
query=args.get("query"),
query=cast(str, args.get("query")),
account=current_user,
retrieval_model=args.get("retrieval_model"),
external_retrieval_model=args.get("external_retrieval_model"),
external_retrieval_model=cast(dict[str, Any], args.get("external_retrieval_model")),
attachment_ids=args.get("attachment_ids"),
limit=10,
)
query = response.get("query")
if not isinstance(query, dict) or not isinstance(query.get("content"), str):
raise ValueError("Invalid hit testing query response")
return {
"query": DatasetsHitTestingBase._extract_hit_testing_query(response.get("query")),
"records": DatasetsHitTestingBase._prepare_hit_testing_records(
marshal(response.get("records", []), hit_testing_record_fields)
),
"query": {"content": query["content"]},
"records": DatasetsHitTestingBase._prepare_hit_testing_records(response.get("records", [])),
}
except services.errors.index.IndexNotInitializedError:
raise DatasetNotInitializedError()

View File

@@ -1,11 +1,14 @@
from uuid import UUID
from controllers.common.schema import register_schema_model
from controllers.common.schema import register_response_schema_models, register_schema_models
from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase, HitTestingPayload
from controllers.service_api import service_api_ns
from controllers.service_api.wraps import DatasetApiResource, cloud_edition_billing_rate_limit_check
from fields.hit_testing_fields import HitTestingResponse
from libs.helper import dump_response
register_schema_model(service_api_ns, HitTestingPayload)
register_schema_models(service_api_ns, HitTestingPayload)
register_response_schema_models(service_api_ns, HitTestingResponse)
@service_api_ns.route("/datasets/<uuid:dataset_id>/hit-testing", "/datasets/<uuid:dataset_id>/retrieve")
@@ -13,16 +16,16 @@ class HitTestingApi(DatasetApiResource, DatasetsHitTestingBase):
@service_api_ns.doc("dataset_hit_testing")
@service_api_ns.doc(description="Perform hit testing on a dataset")
@service_api_ns.doc(params={"dataset_id": "Dataset ID"})
@service_api_ns.doc(
responses={
200: "Hit testing results",
401: "Unauthorized - invalid API token",
404: "Dataset not found",
}
@service_api_ns.response(
200,
"Hit testing results",
model=service_api_ns.models[HitTestingResponse.__name__],
)
@service_api_ns.response(401, "Unauthorized - invalid API token")
@service_api_ns.response(404, "Dataset not found")
@service_api_ns.expect(service_api_ns.models[HitTestingPayload.__name__])
@cloud_edition_billing_rate_limit_check("knowledge", "dataset")
def post(self, tenant_id, dataset_id: UUID):
def post(self, tenant_id: str, dataset_id: UUID) -> dict[str, object]:
"""Perform hit testing on a dataset.
Tests retrieval performance for the specified dataset.
@@ -33,4 +36,4 @@ class HitTestingApi(DatasetApiResource, DatasetsHitTestingBase):
args = self.parse_args(service_api_ns.payload)
self.hit_testing_args_check(args)
return self.perform_hit_testing(dataset, args)
return dump_response(HitTestingResponse, self.perform_hit_testing(dataset, args))