fact-checker-backend/app/models/fact_check_models.py
2024-12-11 17:39:10 +06:00

109 lines
No EOL
3.3 KiB
Python

from pydantic import BaseModel, Field, HttpUrl, validator, ConfigDict
from typing import Dict, List, Optional
from enum import Enum
from datetime import datetime
class ErrorResponse(BaseModel):
detail: str
error_code: str = Field(..., description="Unique error code for this type of error")
timestamp: str = Field(default_factory=lambda: datetime.now().isoformat())
path: Optional[str] = Field(None, description="The endpoint path where error occurred")
model_config = ConfigDict(json_schema_extra={
"example": {
"detail": "Error description",
"error_code": "ERROR_CODE",
"timestamp": "2024-12-09T16:49:30.905765",
"path": "/check-facts"
}
})
class RequestValidationError(BaseModel):
loc: List[str]
msg: str
type: str
class Publisher(BaseModel):
name: str
site: Optional[str] = Field(None, description="Publisher's website")
@validator('site')
def validate_site(cls, v):
if v and not (v.startswith('http://') or v.startswith('https://')):
return f"https://{v}"
return v
class ClaimReview(BaseModel):
publisher: Publisher
url: Optional[HttpUrl] = None
title: Optional[str] = None
reviewDate: Optional[str] = None
textualRating: Optional[str] = None
languageCode: str = Field(default="en-US")
class Claim(BaseModel):
text: str
claimant: Optional[str] = None
claimDate: Optional[str] = None
claimReview: List[ClaimReview]
class FactCheckResponse(BaseModel):
query: str = Field(..., description="Original query that was fact-checked")
total_claims_found: int = Field(..., ge=0)
results: List[Claim] = Field(default_factory=list)
summary: Dict[str, int] = Field(...)
model_config = ConfigDict(json_schema_extra={
"example": {
"query": "Example claim",
"total_claims_found": 1,
"results": [{
"text": "Example claim text",
"claimant": "Source name",
"claimReview": [{
"publisher": {
"name": "Fact Checker",
"site": "factchecker.com"
},
"textualRating": "True"
}]
}],
"summary": {
"total_sources": 1,
"fact_checking_sites_queried": 10
}
}
})
class SourceType(str, Enum):
FACT_CHECKER = "fact_checker"
NEWS_SITE = "news_site"
class FactCheckSource(BaseModel):
domain: str
type: SourceType
priority: int = Field(default=1, ge=1, le=10)
model_config = ConfigDict(json_schema_extra={
"example": {
"domain": "factcheck.org",
"type": "fact_checker",
"priority": 1
}
})
class FactCheckRequest(BaseModel):
content: str = Field(
...,
min_length=10,
max_length=1000,
description="The claim to be fact-checked"
)
language: str = Field(default="en-US", pattern="^[a-z]{2}-[A-Z]{2}$")
max_results_per_source: int = Field(default=10, ge=1, le=50)
@validator('content')
def validate_content(cls, v):
if not v.strip():
raise ValueError("Content cannot be empty or just whitespace")
return v.strip()