.gitlab-ci.yml

@@ -11,7 +11,6 @@ cache:
 
 stages:
   - setup
-  - lint
   - test
 
 before_script:
@@ -29,14 +28,6 @@ setup:
       - venv/
     expire_in: 1 hour
 
-lint:
-  stage: lint
-  needs:
-    - setup
-  script:
-    - black --check app/ main.py tests/
-    - flake8 app/ main.py tests/ --max-line-length=100
-
 test:
   stage: test
   needs:
@@ -47,7 +38,7 @@ test:
     # Start FastAPI server
     - uvicorn main:app --host 0.0.0.0 --port 8000 &
     # Wait for server to start
-    - sleep 10
+    - sleep 15
     # Test health endpoint
     - |
       RESPONSE=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:8000/health)

app/api/ai_fact_check.py

@@ -6,7 +6,7 @@ from app.models.ai_fact_check_models import (
     AIFactCheckResponse,
     VerificationResult,
     TokenUsage,
-    ErrorResponse
+    ErrorResponse,
 )
 from urllib.parse import urlparse
 import asyncio
@@ -16,13 +16,11 @@ aifact_check_router = APIRouter()
 openai_client = OpenAIClient(api_key=OPENAI_API_KEY)
 fact_checker = AIFactChecker(openai_client=openai_client)
 
+
 @aifact_check_router.post(
     "/aicheck-facts",
     response_model=AIFactCheckResponse,
-    responses={
-        400: {"model": ErrorResponse},
-        500: {"model": ErrorResponse}
-    }
+    responses={400: {"model": ErrorResponse}, 500: {"model": ErrorResponse}},
 )
 async def ai_fact_check(request: AIFactCheckRequest):
     """
@@ -57,7 +55,7 @@ async def ai_fact_check(request: AIFactCheckRequest):
                     confidence="Low",
                     evidence=f"Error checking URL: {str(result)}",
                     reasoning="URL processing failed",
-                    missing_info="Could not access or process the URL"
+                    missing_info="Could not access or process the URL",
                 )
                 continue
 
@@ -66,7 +64,7 @@ async def ai_fact_check(request: AIFactCheckRequest):
                 confidence=result["verification_result"]["confidence"],
                 evidence=result["verification_result"]["evidence"],
                 reasoning=result["verification_result"]["reasoning"],
-                missing_info=result["verification_result"].get("missing_info", None)
+                missing_info=result["verification_result"].get("missing_info", None),
             )
 
             results[url] = verification_result
@@ -80,24 +78,22 @@ async def ai_fact_check(request: AIFactCheckRequest):
         token_usage = TokenUsage(
             prompt_tokens=total_prompt_tokens,
             completion_tokens=total_completion_tokens,
-            total_tokens=total_tokens
+            total_tokens=total_tokens,
         )
 
         return AIFactCheckResponse(
             query=request.content,
             verification_result=results,
             sources=list(all_sources),
-            token_usage=token_usage
+            token_usage=token_usage,
         )
 
     except ValueError as e:
         raise HTTPException(
             status_code=400,
             detail=ErrorResponse(
-                detail=str(e),
-                error_code="INVALID_URL",
-                path="/aicheck-facts"
-            ).dict()
+                detail=str(e), error_code="INVALID_URL", path="/aicheck-facts"
+            ).dict(),
         )
     except Exception as e:
         raise HTTPException(
@@ -105,6 +101,6 @@ async def ai_fact_check(request: AIFactCheckRequest):
             detail=ErrorResponse(
                 detail=f"Error processing fact-check request: {str(e)}",
                 error_code="PROCESSING_ERROR",
-                path="/aicheck-facts"
-            ).dict()
+                path="/aicheck-facts",
+            ).dict(),
         )

app/api/fact_check.py

@@ -7,13 +7,14 @@ from app.models.fact_check_models import (
     FactCheckRequest,
     FactCheckResponse,
     ErrorResponse,
-    Source
+    Source,
 )
 from app.websites.fact_checker_website import get_all_sources
 
 fact_check_router = APIRouter()
 openai_client = OpenAIClient(OPENAI_API_KEY)
 
+
 async def generate_fact_report(query: str, fact_check_data: dict) -> FactCheckResponse:
     """Generate a fact check report using OpenAI based on the fact check results."""
     try:
@@ -70,9 +71,7 @@ Ensure all URLs in sources are complete (including https:// if missing) and each
             4. Note any conflicting information between sources"""
 
         response = await openai_client.generate_text_response(
-            system_prompt=system_prompt,
-            user_prompt=user_prompt,
-            max_tokens=1000
+            system_prompt=system_prompt, user_prompt=user_prompt, max_tokens=1000
         )
 
         try:
@@ -80,23 +79,22 @@ Ensure all URLs in sources are complete (including https:// if missing) and each
             response_data = response["response"]
 
             # Clean up sources before validation
-            if isinstance(response_data.get('sources'), list):
+            if isinstance(response_data.get("sources"), list):
                 cleaned_sources = []
-                for source in response_data['sources']:
+                for source in response_data["sources"]:
                     if isinstance(source, str):
                         # Convert string sources to Source objects
-                        url = source if source.startswith('http') else f"https://{source}"
-                        cleaned_sources.append({
-                            "url": url,
-                            "name": source
-                        })
+                        url = (
+                            source if source.startswith("http") else f"https://{source}"
+                        )
+                        cleaned_sources.append({"url": url, "name": source})
                     elif isinstance(source, dict):
                         # Ensure URL has proper scheme
-                        url = source.get('url', '')
-                        if url and not url.startswith('http'):
-                            source['url'] = f"https://{url}"
+                        url = source.get("url", "")
+                        if url and not url.startswith("http"):
+                            source["url"] = f"https://{url}"
                         cleaned_sources.append(source)
-                response_data['sources'] = cleaned_sources
+                response_data["sources"] = cleaned_sources
 
             fact_check_response = FactCheckResponse(**response_data)
             return fact_check_response
@@ -108,8 +106,8 @@ Ensure all URLs in sources are complete (including https:// if missing) and each
                 detail=ErrorResponse(
                     detail=f"Invalid response format: {str(validation_error)}",
                     error_code="VALIDATION_ERROR",
-                    path="/check-facts"
-                ).dict()
+                    path="/check-facts",
+                ).dict(),
             )
 
     except Exception as e:
@@ -119,10 +117,11 @@ Ensure all URLs in sources are complete (including https:// if missing) and each
             detail=ErrorResponse(
                 detail="Error generating fact report",
                 error_code="FACT_CHECK_ERROR",
-                path="/check-facts"
-            ).dict()
+                path="/check-facts",
+            ).dict(),
         )
 
+
 @fact_check_router.post("/check-facts", response_model=FactCheckResponse)
 async def check_facts(request: FactCheckRequest):
     """
@@ -134,8 +133,8 @@ async def check_facts(request: FactCheckRequest):
             detail=ErrorResponse(
                 detail="Google API key or base URL is not configured",
                 error_code="CONFIGURATION_ERROR",
-                path="/check-facts"
-            ).dict()
+                path="/check-facts",
+            ).dict(),
         )
 
     headers = {"Content-Type": "application/json"}
@@ -149,14 +148,12 @@ async def check_facts(request: FactCheckRequest):
                 "query": request.query,
                 "languageCode": "en-US",
                 "reviewPublisherSiteFilter": source.domain,
-                "pageSize": 10
+                "pageSize": 10,
             }
 
             try:
                 response = await client.get(
-                    GOOGLE_FACT_CHECK_BASE_URL,
-                    params=params,
-                    headers=headers
+                    GOOGLE_FACT_CHECK_BASE_URL, params=params, headers=headers
                 )
                 response.raise_for_status()
                 json_response = response.json()
@@ -173,8 +170,7 @@ async def check_facts(request: FactCheckRequest):
 
         try:
             search_request = SearchRequest(
-                search_text=request.query,
-                source_types=["fact_checkers"]
+                search_text=request.query, source_types=["fact_checkers"]
             )
 
             ai_response = await search_websites(search_request)
@@ -187,6 +183,6 @@ async def check_facts(request: FactCheckRequest):
                 detail=ErrorResponse(
                     detail="No fact check results found",
                     error_code="NOT_FOUND",
-                    path="/check-facts"
-                ).dict()
+                    path="/check-facts",
+                ).dict(),
             )

app/api/scrap_websites.py

@@ -7,7 +7,7 @@ from pydantic import BaseModel
 from app.models.ai_fact_check_models import (
     AIFactCheckRequest,
     FactCheckSource,
-    SourceType
+    SourceType,
 )
 from app.websites.fact_checker_website import SOURCES, get_all_sources
 from app.api.ai_fact_check import ai_fact_check
@@ -18,10 +18,10 @@ class SearchRequest(BaseModel):
     search_text: str
     source_types: List[str] = ["fact_checkers"]
 
+
 # Configure logging
 logging.basicConfig(
-    level=logging.INFO,
-    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+    level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s"
 )
 logger = logging.getLogger(__name__)
 
@@ -38,39 +38,46 @@ def get_domain_from_url(url: str) -> str:
     try:
         parsed = urlparse(url)
         domain = parsed.netloc.lower()
-        if domain.startswith('www.'):
+        if domain.startswith("www."):
             domain = domain[4:]
         return domain
     except Exception as e:
         logger.error(f"Error extracting domain from URL {url}: {str(e)}")
         return ""
 
+
 def is_valid_source_domain(domain: str, sources: List[FactCheckSource]) -> bool:
     """Check if domain matches any source with improved matching logic."""
     if not domain:
         return False
 
     domain = domain.lower()
-    if domain.startswith('www.'):
+    if domain.startswith("www."):
         domain = domain[4:]
 
     for source in sources:
         source_domain = source.domain.lower()
-        if source_domain.startswith('www.'):
+        if source_domain.startswith("www."):
             source_domain = source_domain[4:]
 
-        if domain == source_domain or domain.endswith('.' + source_domain):
+        if domain == source_domain or domain.endswith("." + source_domain):
             return True
 
     return False
 
-async def build_enhanced_search_query(query: str, sources: List[FactCheckSource]) -> str:
+
+async def build_enhanced_search_query(
+    query: str, sources: List[FactCheckSource]
+) -> str:
     """Build search query with site restrictions."""
     site_queries = [f"site:{source.domain}" for source in sources]
     site_restriction = " OR ".join(site_queries)
     return f"({query}) ({site_restriction})"
 
-async def google_custom_search(query: str, sources: List[FactCheckSource], page: int = 1) -> Optional[Dict]:
+
+async def google_custom_search(
+    query: str, sources: List[FactCheckSource], page: int = 1
+) -> Optional[Dict]:
     """Perform Google Custom Search with enhanced query."""
     enhanced_query = await build_enhanced_search_query(query, sources)
     start_index = ((page - 1) * RESULTS_PER_PAGE) + 1
@@ -80,7 +87,7 @@ async def google_custom_search(query: str, sources: List[FactCheckSource], page:
         "cx": GOOGLE_ENGINE_ID,
         "q": enhanced_query,
         "num": RESULTS_PER_PAGE,
-        "start": start_index
+        "start": start_index,
     }
 
     async with httpx.AsyncClient(timeout=30.0) as client:
@@ -92,6 +99,7 @@ async def google_custom_search(query: str, sources: List[FactCheckSource], page:
             logger.error(f"Search error: {str(e)}")
             raise HTTPException(status_code=500, detail=f"Search error: {str(e)}")
 
+
 @scrap_websites_router.post("/search")
 async def search_websites(request: SearchRequest):
     # Get the source types from the request
@@ -115,7 +123,9 @@ async def search_websites(request: SearchRequest):
             if len(all_urls) >= 50:
                 break
 
-            search_response = await google_custom_search(request.search_text, selected_sources, page)
+            search_response = await google_custom_search(
+                request.search_text, selected_sources, page
+            )
 
             if not search_response or not search_response.get("items"):
                 break
@@ -132,25 +142,23 @@ async def search_websites(request: SearchRequest):
                         domain_results[domain] = []
 
                     if len(domain_results[domain]) < MAX_URLS_PER_DOMAIN:
-                        domain_results[domain].append({
-                            "url": url,
-                            "title": item.get("title", ""),
-                            "snippet": item.get("snippet", "")
-                        })
+                        domain_results[domain].append(
+                            {
+                                "url": url,
+                                "title": item.get("title", ""),
+                                "snippet": item.get("snippet", ""),
+                            }
+                        )
                         all_urls.append(url)
 
                 if len(all_urls) >= 50:
                     break
 
         if not all_urls:
-            return {
-                "status": "no_results",
-                "urls_found": 0
-            }
+            return {"status": "no_results", "urls_found": 0}
 
         fact_check_request = AIFactCheckRequest(
-            content=request.search_text,
-            urls=all_urls[:5]
+            content=request.search_text, urls=all_urls[:5]
         )
 
         return await ai_fact_check(fact_check_request)

app/config.py

@@ -4,7 +4,7 @@ from dotenv import load_dotenv
 load_dotenv()
 
 GOOGLE_API_KEY = os.environ["GOOGLE_API_KEY"]
-GOOGLE_FACT_CHECK_BASE_URL= os.environ["GOOGLE_FACT_CHECK_BASE_URL"]
+GOOGLE_FACT_CHECK_BASE_URL = os.environ["GOOGLE_FACT_CHECK_BASE_URL"]
 GOOGLE_ENGINE_ID = os.environ["GOOGLE_ENGINE_ID"]
 GOOGLE_SEARCH_URL = os.environ["GOOGLE_SEARCH_URL"]
 

app/models/ai_fact_check_models.py

@@ -4,38 +4,46 @@ from enum import Enum
 from datetime import datetime
 from urllib.parse import urlparse
 
+
 # Common Models
 class TokenUsage(BaseModel):
     prompt_tokens: Optional[int] = 0
     completion_tokens: Optional[int] = 0
     total_tokens: Optional[int] = 0
 
+
 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")
+    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"
+    model_config = ConfigDict(
+        json_schema_extra={
+            "example": {
+                "detail": "Error description",
+                "error_code": "ERROR_CODE",
+                "timestamp": "2024-12-09T16:49:30.905765",
+                "path": "/check-facts",
+            }
         }
-    })
+    )
+
 
 # Fact Check Models
 class Publisher(BaseModel):
     name: str
     site: Optional[str] = Field(None, description="Publisher's website")
 
-    @validator('site')
+    @validator("site")
     def validate_site(cls, v):
-        if v and not (v.startswith('http://') or v.startswith('https://')):
+        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
@@ -44,21 +52,25 @@ class ClaimReview(BaseModel):
     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 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)
 
+
 # Verification Models
 class VerificationResult(BaseModel):
     verdict: str = Field(..., description="True/False/Insufficient Information")
@@ -67,44 +79,46 @@ class VerificationResult(BaseModel):
     reasoning: str
     missing_info: Optional[str] = None
 
-    model_config = ConfigDict(json_schema_extra={
-        "example": {
-            "verdict": "True",
-            "confidence": "High",
-            "evidence": ["Direct quote from source supporting the claim"],
-            "reasoning": "Detailed analysis of why the claim is considered true",
-            "missing_info": "Any caveats or limitations of the verification"
+    model_config = ConfigDict(
+        json_schema_extra={
+            "example": {
+                "verdict": "True",
+                "confidence": "High",
+                "evidence": ["Direct quote from source supporting the claim"],
+                "reasoning": "Detailed analysis of why the claim is considered true",
+                "missing_info": "Any caveats or limitations of the verification",
+            }
         }
-    })
+    )
+
 
 # Request Models
 class BaseFactCheckRequest(BaseModel):
     content: str = Field(
-        ...,
-        min_length=10,
-        max_length=1000,
-        description="The claim to be fact-checked"
+        ..., min_length=10, max_length=1000, description="The claim to be fact-checked"
     )
 
-    @validator('content')
+    @validator("content")
     def validate_content(cls, v):
         if not v.strip():
             raise ValueError("Content cannot be empty or just whitespace")
         return v.strip()
 
+
 class GoogleFactCheckRequest(BaseFactCheckRequest):
     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)
 
+
 class AIFactCheckRequest(BaseFactCheckRequest):
     urls: List[str] = Field(
         ...,
         min_items=1,
         max_items=5,
-        description="List of URLs to check the content against. URLs will be prefixed with https:// if protocol is missing"
+        description="List of URLs to check the content against. URLs will be prefixed with https:// if protocol is missing",
     )
 
-    @validator('urls')
+    @validator("urls")
     def validate_urls(cls, urls):
         validated_urls = []
         for url in urls:
@@ -112,8 +126,8 @@ class AIFactCheckRequest(BaseFactCheckRequest):
                 raise ValueError("URL cannot be empty")
 
             # Add https:// if no protocol specified
-            if not url.startswith(('http://', 'https://')):
-                url = f'https://{url}'
+            if not url.startswith(("http://", "https://")):
+                url = f"https://{url}"
 
             try:
                 result = urlparse(url)
@@ -125,15 +139,18 @@ class AIFactCheckRequest(BaseFactCheckRequest):
 
         return validated_urls
 
-    model_config = ConfigDict(json_schema_extra={
-        "example": {
-            "content": "Indian flag was drawn in BUET campus",
-            "urls": [
-                "www.altnews.in/article-about-flag",
-                "www.another-source.com/related-news"
-            ]
+    model_config = ConfigDict(
+        json_schema_extra={
+            "example": {
+                "content": "Indian flag was drawn in BUET campus",
+                "urls": [
+                    "www.altnews.in/article-about-flag",
+                    "www.another-source.com/related-news",
+                ],
+            }
         }
-    })
+    )
+
 
 # Response Models
 class BaseFactCheckResponse(BaseModel):
@@ -141,17 +158,20 @@ class BaseFactCheckResponse(BaseModel):
     token_usage: TokenUsage
     sources: List[str]
 
-    model_config = ConfigDict(json_schema_extra={
-        "example": {
-            "query": "Example statement to verify",
-            "token_usage": {
-                "prompt_tokens": 100,
-                "completion_tokens": 50,
-                "total_tokens": 150
-            },
-            "sources": ["source1.com", "source2.com"],
+    model_config = ConfigDict(
+        json_schema_extra={
+            "example": {
+                "query": "Example statement to verify",
+                "token_usage": {
+                    "prompt_tokens": 100,
+                    "completion_tokens": 50,
+                    "total_tokens": 150,
+                },
+                "sources": ["source1.com", "source2.com"],
+            }
         }
-    })
+    )
+
 
 class GoogleFactCheckResponse(BaseFactCheckResponse):
     total_claims_found: int
@@ -159,70 +179,79 @@ class GoogleFactCheckResponse(BaseFactCheckResponse):
     verification_result: Dict[str, Any]
     summary: Dict[str, int]
 
-    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"
-                }]
-            }],
-            "verification_result": {
-                "verdict": "True",
-                "confidence": "High",
-                "evidence": ["Supporting evidence"],
-                "reasoning": "Detailed analysis"
-            },
-            "sources": ["factchecker.com"],
-            "token_usage": {
-                "prompt_tokens": 100,
-                "completion_tokens": 50,
-                "total_tokens": 150
-            },
-            "summary": {
-                "total_sources": 1,
-                "fact_checking_sites_queried": 10
-            }
-        }
-    })
-
-class AIFactCheckResponse(BaseFactCheckResponse):
-    verification_result: Dict[str, VerificationResult]  # Changed to Dict to store results per URL
-
-    model_config = ConfigDict(json_schema_extra={
-        "example": {
-            "query": "Indian flag was drawn in BUET campus",
-            "verification_result": {
-                "https://www.source1.com": {
+    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",
+                            }
+                        ],
+                    }
+                ],
+                "verification_result": {
                     "verdict": "True",
                     "confidence": "High",
-                    "evidence": ["Supporting evidence from source 1"],
-                    "reasoning": "Detailed analysis from source 1",
-                    "missing_info": None
+                    "evidence": ["Supporting evidence"],
+                    "reasoning": "Detailed analysis",
                 },
-                "https://www.source2.com": {
-                    "verdict": "True",
-                    "confidence": "Medium",
-                    "evidence": ["Supporting evidence from source 2"],
-                    "reasoning": "Analysis from source 2",
-                    "missing_info": "Additional context needed"
-                }
-            },
-            "sources": ["source1.com", "source2.com"],
-            "token_usage": {
-                "prompt_tokens": 200,
-                "completion_tokens": 100,
-                "total_tokens": 300
+                "sources": ["factchecker.com"],
+                "token_usage": {
+                    "prompt_tokens": 100,
+                    "completion_tokens": 50,
+                    "total_tokens": 150,
+                },
+                "summary": {"total_sources": 1, "fact_checking_sites_queried": 10},
             }
         }
-    })
+    )
+
+
+class AIFactCheckResponse(BaseFactCheckResponse):
+    verification_result: Dict[
+        str, VerificationResult
+    ]  # Changed to Dict to store results per URL
+
+    model_config = ConfigDict(
+        json_schema_extra={
+            "example": {
+                "query": "Indian flag was drawn in BUET campus",
+                "verification_result": {
+                    "https://www.source1.com": {
+                        "verdict": "True",
+                        "confidence": "High",
+                        "evidence": ["Supporting evidence from source 1"],
+                        "reasoning": "Detailed analysis from source 1",
+                        "missing_info": None,
+                    },
+                    "https://www.source2.com": {
+                        "verdict": "True",
+                        "confidence": "Medium",
+                        "evidence": ["Supporting evidence from source 2"],
+                        "reasoning": "Analysis from source 2",
+                        "missing_info": "Additional context needed",
+                    },
+                },
+                "sources": ["source1.com", "source2.com"],
+                "token_usage": {
+                    "prompt_tokens": 200,
+                    "completion_tokens": 100,
+                    "total_tokens": 300,
+                },
+            }
+        }
+    )
+
 
 # Backwards compatibility aliases
 FactCheckRequest = GoogleFactCheckRequest

app/models/fact_check_models.py

@@ -3,74 +3,73 @@ from typing import List, Literal, Union
 from datetime import datetime
 from enum import Enum
 
+
 class VerdictEnum(str, Enum):
     TRUE = "True"
     FALSE = "False"
     PARTIALLY_TRUE = "Partially True"
     UNVERIFIED = "Unverified"
 
+
 class ConfidenceEnum(str, Enum):
     HIGH = "High"
     MEDIUM = "Medium"
     LOW = "Low"
 
+
 class FactCheckRequest(BaseModel):
     query: str = Field(
         ...,
         min_length=3,
         max_length=500,
         description="The claim or statement to be fact-checked",
-        example="Did NASA confirm finding alien structures on Mars in 2024?"
+        example="Did NASA confirm finding alien structures on Mars in 2024?",
     )
 
+
 class Source(BaseModel):
     url: str
     name: str = ""
 
-    @validator('url')
+    @validator("url")
     def validate_url(cls, v):
         # Basic URL validation without requiring HTTP/HTTPS
         if not v or len(v) < 3:
             raise ValueError("URL must not be empty and must be at least 3 characters")
         return v
 
+
 class FactCheckResponse(BaseModel):
     claim: str = Field(
         ...,
         min_length=10,
         max_length=1000,
-        description="The exact claim being verified"
-    )
-    verdict: VerdictEnum = Field(
-        ...,
-        description="The verification verdict"
+        description="The exact claim being verified",
     )
+    verdict: VerdictEnum = Field(..., description="The verification verdict")
     confidence: ConfidenceEnum = Field(
-        ...,
-        description="Confidence level in the verdict"
+        ..., description="Confidence level in the verdict"
     )
     sources: List[Source] = Field(
-        ...,
-        min_items=1,
-        description="List of sources used in verification"
+        ..., min_items=1, description="List of sources used in verification"
     )
     evidence: str = Field(
         ...,
         min_length=20,
         max_length=500,
-        description="Concise summary of key evidence"
+        description="Concise summary of key evidence",
     )
     explanation: str = Field(
         ...,
         min_length=50,
         max_length=1000,
-        description="Detailed explanation of verification findings"
+        description="Detailed explanation of verification findings",
     )
     additional_context: str = Field(
         ...,
         min_length=20,
         max_length=500,
-        description="Important context about the verification"
+        description="Important context about the verification",
     )
 
     class Config:
@@ -82,19 +81,20 @@ class FactCheckResponse(BaseModel):
                 "sources": [
                     {
                         "url": "https://www.nasa.gov/mars-exploration",
-                        "name": "NASA Mars Exploration"
+                        "name": "NASA Mars Exploration",
                     },
                     {
                         "url": "https://factcheck.org/2024/mars-claims",
-                        "name": "FactCheck.org"
-                    }
+                        "name": "FactCheck.org",
+                    },
                 ],
                 "evidence": "NASA has made no such announcement. Recent Mars rover images show natural rock formations.",
                 "explanation": "Multiple fact-checking organizations investigated this claim. NASA's official communications and Mars mission reports from 2024 contain no mention of alien structures. The viral images being shared are misidentified natural geological formations.",
-                "additional_context": "Similar false claims about alien structures on Mars have circulated periodically since the first Mars rovers began sending back images."
+                "additional_context": "Similar false claims about alien structures on Mars have circulated periodically since the first Mars rovers began sending back images.",
             }
         }
 
+
 class ErrorResponse(BaseModel):
     detail: str
     error_code: str = Field(..., example="VALIDATION_ERROR")

app/models/scrap_websites_models.py

@@ -1,38 +1,46 @@
 from pydantic import BaseModel
 from typing import List, Dict
 
+
 class SearchRequest(BaseModel):
     search_text: str
     source_types: List[str] = ["fact_checkers"]
 
+
 class Publisher(BaseModel):
     name: str
     site: str
 
+
 class ClaimReview(BaseModel):
     publisher: Publisher
     textualRating: str
 
+
 class Claim(BaseModel):
     claimReview: List[ClaimReview]
     claimant: str
     text: str
 
+
 class Summary(BaseModel):
     fact_checking_sites_queried: int
     total_sources: int
 
+
 class TokenUsage(BaseModel):
     prompt_tokens: int
     completion_tokens: int
     total_tokens: int
 
+
 class VerificationResult(BaseModel):
     verdict: str
     confidence: str
     evidence: List[str]
     reasoning: str
 
+
 class EnhancedFactCheckResponse(BaseModel):
     query: str
     results: List[Claim]

app/services/openai_client.py

@@ -9,6 +9,7 @@ import json
 import aiohttp
 from bs4 import BeautifulSoup
 
+
 class OpenAIClient:
     def __init__(self, api_key: str):
         """
@@ -16,7 +17,9 @@ class OpenAIClient:
         """
         openai.api_key = api_key
 
-    async def generate_text_response(self, system_prompt: str, user_prompt: str, max_tokens: int) -> dict:
+    async def generate_text_response(
+        self, system_prompt: str, user_prompt: str, max_tokens: int
+    ) -> dict:
         """
         Generate a response using OpenAI's chat completion API.
         """
@@ -25,19 +28,19 @@ class OpenAIClient:
                 model="gpt-4",
                 messages=[
                     {"role": "system", "content": system_prompt},
-                    {"role": "user", "content": user_prompt}
+                    {"role": "user", "content": user_prompt},
                 ],
-                max_tokens=max_tokens
+                max_tokens=max_tokens,
             )
-            content = response['choices'][0]['message']['content']
+            content = response["choices"][0]["message"]["content"]
             # Parse the JSON string into a dictionary
             parsed_content = json.loads(content)
 
             return {
                 "response": parsed_content,  # Now returns a dictionary instead of string
-                "prompt_tokens": response['usage']['prompt_tokens'],
-                "completion_tokens": response['usage']['completion_tokens'],
-                "total_tokens": response['usage']['total_tokens']
+                "prompt_tokens": response["usage"]["prompt_tokens"],
+                "completion_tokens": response["usage"]["completion_tokens"],
+                "total_tokens": response["usage"]["total_tokens"],
             }
         except json.JSONDecodeError as e:
             raise Exception(f"Failed to parse OpenAI response as JSON: {str(e)}")
@@ -50,14 +53,14 @@ class OpenAIClient:
         """
         try:
             response = openai.Embedding.create(
-                input=texts,
-                model="text-embedding-ada-002"
+                input=texts, model="text-embedding-ada-002"
             )
-            embeddings = [data['embedding'] for data in response['data']]
+            embeddings = [data["embedding"] for data in response["data"]]
             return embeddings
         except Exception as e:
             raise Exception(f"OpenAI embedding error: {str(e)}")
 
+
 class AIFactChecker:
     def __init__(self, openai_client: OpenAIClient):
         """Initialize the fact checker with OpenAI client."""
@@ -66,7 +69,7 @@ class AIFactChecker:
             chunk_size=1000,
             chunk_overlap=200,
             length_function=len,
-            separators=["\n\n", "\n", ".", "!", "?", ",", " ", ""]
+            separators=["\n\n", "\n", ".", "!", "?", ",", " ", ""],
         )
 
     async def scrape_webpage(self, url: str) -> List[Document]:
@@ -75,23 +78,27 @@ class AIFactChecker:
             async with aiohttp.ClientSession() as session:
                 async with session.get(url) as response:
                     if response.status != 200:
-                        raise Exception(f"Failed to fetch URL: {url}, status: {response.status}")
+                        raise Exception(
+                            f"Failed to fetch URL: {url}, status: {response.status}"
+                        )
 
                     html_content = await response.text()
 
                     # Parse HTML with BeautifulSoup
-                    soup = BeautifulSoup(html_content, 'html.parser')
+                    soup = BeautifulSoup(html_content, "html.parser")
 
                     # Create a Document with the parsed content
                     doc = Document(
-                        page_content=soup.get_text(separator='\n', strip=True),
-                        metadata={"source": url}
+                        page_content=soup.get_text(separator="\n", strip=True),
+                        metadata={"source": url},
                     )
 
                     # Split into chunks
                     docs_chunks = self.text_splitter.split_documents([doc])
 
-                    logger.info(f"Successfully scraped webpage | chunks={len(docs_chunks)}")
+                    logger.info(
+                        f"Successfully scraped webpage | chunks={len(docs_chunks)}"
+                    )
                     return docs_chunks
 
         except Exception as e:
@@ -102,7 +109,7 @@ class AIFactChecker:
         self,
         query_embedding: List[float],
         doc_embeddings: List[List[float]],
-        docs: List[Document]
+        docs: List[Document],
     ) -> List[Document]:
         """Find most relevant document chunks using cosine similarity."""
         try:
@@ -120,7 +127,9 @@ class AIFactChecker:
             logger.error(f"Error finding relevant chunks | error={str(e)}")
             raise
 
-    async def verify_fact(self, query: str, relevant_docs: List[Document]) -> Dict[str, Any]:
+    async def verify_fact(
+        self, query: str, relevant_docs: List[Document]
+    ) -> Dict[str, Any]:
         """Verify fact using OpenAI's API with context from relevant documents."""
         try:
             context = "\n\n".join([doc.page_content for doc in relevant_docs])
@@ -145,12 +154,17 @@ class AIFactChecker:
             Analyze the statement based on the provided context and return your response in the specified JSON format."""
 
             response = await self.openai_client.generate_text_response(
-                system_prompt=system_prompt,
-                user_prompt=user_prompt,
-                max_tokens=800
+                system_prompt=system_prompt, user_prompt=user_prompt, max_tokens=800
             )
 
-            sources = list(set([doc.metadata.get('source', 'Unknown source') for doc in relevant_docs]))
+            sources = list(
+                set(
+                    [
+                        doc.metadata.get("source", "Unknown source")
+                        for doc in relevant_docs
+                    ]
+                )
+            )
 
             return {
                 "verification_result": response["response"],  # This is now a dictionary
@@ -158,8 +172,8 @@ class AIFactChecker:
                 "token_usage": {
                     "prompt_tokens": response["prompt_tokens"],
                     "completion_tokens": response["completion_tokens"],
-                    "total_tokens": response["total_tokens"]
-                }
+                    "total_tokens": response["total_tokens"],
+                },
             }
 
         except Exception as e:
@@ -175,7 +189,9 @@ class AIFactChecker:
             doc_embeddings = self.openai_client.get_embeddings(doc_texts)
             query_embedding = self.openai_client.get_embeddings([query])
 
-            relevant_docs = self.find_relevant_chunks(query_embedding[0], doc_embeddings, docs)
+            relevant_docs = self.find_relevant_chunks(
+                query_embedding[0], doc_embeddings, docs
+            )
             verification_result = await self.verify_fact(query, relevant_docs)
 
             return verification_result

app/websites/fact_checker_website.py

@@ -1,120 +1,125 @@
 from typing import Dict, List
 import requests
 from fastapi import HTTPException
-from app.models.ai_fact_check_models import FactCheckSource, ErrorResponse, FactCheckRequest, SourceType
+from app.models.ai_fact_check_models import (
+    FactCheckSource,
+    ErrorResponse,
+    FactCheckRequest,
+    SourceType,
+)
 
 # Sources configuration with validation
 SOURCES = {
     "fact_checkers": [
         FactCheckSource(domain=domain, type=SourceType.FACT_CHECKER, priority=1)
         for domain in [
-    "snopes.com",
-    "politifact.com",
-    "factcheck.org",
-    "reuters.com/fact-check",
-    "apnews.com/hub/ap-fact-check",
-    "bbc.com/news/reality_check",
-    "fullfact.org",
-    "afp.com/fact-check",
-    "truthorfiction.com",
-    "leadstories.com",
-    "checkyourfact.com",
-    "washingtonpost.com/news/fact-checker",
-    "factcheck.kz",
-    "poynter.org/ifcn",
-    "factcheckeu.info",
-    "africacheck.org",
-    "thequint.com/webqoof",
-    "altnews.in",
-    "facta.news",
-    "factcheckni.org",
-    "mythdetector.ge",
-    "verificado.mx",
-    "euvsdisinfo.eu",
-    "factcheck.afp.com",
-    "newtral.es",
-    "maldita.es",
-    "faktograf.hr",
-    "demagog.org.pl",
-    "factnameh.com",
-    "faktiskt.se",
-    "teyit.org",
-    "factly.in",
-    "boom.live",
-    "stopfake.org",
-    "factcheck.ge",
-    "factcheck.kg",
-    "factcheck.uz",
-    "factcheck.tj",
-    "factcheck.az",
-    "factcheck.am",
-    "factcheck.md",
-    "verafiles.org",
-    "rappler.com/fact-check",
-    "vera.com.gt",
-    "chequeado.com",
-    "aosfatos.org",
-    "lasillavacia.com/detector-mentiras",
-    "colombiacheck.com",
-    "ecuadorchequea.com",
-    "elsurti.com/checado",
-    "verificat.cat",
-    "mafindo.or.id",
-    "tempo.co/cek-fakta",
-    "factcheck.mk",
-    "raskrinkavanje.ba",
-    "faktograf.hr",
-    "demagog.cz",
-    "faktabaari.fi",
-    "correctiv.org",
-    "mimikama.at",
-    "factcheck.vlaanderen",
-    "factuel.afp.com",
-    "nieuwscheckers.nl",
-    "faktisk.no",
-    "tjekdet.dk",
-    "ellinikahoaxes.gr",
-    "faktograf.id",
-    "stopfake.kz",
-    "pesacheck.org",
-    "dubawa.org",
-    "namibiafactcheck.org.na",
-    "zimfact.org",
-    "ghanafact.com",
-    "factspace.africa",
-    "factcrescendo.com",
-    "vishvasnews.com",
-    "factcheck.lk",
-    "newschecker.in",
-    "boomlive.in",
-    "digiteye.in",
-    "indiatoday.in/fact-check",
-    "factcrescendo.com",
-    "piyasa.com/fact-check",
-    "taiwanese.facts.news",
-    "taiwanfactcheck.com",
-    "mygopen.com",
-    "tfc-taiwan.org.tw",
-    "cofacts.tw",
-    "rumor.taipei",
-    "fact.qq.com",
-    "factcheck.afp.com/list",
-    "acfta.org",
-    "crosscheck.firstdraftnews.org",
-    "healthfeedback.org",
-    "climatefeedback.org",
-    "sciencefeedback.co",
-    "factcheck.aap.com.au",
-    "emergent.info",
-    "hoax-slayer.net",
-    "truthorfiction.com",
-    "factcheck.media",
-    "mediawise.org",
-    "thejournal.ie/factcheck",
-    "journalistsresource.org",
-    "metafact.io",
-    "reporterslab.org/fact-checking"
-]
+            "snopes.com",
+            "politifact.com",
+            "factcheck.org",
+            "reuters.com/fact-check",
+            "apnews.com/hub/ap-fact-check",
+            "bbc.com/news/reality_check",
+            "fullfact.org",
+            "afp.com/fact-check",
+            "truthorfiction.com",
+            "leadstories.com",
+            "checkyourfact.com",
+            "washingtonpost.com/news/fact-checker",
+            "factcheck.kz",
+            "poynter.org/ifcn",
+            "factcheckeu.info",
+            "africacheck.org",
+            "thequint.com/webqoof",
+            "altnews.in",
+            "facta.news",
+            "factcheckni.org",
+            "mythdetector.ge",
+            "verificado.mx",
+            "euvsdisinfo.eu",
+            "factcheck.afp.com",
+            "newtral.es",
+            "maldita.es",
+            "faktograf.hr",
+            "demagog.org.pl",
+            "factnameh.com",
+            "faktiskt.se",
+            "teyit.org",
+            "factly.in",
+            "boom.live",
+            "stopfake.org",
+            "factcheck.ge",
+            "factcheck.kg",
+            "factcheck.uz",
+            "factcheck.tj",
+            "factcheck.az",
+            "factcheck.am",
+            "factcheck.md",
+            "verafiles.org",
+            "rappler.com/fact-check",
+            "vera.com.gt",
+            "chequeado.com",
+            "aosfatos.org",
+            "lasillavacia.com/detector-mentiras",
+            "colombiacheck.com",
+            "ecuadorchequea.com",
+            "elsurti.com/checado",
+            "verificat.cat",
+            "mafindo.or.id",
+            "tempo.co/cek-fakta",
+            "factcheck.mk",
+            "raskrinkavanje.ba",
+            "faktograf.hr",
+            "demagog.cz",
+            "faktabaari.fi",
+            "correctiv.org",
+            "mimikama.at",
+            "factcheck.vlaanderen",
+            "factuel.afp.com",
+            "nieuwscheckers.nl",
+            "faktisk.no",
+            "tjekdet.dk",
+            "ellinikahoaxes.gr",
+            "faktograf.id",
+            "stopfake.kz",
+            "pesacheck.org",
+            "dubawa.org",
+            "namibiafactcheck.org.na",
+            "zimfact.org",
+            "ghanafact.com",
+            "factspace.africa",
+            "factcrescendo.com",
+            "vishvasnews.com",
+            "factcheck.lk",
+            "newschecker.in",
+            "boomlive.in",
+            "digiteye.in",
+            "indiatoday.in/fact-check",
+            "factcrescendo.com",
+            "piyasa.com/fact-check",
+            "taiwanese.facts.news",
+            "taiwanfactcheck.com",
+            "mygopen.com",
+            "tfc-taiwan.org.tw",
+            "cofacts.tw",
+            "rumor.taipei",
+            "fact.qq.com",
+            "factcheck.afp.com/list",
+            "acfta.org",
+            "crosscheck.firstdraftnews.org",
+            "healthfeedback.org",
+            "climatefeedback.org",
+            "sciencefeedback.co",
+            "factcheck.aap.com.au",
+            "emergent.info",
+            "hoax-slayer.net",
+            "truthorfiction.com",
+            "factcheck.media",
+            "mediawise.org",
+            "thejournal.ie/factcheck",
+            "journalistsresource.org",
+            "metafact.io",
+            "reporterslab.org/fact-checking",
+        ]
     ],
     "news_sites": [
         FactCheckSource(domain=domain, type=SourceType.NEWS_SITE, priority=2)
@@ -133,16 +138,14 @@ SOURCES = {
             "www.risingbd.com/english",
             "www.dailyindustry.news",
             "www.bangladeshpost.net",
-            "www.daily-bangladesh.com/english"
+            "www.daily-bangladesh.com/english",
         ]
-    ]
+    ],
 }
 
+
 async def fetch_fact_checks(
-    api_key: str,
-    base_url: str,
-    query: str,
-    site: FactCheckSource
+    api_key: str, base_url: str, query: str, site: FactCheckSource
 ) -> Dict:
     """
     Fetch fact checks from a specific site using the Google Fact Check API
@@ -156,7 +159,7 @@ async def fetch_fact_checks(
             "query": query,
             "languageCode": "en-US",
             "reviewPublisherSiteFilter": site.domain,
-            "pageSize": 10
+            "pageSize": 10,
         }
 
         response = requests.get(base_url, params=params)
@@ -168,19 +171,18 @@ async def fetch_fact_checks(
             detail=ErrorResponse(
                 detail=f"Error fetching from {site.domain}: {str(e)}",
                 error_code="FACT_CHECK_SERVICE_ERROR",
-                path="/check-facts"
-            ).dict()
+                path="/check-facts",
+            ).dict(),
         )
     except ValueError as e:
         raise HTTPException(
             status_code=500,
             detail=ErrorResponse(
-                detail=str(e),
-                error_code="CONFIGURATION_ERROR",
-                path="/check-facts"
-            ).dict()
+                detail=str(e), error_code="CONFIGURATION_ERROR", path="/check-facts"
+            ).dict(),
         )
 
+
 def get_all_sources() -> List[FactCheckSource]:
     """
     Get all sources sorted by priority

main.py

@@ -7,9 +7,7 @@ from app.config import FRONTEND_URL
 
 # Initialize FastAPI app
 app = FastAPI(
-    title="Your API Title",
-    description="Your API Description",
-    version="1.0.0"
+    title="Your API Title", description="Your API Description", version="1.0.0"
 )
 
 # CORS configuration
@@ -30,16 +28,19 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
+
 # Basic root endpoint
 @app.get("/")
 async def root():
     return {"message": "Welcome to your FastAPI application"}
 
+
 # Health check endpoint
 @app.get("/health")
 async def health_check():
     return {"status": "healthy"}
 
+
 app.include_router(fact_check_router, prefix="")
 app.include_router(aifact_check_router, prefix="")
 app.include_router(scrap_websites_router, prefix="")
@@ -50,4 +51,5 @@ app.include_router(scrap_websites_router, prefix="")
 
 if __name__ == "__main__":
     import uvicorn
+
     uvicorn.run("main:app", host="0.0.0.0", port=8000, reload=True)

tests/test_main.py

@@ -3,16 +3,19 @@ from main import app
 
 client = TestClient(app)
 
+
 def test_root_endpoint():
     response = client.get("/")
     assert response.status_code == 200
     assert response.json() == {"message": "Welcome to your FastAPI application"}
 
+
 def test_health_endpoint():
     response = client.get("/health")
     assert response.status_code == 200
     assert response.json() == {"status": "healthy"}
 
+
 def test_cors_headers():
     response = client.get("/", headers={"Origin": "http://localhost:5173"})
     assert response.headers["access-control-allow-origin"] == "http://localhost:5173"