update

Dev local

See merge request planpostai/fact-checker-backend!3

.flake8

@@ -0,0 +1,4 @@
+[flake8]
+max-line-length = 100
+exclude = .git,__pycache__,dist,*.egg-info,venv
+extend-ignore = E203

.gitignore

@@ -1,4 +1,42 @@
-env
+# Environment
+env/
 .env
+venv/
+ENV/
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+.Python
+*.so
+.pytest_cache/
+.coverage
+.coverage.*
+coverage.xml
+*.cover
+htmlcov/
+
+# IDEs and editors
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+
+# Project specific
 test.py
-__pycache__
+*.log
+.pip-cache/
+
+# Temporary files
+*.tmp
+.DS_Store
+
+# Distribution / packaging
+dist/
+build/
+*.egg-info/
+
+# Docker
+.docker/

.gitlab-ci.yml

@@ -0,0 +1,52 @@
+image: python:3.10-slim
+
+variables:
+  PIP_CACHE_DIR: "$CI_PROJECT_DIR/.pip-cache"
+  PYTHONPATH: "$CI_PROJECT_DIR"
+
+cache:
+  paths:
+    - .pip-cache
+    - venv/
+
+stages:
+  - setup
+  - test
+
+before_script:
+  - apt-get update
+  - apt-get install -y curl
+  - python --version
+  - pip install virtualenv
+  - virtualenv venv
+  - source venv/bin/activate
+
+setup:
+  stage: setup
+  script:
+    - pip install --no-cache-dir -r requirements.txt
+  artifacts:
+    paths:
+      - venv/
+    expire_in: 1 hour
+
+test:
+  stage: test
+  needs:
+    - setup
+  script:
+    # Run all tests
+    - pytest tests/ -v
+    # Start FastAPI server
+    - uvicorn main:app --host 0.0.0.0 --port 8000 &
+    # Wait for server to start
+    - sleep 15
+    # Test health endpoint
+    - |
+      RESPONSE=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:8000/health)
+      if [ "$RESPONSE" = "200" ]; then
+        echo "✅ Health check passed"
+      else
+        echo "❌ Health check failed with status $RESPONSE"
+        exit 1
+      fi

Dockerfile

@@ -0,0 +1,8 @@
+
+FROM python:3.12
+COPY requirements.txt requirements.txt
+RUN pip install --upgrade pip
+RUN pip install -r requirements.txt
+COPY . .
+EXPOSE 8000
+ENTRYPOINT ["gunicorn", "main:app", "--workers", "4", "--timeout", "90", "--worker-class", "uvicorn.workers.UvicornWorker", "--bind", "0.0.0.0:8000"]

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={
+    responses={400: {"model": ErrorResponse}, 500: {"model": ErrorResponse}},
-        400: {"model": ErrorResponse},
-        500: {"model": ErrorResponse}
-    }
 )
 async def ai_fact_check(request: AIFactCheckRequest):
     """
@@ -40,14 +38,14 @@ async def ai_fact_check(request: AIFactCheckRequest):
         total_prompt_tokens = 0
         total_completion_tokens = 0
         total_tokens = 0
-        
+
         # Process all URLs concurrently
         tasks = [
             fact_checker.check_fact(url=url, query=request.content)
             for url in request.urls
         ]
         fact_check_results = await asyncio.gather(*tasks, return_exceptions=True)
-        
+
         # Process results
         for url, result in zip(request.urls, fact_check_results):
             if isinstance(result, Exception):
@@ -57,21 +55,21 @@ 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
-                
+
             verification_result = VerificationResult(
                 verdict=result["verification_result"]["verdict"],
                 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
             all_sources.update(result["sources"])
-            
+
             # Accumulate token usage
             total_prompt_tokens += result["token_usage"]["prompt_tokens"]
             total_completion_tokens += result["token_usage"]["completion_tokens"]
@@ -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),
+                detail=str(e), error_code="INVALID_URL", path="/aicheck-facts"
-                error_code="INVALID_URL",
+            ).dict(),
-                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"
+                path="/aicheck-facts",
-            ).dict()
+            ).dict(),
-        )
+        )

app/api/fact_check.py

@@ -1,20 +1,289 @@
 from fastapi import APIRouter, HTTPException
+import asyncio
+import logging
 import httpx
-from app.config import GOOGLE_API_KEY, GOOGLE_FACT_CHECK_BASE_URL, OPENAI_API_KEY
+import json
+import re
+from typing import Union, Optional, Dict, Any
+from datetime import datetime
+from app.config import OPENAI_API_KEY,PERPLEXITY_API_KEY
 from app.api.scrap_websites import search_websites, SearchRequest
-from app.services.openai_client import OpenAIClient
+from app.services.openai_client import OpenAIClient, AIFactChecker
+from app.services.image_text_extractor import ImageTextExtractor
+from app.models.ai_fact_check_models import AIFactCheckResponse
 from app.models.fact_check_models import (
-    FactCheckRequest, 
+    FactCheckRequest,
-    FactCheckResponse, 
+    FactCheckResponse,
-    ErrorResponse,
+    UnverifiedFactCheckResponse,
-    Source
+    Source,
-)
+    VerdictEnum,
-from app.websites.fact_checker_website import get_all_sources
+    ConfidenceEnum
+) 
+
+# Setup logging
+logger = logging.getLogger(__name__)
 
 fact_check_router = APIRouter()
 openai_client = OpenAIClient(OPENAI_API_KEY)
+ai_fact_checker = AIFactChecker(openai_client)
+image_text_extractor = ImageTextExtractor(OPENAI_API_KEY)
 
-async def generate_fact_report(query: str, fact_check_data: dict) -> FactCheckResponse:
+
+async def process_url_content(url: str) -> Optional[str]:
+    """Extract text content from the provided URL."""
+    try:
+        # Add await here
+        text = await image_text_extractor.extract_text(url, is_url=True)
+        if text:
+            logger.info(f"Successfully extracted text from URL: {text}")
+        else:
+            logger.warning(f"No text could be extracted from URL: {url}")
+        return text
+    except Exception as e:
+        logger.error(f"Error extracting text from URL: {str(e)}")
+        return None
+
+# Assuming the enums and models like FactCheckResponse, VerdictEnum, etc., are already imported
+
+async def process_fact_check(query: str) -> Union[FactCheckResponse, UnverifiedFactCheckResponse]:
+    if not PERPLEXITY_API_KEY:
+        logger.error("Perplexity API key not configured")
+        return UnverifiedFactCheckResponse(
+            claim=query,
+            verdict=VerdictEnum.UNVERIFIED,
+            confidence=ConfidenceEnum.LOW,
+            sources=[],
+            evidence="The fact-checking service is not properly configured.",
+            explanation="The system is missing required API configuration for fact-checking services.",
+            additional_context="This is a temporary system configuration issue."
+        )
+
+    url = "https://api.perplexity.ai/chat/completions"
+    headers = {
+        "accept": "application/json",
+        "content-type": "application/json",
+        "Authorization": f"Bearer {PERPLEXITY_API_KEY}"
+    }
+
+    payload = {
+        "model": "sonar",
+        "messages": [
+            {
+                "role": "system",
+                "content": (
+                    "You are a precise fact checker. Analyze the following claim and determine if it's true, false, or partially true. "
+                    "Provide a clear verdict, confidence level (HIGH, MEDIUM, LOW), and cite reliable sources. "
+                    "Format your response as JSON with fields: verdict, confidence, sources (array of URLs), "
+                    "evidence (key facts as a string), and explanation (detailed reasoning as a string)."
+                )
+            },
+            {
+                "role": "user",
+                "content": f"Fact check this claim: {query}"
+            }
+        ]
+    }
+
+    try:
+        async with httpx.AsyncClient(timeout=30) as client:
+            response = await client.post(url, headers=headers, json=payload)
+            response.raise_for_status()
+            result = response.json()
+            perplexity_response = result["choices"][0]["message"]["content"]
+
+            # Attempt to extract JSON
+            try:
+                parsed_data = json.loads(perplexity_response)
+            except json.JSONDecodeError:
+                match = re.search(r'\{.*\}', perplexity_response, re.DOTALL)
+                if match:
+                    parsed_data = json.loads(match.group(0))
+                else:
+                    parsed_data = extract_fact_check_info(perplexity_response)
+
+            verdict_mapping = {
+                "true": VerdictEnum.TRUE,
+                "false": VerdictEnum.FALSE,
+                "partially true": VerdictEnum.PARTIALLY_TRUE,
+                "partially false": VerdictEnum.PARTIALLY_TRUE,
+                "unverified": VerdictEnum.UNVERIFIED
+            }
+
+            confidence_mapping = {
+                "high": ConfidenceEnum.HIGH,
+                "medium": ConfidenceEnum.MEDIUM,
+                "low": ConfidenceEnum.LOW
+            }
+
+            raw_verdict = parsed_data.get("verdict", "").lower()
+            verdict = verdict_mapping.get(raw_verdict, VerdictEnum.UNVERIFIED)
+
+            raw_confidence = parsed_data.get("confidence", "").lower()
+            confidence = confidence_mapping.get(raw_confidence, ConfidenceEnum.MEDIUM)
+
+            sources = [
+                Source(
+                    url=url,
+                    domain=extract_domain(url),
+                    title=f"Source from {extract_domain(url)}",
+                    publisher=extract_domain(url),
+                    date_published=None,
+                    snippet="Source cited by Perplexity AI"
+                )
+                for url in parsed_data.get("sources", [])
+            ]
+
+            # Convert evidence to string if it's not already
+            evidence = parsed_data.get("evidence", "")
+            if isinstance(evidence, dict):
+                # Convert dictionary evidence to string format
+                evidence_str = ""
+                for key, value in evidence.items():
+                    evidence_str += f"{key}: {value}\n"
+                evidence = evidence_str.strip()
+            
+            # Convert explanation to string if it's not already
+            explanation = parsed_data.get("explanation", "")
+            if isinstance(explanation, dict):
+                explanation_str = ""
+                for key, value in explanation.items():
+                    explanation_str += f"{key}: {value}\n"
+                explanation = explanation_str.strip()
+
+            return FactCheckResponse(
+                claim=query,
+                verdict=verdict,
+                confidence=confidence,
+                sources=sources,
+                evidence=evidence,
+                explanation=explanation,
+                additional_context=f"Fact checked using PlanPost AI on {datetime.now().strftime('%Y-%m-%d')}"
+            )
+
+    except Exception as e:
+        logger.error(f"Fact check error: {str(e)}")
+        return UnverifiedFactCheckResponse(
+            claim=query,
+            verdict=VerdictEnum.UNVERIFIED,
+            confidence=ConfidenceEnum.LOW,
+            sources=[],
+            evidence='No fact check results found.',
+            explanation="Failed to contact Perplexity AI or parse its response.",
+            additional_context="Possible API issue or malformed response."
+        )
+
+
+
+def extract_domain(url: str) -> str:
+    """Extract domain from URL.
+    
+    Args:
+        url: The URL to extract domain from
+        
+    Returns:
+        The domain name or "unknown" if parsing fails
+    """
+    try:
+        from urllib.parse import urlparse
+        parsed_url = urlparse(url)
+        domain = parsed_url.netloc
+        return domain if domain else "unknown"
+    except Exception as e:
+        logger.warning(f"Failed to extract domain from URL {url}: {str(e)}")
+        return "unknown"
+
+
+def extract_fact_check_info(text_response: str) -> Dict[str, Any]:
+    """Extract fact-checking information from a text response when JSON parsing fails.
+    
+    Args:
+        text_response: The text response from Perplexity AI
+        
+    Returns:
+        A dictionary with fact-checking information extracted from the text
+    """
+    import re
+    
+    result = {
+        "verdict": "unverified",
+        "confidence": "medium",
+        "sources": [],
+        "evidence": "",
+        "explanation": ""
+    }
+    
+    # Try to extract verdict with more comprehensive pattern matching
+    verdict_patterns = [
+        r'verdict[:\s]+(true|false|partially true|partially false|inconclusive|unverified)',
+        r'(true|false|partially true|partially false|inconclusive|unverified)[:\s]+verdict',
+        r'claim is (true|false|partially true|partially false|inconclusive|unverified)',
+        r'statement is (true|false|partially true|partially false|inconclusive|unverified)'
+    ]
+    
+    for pattern in verdict_patterns:
+        verdict_match = re.search(pattern, text_response.lower(), re.IGNORECASE)
+        if verdict_match:
+            result["verdict"] = verdict_match.group(1)
+            break
+    
+    # Try to extract confidence with multiple patterns
+    confidence_patterns = [
+        r'confidence[:\s]+(high|medium|low)',
+        r'(high|medium|low)[:\s]+confidence',
+        r'confidence level[:\s]+(high|medium|low)',
+        r'(high|medium|low)[:\s]+confidence level'
+    ]
+    
+    for pattern in confidence_patterns:
+        confidence_match = re.search(pattern, text_response.lower(), re.IGNORECASE)
+        if confidence_match:
+            result["confidence"] = confidence_match.group(1)
+            break
+    
+    # Try to extract URLs as sources - more robust pattern
+    urls = re.findall(r'https?://[^\s"\'\]\)]+', text_response)
+    # Filter out any malformed URLs
+    valid_urls = []
+    for url in urls:
+        if '.' in url and len(url) > 10:  # Basic validation
+            valid_urls.append(url)
+    result["sources"] = valid_urls
+    
+    # Try to extract evidence and explanation with multiple patterns
+    evidence_patterns = [
+        r'evidence[:\s]+(.*?)(?=explanation|\Z)',
+        r'key facts[:\s]+(.*?)(?=explanation|\Z)',
+        r'facts[:\s]+(.*?)(?=explanation|\Z)'
+    ]
+    
+    for pattern in evidence_patterns:
+        evidence_match = re.search(pattern, text_response, re.IGNORECASE | re.DOTALL)
+        if evidence_match:
+            result["evidence"] = evidence_match.group(1).strip()
+            break
+    
+    explanation_patterns = [
+        r'explanation[:\s]+(.*?)(?=\Z)',
+        r'reasoning[:\s]+(.*?)(?=\Z)',
+        r'analysis[:\s]+(.*?)(?=\Z)'
+    ]
+    
+    for pattern in explanation_patterns:
+        explanation_match = re.search(pattern, text_response, re.IGNORECASE | re.DOTALL)
+        if explanation_match:
+            result["explanation"] = explanation_match.group(1).strip()
+            break
+    
+    # If no structured information found, use the whole response as evidence
+    if not result["evidence"] and not result["explanation"]:
+        result["evidence"] = text_response
+        # Generate a minimal explanation if none was found
+        result["explanation"] = "The fact-checking service provided information about this claim but did not structure it in the expected format. The full response has been included as evidence for you to review."
+    
+    return result
+
+
+async def generate_fact_report(query: str, fact_check_data: dict | AIFactCheckResponse) -> Union[FactCheckResponse, UnverifiedFactCheckResponse]:
     """Generate a fact check report using OpenAI based on the fact check results."""
     try:
         base_system_prompt = """You are a professional fact-checking reporter. Your task is to create a detailed fact check report based on the provided data. Focus on accuracy, clarity, and proper citation of sources.
@@ -23,7 +292,35 @@ Rules:
 1. Include all source URLs and names in the sources list
 2. Keep the explanation focused on verifiable facts
 3. Include dates when available
-4. Maintain objectivity in the report"""
+4. Maintain objectivity in the report
+5. If no reliable sources are found, provide a clear explanation why"""
+
+        # Handle both dictionary and AIFactCheckResponse
+        if hasattr(fact_check_data, 'verification_result'):
+            # It's an AIFactCheckResponse
+            has_sources = bool(fact_check_data.sources)
+            verification_result = fact_check_data.verification_result
+            fact_check_data_dict = fact_check_data.dict()
+        else:
+            # It's a dictionary
+            has_sources = bool(fact_check_data.get("claims") or fact_check_data.get("urls_found"))
+            verification_result = fact_check_data.get("verification_result", {})
+            fact_check_data_dict = fact_check_data
+
+        # If no sources were found, return an unverified response
+        if not has_sources or (
+            isinstance(fact_check_data, dict) and 
+            fact_check_data.get("status") == "no_results"
+        ) or (verification_result and verification_result.get("no_sources_found")):
+            return UnverifiedFactCheckResponse(
+                claim=query,
+                verdict=VerdictEnum.UNVERIFIED,
+                confidence=ConfidenceEnum.LOW,
+                sources=[],
+                evidence="No fact-checking sources have verified this claim yet.",
+                explanation="Our search across reputable fact-checking websites did not find any formal verification of this claim. This doesn't mean the claim is false - just that it hasn't been formally fact-checked yet.",
+                additional_context="The claim may be too recent for fact-checkers to have investigated, or it may not have been widely circulated enough to warrant formal fact-checking."
+            )
 
         base_user_prompt = """Generate a comprehensive fact check report in this exact JSON format:
 {
@@ -39,14 +336,12 @@ Rules:
     "evidence": "A concise summary of the key evidence (1-2 sentences)",
     "explanation": "A detailed explanation including who verified it, when it was verified, and the key findings (2-3 sentences)",
     "additional_context": "Important context about the verification process, limitations, or broader implications (1-2 sentences)"
-}
+}"""
 
-Ensure all URLs in sources are complete (including https:// if missing) and each source has both a URL and name."""
+        if isinstance(fact_check_data, dict) and "claims" in fact_check_data:
-
-        if "claims" in fact_check_data:
             system_prompt = base_system_prompt
             user_prompt = f"""Query: {query}
-            Fact Check Results: {fact_check_data}
+            Fact Check Results: {fact_check_data_dict}
             
             {base_user_prompt}
 
@@ -55,11 +350,10 @@ Ensure all URLs in sources are complete (including https:// if missing) and each
             2. Specify verification dates when available 
             3. Name the fact-checking organizations involved
             4. Describe the verification process"""
-            
         else:
             system_prompt = base_system_prompt
             user_prompt = f"""Query: {query}
-            Fact Check Results: {fact_check_data}
+            Fact Check Results: {fact_check_data_dict}
             
             {base_user_prompt}
 
@@ -74,119 +368,238 @@ Ensure all URLs in sources are complete (including https:// if missing) and each
             user_prompt=user_prompt,
             max_tokens=1000
         )
-        
+
         try:
-            # First try to parse the response directly
             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}"
-                        url = source if source.startswith('http') else f"https://{source}"
+                        cleaned_sources.append({"url": url, "name": source})
-                        cleaned_sources.append({
-                            "url": url,
-                            "name": source
-                        })
                     elif isinstance(source, dict):
-                        # Ensure URL has proper scheme
+                        url = source.get("url", "")
-                        url = source.get('url', '')
+                        if url and not url.startswith("http"):
-                        if url and not url.startswith('http'):
+                            source["url"] = f"https://{url}"
-                            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)
+            if response_data["verdict"] == "Unverified" or not response_data.get("sources"):
-            return fact_check_response
+                return UnverifiedFactCheckResponse(**response_data)
-            
+            return FactCheckResponse(**response_data)
+
         except Exception as validation_error:
-            print(f"Response validation error: {str(validation_error)}")
+            logger.error(f"Response validation error: {str(validation_error)}")
-            raise HTTPException(
+            return UnverifiedFactCheckResponse(
-                status_code=422,
+                claim=query,
-                detail=ErrorResponse(
+                verdict=VerdictEnum.UNVERIFIED,
-                    detail=f"Invalid response format: {str(validation_error)}",
+                confidence=ConfidenceEnum.LOW,
-                    error_code="VALIDATION_ERROR",
+                sources=[],
-                    path="/check-facts"
+                evidence="An error occurred while processing the fact check results.",
-                ).dict()
+                explanation="The system encountered an error while validating the fact check results.",
+                additional_context="This is a technical error and does not reflect on the truthfulness of the claim."
             )
-        
+
     except Exception as e:
-        print(f"Error generating fact report: {str(e)}")
+        logger.error(f"Error generating fact report: {str(e)}")
-        raise HTTPException(
+        return UnverifiedFactCheckResponse(
-            status_code=500,
+            claim=query,
-            detail=ErrorResponse(
+            verdict=VerdictEnum.UNVERIFIED,
-                detail="Error generating fact report",
+            confidence=ConfidenceEnum.LOW,
-                error_code="FACT_CHECK_ERROR",
+            sources=[],
-                path="/check-facts"
+            evidence="An error occurred while generating the fact check report.",
-            ).dict()
+            explanation="The system encountered an unexpected error while processing the fact check request.",
+            additional_context="This is a technical error and does not reflect on the truthfulness of the claim."
+        )
+        
+async def combine_fact_reports(query: str, url_text: str, query_result: Dict[str, Any], url_result: Dict[str, Any]) -> Union[FactCheckResponse, UnverifiedFactCheckResponse]:
+    """Combine fact check results from query and URL into a single comprehensive report."""
+    try:
+        system_prompt = """You are a professional fact-checking reporter. Your task is to create a comprehensive fact check report by combining and analyzing multiple fact-checking results. Focus on accuracy, clarity, and proper citation of all sources.
+
+Rules:
+1. Include all source URLs and names from both result sets
+2. Compare and contrast findings from different sources
+3. Include dates when available
+4. Note any discrepancies between sources
+5. Provide a balanced, objective analysis"""
+
+        user_prompt = f"""Original Query: {query}
+Extracted Text from URL: {url_text}
+
+First Fact Check Result: {query_result}
+Second Fact Check Result: {url_result}
+
+Generate a comprehensive fact check report in this exact JSON format:
+{{
+    "claim": "Write the exact claim being verified",
+    "verdict": "One of: True/False/Partially True/Unverified",
+    "confidence": "One of: High/Medium/Low",
+    "sources": [
+        {{
+            "url": "Full URL of the source",
+            "name": "Name of the source organization"
+        }}
+    ],
+    "evidence": "A concise summary of the key evidence from both sources (2-3 sentences)",
+    "explanation": "A detailed explanation combining findings from both fact checks (3-4 sentences)",
+    "additional_context": "Important context about differences or similarities in findings (1-2 sentences)"
+}}
+
+The report should:
+1. Combine sources from both fact checks
+2. Compare findings from both analyses
+3. Note any differences in conclusions
+4. Provide a unified verdict based on all available information"""
+
+        response = await openai_client.generate_text_response(
+            system_prompt=system_prompt,
+            user_prompt=user_prompt,
+            max_tokens=1000
         )
 
-@fact_check_router.post("/check-facts", response_model=FactCheckResponse)
+        response_data = response["response"]
+
+        # Clean up sources from both results
+        if isinstance(response_data.get("sources"), list):
+            cleaned_sources = []
+            for source in response_data["sources"]:
+                if isinstance(source, str):
+                    url = source if source.startswith("http") else f"https://{source}"
+                    cleaned_sources.append({"url": url, "name": source})
+                elif isinstance(source, dict):
+                    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
+
+        if response_data["verdict"] == "Unverified" or not response_data.get("sources"):
+            return UnverifiedFactCheckResponse(**response_data)
+        return FactCheckResponse(**response_data)
+
+    except Exception as e:
+        logger.error(f"Error combining fact reports: {str(e)}")
+        return UnverifiedFactCheckResponse(
+            claim=query,
+            verdict=VerdictEnum.UNVERIFIED,
+            confidence=ConfidenceEnum.LOW,
+            sources=[],
+            evidence="An error occurred while combining fact check reports.",
+            explanation="The system encountered an error while trying to combine results from multiple sources.",
+            additional_context="This is a technical error and does not reflect on the truthfulness of the claim."
+        )
+
+
+@fact_check_router.post("/check-facts", response_model=Union[FactCheckResponse, UnverifiedFactCheckResponse])
 async def check_facts(request: FactCheckRequest):
     """
     Fetch fact check results and generate a comprehensive report.
+    Handles both query-based and URL-based fact checking.
+    Always returns a 200 response with appropriate content, never an error.
     """
-    if not GOOGLE_API_KEY or not GOOGLE_FACT_CHECK_BASE_URL:
+    try:
-        raise HTTPException(
+        url_text = None
-            status_code=500,
+        query_result = None
-            detail=ErrorResponse(
+        url_result = None
-                detail="Google API key or base URL is not configured",
-                error_code="CONFIGURATION_ERROR",
-                path="/check-facts"
-            ).dict()
-        )
-
-    headers = {"Content-Type": "application/json"}
-    async with httpx.AsyncClient() as client:
-        # Get fact checker sources from the centralized configuration
-        fact_checker_sources = get_all_sources()
-        
-        for source in fact_checker_sources:
-            params = {
-                "key": GOOGLE_API_KEY,
-                "query": request.query,
-                "languageCode": "en-US",
-                "reviewPublisherSiteFilter": source.domain,
-                "pageSize": 10
-            }
 
+        # If URL is provided, try to extract text
+        if request.url:
             try:
-                response = await client.get(
+                url_text = await process_url_content(request.url)
-                    GOOGLE_FACT_CHECK_BASE_URL,
-                    params=params,
-                    headers=headers
-                )
-                response.raise_for_status()
-                json_response = response.json()
-
-                if json_response.get("claims"):
-                    return await generate_fact_report(request.query, json_response)
-                
-            except httpx.RequestError as e:
-                print(f"Error fetching results for site {source.domain}: {str(e)}")
-                continue
             except Exception as e:
-                print(f"Unexpected error for site {source.domain}: {str(e)}")
+                logger.error(f"Error extracting text from URL: {str(e)}")
-                continue
+                url_text = None
-        
+                
-        try:
+            if not url_text and not request.query:
-            search_request = SearchRequest(
+                # Only return early if URL text extraction failed and no query provided
-                search_text=request.query,
+                return UnverifiedFactCheckResponse(
-                source_types=["fact_checkers"]
+                    claim=f"URL check requested: {request.url}",
-            )
+                    verdict=VerdictEnum.UNVERIFIED,
+                    confidence=ConfidenceEnum.LOW,
+                    sources=[],
+                    evidence="No fact check results found",
+                    explanation="The system encountered errors while processing the fact checks.",
+                    additional_context="Please try again with different input or contact support if the issue persists."
+                )
             
-            ai_response = await search_websites(search_request)
+            # If URL text was successfully extracted, process it
-            return await generate_fact_report(request.query, ai_response)
+            if url_text:
-            
+                logger.info(f"Processing fact check for extracted text: {url_text}")
-        except Exception as e:
+                try:
-            print(f"Error in AI fact check: {str(e)}")
+                    url_result = await process_fact_check(url_text)
-            raise HTTPException(
+                except Exception as e:
-                status_code=404,
+                    logger.error(f"Error processing fact check for URL text: {str(e)}")
-                detail=ErrorResponse(
+                    url_result = UnverifiedFactCheckResponse(
-                    detail="No fact check results found",
+                        claim=f"URL: {request.url}",
-                    error_code="NOT_FOUND",
+                        verdict=VerdictEnum.UNVERIFIED,
-                    path="/check-facts"
+                        confidence=ConfidenceEnum.LOW,
-                ).dict()
+                        sources=[],
-            )
+                        evidence="No fact check results found",
+                        explanation="The system encountered errors while processing the fact checks.",
+                        additional_context="Please try again with different input or contact support if the issue persists."
+                    )
+
+        # Process query if provided
+        if request.query:
+            try:
+                query_result = await process_fact_check(request.query)
+            except Exception as e:
+                logger.error(f"Error processing fact check for query: {str(e)}")
+                query_result = UnverifiedFactCheckResponse(
+                    claim=request.query,
+                    verdict=VerdictEnum.UNVERIFIED,
+                    confidence=ConfidenceEnum.LOW,
+                    sources=[],
+                    evidence="No fact check results found",
+                    explanation="The system encountered errors while processing the fact checks.",
+                    additional_context="Please try again with different input or contact support if the issue persists."
+                )
+
+        # If both results are available, combine them
+        if query_result and url_result and url_text:
+            try:
+                return await combine_fact_reports(request.query, url_text, 
+                                                query_result.dict(), url_result.dict())
+            except Exception as e:
+                logger.error(f"Error combining fact reports: {str(e)}")
+                return UnverifiedFactCheckResponse(
+                    claim=request.query or f"URL: {request.url}",
+                    verdict=VerdictEnum.UNVERIFIED,
+                    confidence=ConfidenceEnum.LOW,
+                    sources=[],
+                    evidence="No fact check results found",
+                    explanation="The system encountered errors while processing the fact checks.",
+                    additional_context="Please try again with different input or contact support if the issue persists."
+                )
+
+        # If only one result is available
+        if query_result:
+            return query_result
+        if url_result:
+            return url_result
+
+        # If no valid results
+        return UnverifiedFactCheckResponse(
+            claim=request.query or f"URL: {request.url}",
+            verdict=VerdictEnum.UNVERIFIED,
+            confidence=ConfidenceEnum.LOW,
+            sources=[],
+            evidence="No fact check results found",
+            explanation="The system encountered errors while processing the fact checks.",
+            additional_context="Please try again with different input or contact support if the issue persists."
+        )
+    
+    except Exception as e:
+        # Catch-all exception handler to ensure we always return a 200 response
+        logger.error(f"Unexpected error in check_facts: {str(e)}")
+        return UnverifiedFactCheckResponse(
+            claim=request.query or f"URL: {request.url}",
+            verdict=VerdictEnum.UNVERIFIED,
+            confidence=ConfidenceEnum.LOW,
+            sources=[],
+            evidence="No fact check results found",
+            explanation="The system encountered errors while processing the fact checks.",
+            additional_context="Please try again with different input or contact support if the issue persists."
+        )

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,
+    level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s"
-    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
 )
 logger = logging.getLogger(__name__)
 
@@ -38,51 +38,58 @@ 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
-    
+
     params = {
         "key": GOOGLE_API_KEY,
         "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:
         try:
             response = await client.get(GOOGLE_SEARCH_URL, params=params)
@@ -92,69 +99,70 @@ 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
     source_types = request.source_types if request.source_types else ["fact_checkers"]
-    
+
     # Get sources based on requested types
     selected_sources = []
     for source_type in source_types:
         if source_type in SOURCES:
             selected_sources.extend(SOURCES[source_type])
-    
+
     # If no valid sources found, use fact checkers as default
     if not selected_sources:
         selected_sources = SOURCES["fact_checkers"]
-    
+
     all_urls = []
     domain_results = {}
-    
+
     try:
         for page in range(1, MAX_PAGES + 1):
             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
-            
+
             for item in search_response.get("items", []):
                 url = item.get("link")
                 if not url:
                     continue
-                
+
                 domain = get_domain_from_url(url)
-                
+
                 if is_valid_source_domain(domain, selected_sources):
                     if domain not in domain_results:
                         domain_results[domain] = []
-                    
+
                     if len(domain_results[domain]) < MAX_URLS_PER_DOMAIN:
-                        domain_results[domain].append({
+                        domain_results[domain].append(
-                            "url": url,
+                            {
-                            "title": item.get("title", ""),
+                                "url": url,
-                            "snippet": item.get("snippet", "")
+                                "title": item.get("title", ""),
-                        })
+                                "snippet": item.get("snippet", ""),
+                            }
+                        )
                         all_urls.append(url)
-                
+
                 if len(all_urls) >= 50:
                     break
-        
+
         if not all_urls:
-            return {
+            return {"status": "no_results", "urls_found": 0}
-                "status": "no_results",
+
-                "urls_found": 0
-            }
-        
         fact_check_request = AIFactCheckRequest(
-            content=request.search_text,
+            content=request.search_text, urls=all_urls[:5]
-            urls=all_urls[:5]
         )
-        
+
         return await ai_fact_check(fact_check_request)
 
     except Exception as e:
         logger.error(f"Error during search/fact-check process: {str(e)}")
-        raise HTTPException(status_code=500, detail=str(e))
+        raise HTTPException(status_code=500, detail=str(e))

app/config.py

@@ -4,9 +4,10 @@ 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"]
+PERPLEXITY_API_KEY= os.environ["PERPLEXITY_API_KEY"]
 
 OPENAI_API_KEY = os.environ["OPENAI_API_KEY"]
-FRONTEND_URL = os.environ["FRONTEND_URL"]
+FRONTEND_URL = os.environ["FRONTEND_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={
+    model_config = ConfigDict(
-        "example": {
+        json_schema_extra={
-            "detail": "Error description",
+            "example": {
-            "error_code": "ERROR_CODE",
+                "detail": "Error description",
-            "timestamp": "2024-12-09T16:49:30.905765",
+                "error_code": "ERROR_CODE",
-            "path": "/check-facts"
+                "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")
@@ -67,54 +79,56 @@ class VerificationResult(BaseModel):
     reasoning: str
     missing_info: Optional[str] = None
 
-    model_config = ConfigDict(json_schema_extra={
+    model_config = ConfigDict(
-        "example": {
+        json_schema_extra={
-            "verdict": "True",
+            "example": {
-            "confidence": "High",
+                "verdict": "True",
-            "evidence": ["Direct quote from source supporting the claim"],
+                "confidence": "High",
-            "reasoning": "Detailed analysis of why the claim is considered true",
+                "evidence": ["Direct quote from source supporting the claim"],
-            "missing_info": "Any caveats or limitations of the verification"
+                "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:
             if not url.strip():
                 raise ValueError("URL cannot be empty")
-            
+
             # Add https:// if no protocol specified
-            if not url.startswith(('http://', 'https://')):
+            if not url.startswith(("http://", "https://")):
-                url = f'https://{url}'
+                url = f"https://{url}"
-            
+
             try:
                 result = urlparse(url)
                 if not result.netloc:
@@ -122,18 +136,21 @@ class AIFactCheckRequest(BaseFactCheckRequest):
                 validated_urls.append(url)
             except Exception as e:
                 raise ValueError(f"Invalid URL {url}: {str(e)}")
-        
+
         return validated_urls
 
-    model_config = ConfigDict(json_schema_extra={
+    model_config = ConfigDict(
-        "example": {
+        json_schema_extra={
-            "content": "Indian flag was drawn in BUET campus",
+            "example": {
-            "urls": [
+                "content": "Indian flag was drawn in BUET campus",
-                "www.altnews.in/article-about-flag",
+                "urls": [
-                "www.another-source.com/related-news"
+                    "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={
+    model_config = ConfigDict(
-        "example": {
+        json_schema_extra={
-            "query": "Example statement to verify",
+            "example": {
-            "token_usage": {
+                "query": "Example statement to verify",
-                "prompt_tokens": 100,
+                "token_usage": {
-                "completion_tokens": 50,
+                    "prompt_tokens": 100,
-                "total_tokens": 150
+                    "completion_tokens": 50,
-            },
+                    "total_tokens": 150,
-            "sources": ["source1.com", "source2.com"],
+                },
+                "sources": ["source1.com", "source2.com"],
+            }
         }
-    })
+    )
+
 
 class GoogleFactCheckResponse(BaseFactCheckResponse):
     total_claims_found: int
@@ -159,71 +179,80 @@ class GoogleFactCheckResponse(BaseFactCheckResponse):
     verification_result: Dict[str, Any]
     summary: Dict[str, int]
 
-    model_config = ConfigDict(json_schema_extra={
+    model_config = ConfigDict(
-        "example": {
+        json_schema_extra={
-            "query": "Example claim",
+            "example": {
-            "total_claims_found": 1,
+                "query": "Example claim",
-            "results": [{
+                "total_claims_found": 1,
-                "text": "Example claim text",
+                "results": [
-                "claimant": "Source name",
+                    {
-                "claimReview": [{
+                        "text": "Example claim text",
-                    "publisher": {
+                        "claimant": "Source name",
-                        "name": "Fact Checker",
+                        "claimReview": [
-                        "site": "factchecker.com"
+                            {
-                    },
+                                "publisher": {
-                    "textualRating": "True"
+                                    "name": "Fact Checker",
-                }]
+                                    "site": "factchecker.com",
-            }],
+                                },
-            "verification_result": {
+                                "textualRating": "True",
-                "verdict": "True",
+                            }
-                "confidence": "High",
+                        ],
-                "evidence": ["Supporting evidence"],
+                    }
-                "reasoning": "Detailed analysis"
+                ],
-            },
+                "verification_result": {
-            "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"],
+                    "evidence": ["Supporting evidence"],
-                    "reasoning": "Detailed analysis from source 1",
+                    "reasoning": "Detailed analysis",
-                    "missing_info": None
                 },
-                "https://www.source2.com": {
+                "sources": ["factchecker.com"],
-                    "verdict": "True",
+                "token_usage": {
-                    "confidence": "Medium",
+                    "prompt_tokens": 100,
-                    "evidence": ["Supporting evidence from source 2"],
+                    "completion_tokens": 50,
-                    "reasoning": "Analysis from source 2",
+                    "total_tokens": 150,
-                    "missing_info": "Additional context needed"
+                },
-                }
+                "summary": {"total_sources": 1, "fact_checking_sites_queried": 10},
-            },
-            "sources": ["source1.com", "source2.com"],
-            "token_usage": {
-                "prompt_tokens": 200,
-                "completion_tokens": 100,
-                "total_tokens": 300
             }
         }
-    })
+    )
+
+
+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
-FactCheckResponse = GoogleFactCheckResponse
+FactCheckResponse = GoogleFactCheckResponse

app/models/fact_check_models.py

@@ -1,54 +1,106 @@
-from pydantic import BaseModel, Field, HttpUrl, validator
+from pydantic import BaseModel, Field, HttpUrl, validator, root_validator
-from typing import List, Literal, Union
+from typing import List, Literal, Union, Optional
 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(
+    query: Optional[str] = Field(
-        ...,
+        None,
         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?",
     )
+    url: Optional[str] = Field(
+        None,
+        description="URL to be fact-checked",
+        example="https://example.com/article",
+    )
+
+    @root_validator(pre=True)
+    def validate_at_least_one(cls, values):
+        """Validate that at least one of query or url is provided."""
+        query = values.get('query')
+        url = values.get('url')
+        if not query and not url:
+            raise ValueError("At least one of 'query' or 'url' must be provided")
+        return values
+
+    @validator('url')
+    def validate_url(cls, v):
+        """Validate URL format if provided."""
+        if v is not None and len(v) < 3:
+            raise ValueError("URL must be at least 3 characters")
+        return v
+
 
 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 UnverifiedFactCheckResponse(BaseModel):
+    claim: str = Field(
+        ...,
+        min_length=10,
+        max_length=1000,
+        description="The exact claim being verified",
+    )
+    verdict: VerdictEnum = Field(..., description="The verification verdict")
+    confidence: ConfidenceEnum = Field(..., description="Confidence level in the verdict")
+    sources: List[Source] = Field(
+        default=[],
+        description="List of sources used in verification"
+    )
+    evidence: str = Field(
+        ...,
+        min_length=20,
+        max_length=500,
+        description="Concise summary of key evidence",
+    )
+    explanation: str = Field(
+        ...,
+        min_length=50,
+        max_length=1000,
+        description="Detailed explanation of verification findings",
+    )
+    additional_context: str = Field(
+        ...,
+        min_length=20,
+        max_length=500,
+        description="Important context about the verification",
+    )
+
+
 class FactCheckResponse(BaseModel):
     claim: str = Field(
         ...,
         min_length=10,
         max_length=1000,
-        description="The exact claim being verified"
+        description="The exact claim being verified",
-    )
-    verdict: VerdictEnum = Field(
-        ...,
-        description="The verification verdict"
-    )
-    confidence: ConfidenceEnum = Field(
-        ...,
-        description="Confidence level in the verdict"
     )
+    verdict: VerdictEnum = Field(..., description="The verification verdict")
+    confidence: ConfidenceEnum = Field(..., description="Confidence level in the verdict")
     sources: List[Source] = Field(
         ...,
         min_items=1,
@@ -58,19 +110,19 @@ class FactCheckResponse(BaseModel):
         ...,
         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 +134,16 @@ 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"
                     }
                 ],
                 "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.",
+                "explanation": "Multiple fact-checking organizations investigated this claim. NASA's official communications and Mars mission reports from 2024 contain no mention of alien structures.",
-                "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.",
             }
         }
 
+
 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]
@@ -40,4 +48,4 @@ class EnhancedFactCheckResponse(BaseModel):
     summary: Summary
     token_usage: Dict[str, int]
     total_claims_found: int
-    verification_result: VerificationResult
+    verification_result: VerificationResult

app/services/image_text_extractor.py

@@ -0,0 +1,119 @@
+import base64
+import requests
+import os
+from io import BytesIO
+from typing import Tuple, Optional
+import logging
+import aiohttp
+
+logger = logging.getLogger(__name__)
+
+class ImageTextExtractor:
+    def __init__(self, api_key: str):
+        """Initialize ImageTextExtractor with OpenAI API key."""
+        self.api_key = api_key
+        self.api_url = "https://api.openai.com/v1/chat/completions"
+        self.headers = {
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {api_key}"
+        }
+
+    def encode_image(self, image_path: str) -> str:
+        """Encode a local image into base64."""
+        try:
+            with open(image_path, "rb") as image_file:
+                return base64.b64encode(image_file.read()).decode('utf-8')
+        except Exception as e:
+            logger.error(f"Error encoding image: {str(e)}")
+            raise Exception(f"Error encoding image: {e}")
+
+    async def fetch_image_from_url(self, image_url: str) -> Tuple[str, str]:
+        """Fetch an image from a URL and encode it as base64."""
+        try:
+            async with aiohttp.ClientSession() as session:
+                async with session.get(image_url) as response:
+                    if response.status != 200:
+                        raise Exception(f"Failed to fetch image: Status {response.status}")
+
+                    content_type = response.headers.get('Content-Type', '')
+                    if "text/html" in content_type:
+                        raise ValueError("The URL points to a webpage, not an image")
+                    if "image" not in content_type:
+                        raise ValueError("The URL does not point to a valid image")
+
+                    image_data = await response.read()
+                    image_format = "jpeg" if "jpeg" in content_type or "jpg" in content_type else "png"
+                    base64_image = base64.b64encode(image_data).decode('utf-8')
+                    return base64_image, image_format
+
+        except aiohttp.ClientError as e:
+            logger.error(f"Error fetching image from URL: {str(e)}")
+            raise Exception(f"Error fetching image from URL: {e}")
+        except ValueError as e:
+            raise
+        except Exception as e:
+            logger.error(f"Unexpected error processing image URL: {str(e)}")
+            raise Exception(f"Unexpected error processing image: {e}")
+
+    async def extract_text(self, image_input: str, is_url: bool = False) -> Optional[str]:
+        """Extract text from an image, either from a local path or URL."""
+        try:
+            if is_url:
+                try:
+                    base64_image, image_format = await self.fetch_image_from_url(image_input)
+                except ValueError as e:
+                    if "webpage" in str(e):
+                        return None
+                    raise
+            else:
+                if not os.path.exists(image_input):
+                    raise FileNotFoundError(f"Image file not found: {image_input}")
+                base64_image = self.encode_image(image_input)
+                image_format = "jpeg" if image_input.endswith(".jpg") else "png"
+
+            payload = {
+                "model": "gpt-4-turbo-2024-04-09",  # Updated model name
+                "messages": [
+                    {
+                        "role": "user",
+                        "content": [
+                            {
+                                "type": "text", 
+                                "text": "Extract and return only the key text from this image in the original language. Do not provide translations or explanations."
+                            },
+                            {
+                                "type": "image_url",
+                                "image_url": {
+                                    "url": f"data:image/{image_format};base64,{base64_image}"
+                                }
+                            }
+                        ]
+                    }
+                ],
+                "max_tokens": 300
+            }
+
+            async with aiohttp.ClientSession() as session:
+                async with session.post(self.api_url, headers=self.headers, json=payload) as response:
+                    if response.status != 200:
+                        error_content = await response.text()
+                        logger.error(f"API request failed: Status {response.status}, Response: {error_content}")
+                        raise Exception(f"API request failed with status {response.status}")
+                    
+                    result = await response.json()
+                    logger.debug(f"GPT-4 API Response: {result}")
+
+                    if 'choices' in result and len(result['choices']) > 0:
+                        extracted_text = result['choices'][0]['message']['content'].strip()
+                        if extracted_text:
+                            return extracted_text
+                    return None
+
+        except (aiohttp.ClientError, ValueError, FileNotFoundError) as e:
+            logger.error(f"Error in text extraction: {str(e)}")
+            return None
+        except Exception as e:
+            logger.error(f"Unexpected error in text extraction: {str(e)}")
+            return None
+
+        return None

app/services/openai_client.py

@@ -1,4 +1,3 @@
-from langchain_community.document_loaders import AsyncHtmlLoader
 from langchain_community.document_transformers import BeautifulSoupTransformer
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_core.documents import Document
@@ -7,6 +6,9 @@ import numpy as np
 import logging as logger
 import openai
 import json
+import aiohttp
+from bs4 import BeautifulSoup
+
 
 class OpenAIClient:
     def __init__(self, api_key: str):
@@ -15,7 +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.
         """
@@ -24,19 +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'],
+                "prompt_tokens": response["usage"]["prompt_tokens"],
-                "completion_tokens": response['usage']['completion_tokens'],
+                "completion_tokens": response["usage"]["completion_tokens"],
-                "total_tokens": response['usage']['total_tokens']
+                "total_tokens": response["usage"]["total_tokens"],
             }
         except json.JSONDecodeError as e:
             raise Exception(f"Failed to parse OpenAI response as JSON: {str(e)}")
@@ -49,14 +53,14 @@ class OpenAIClient:
         """
         try:
             response = openai.Embedding.create(
-                input=texts,
+                input=texts, model="text-embedding-ada-002"
-                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."""
@@ -65,53 +69,71 @@ 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]:
-        """Scrape webpage content using LangChain's AsyncHtmlLoader."""
+        """Scrape webpage content without saving HTML files."""
         try:
-            loader = AsyncHtmlLoader([url])
+            async with aiohttp.ClientSession() as session:
-            docs = await loader.aload()
+                async with session.get(url) as response:
-            
+                    if response.status != 200:
-            bs_transformer = BeautifulSoupTransformer()
+                        raise Exception(
-            docs_transformed = bs_transformer.transform_documents(docs)
+                            f"Failed to fetch URL: {url}, status: {response.status}"
-            docs_chunks = self.text_splitter.split_documents(docs_transformed)
+                        )
-            
+
-            logger.info(f"Successfully scraped webpage | chunks={len(docs_chunks)}")
+                    html_content = await response.text()
-            return docs_chunks
+
-            
+                    # Parse HTML with BeautifulSoup
+                    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},
+                    )
+
+                    # Split into chunks
+                    docs_chunks = self.text_splitter.split_documents([doc])
+
+                    logger.info(
+                        f"Successfully scraped webpage | chunks={len(docs_chunks)}"
+                    )
+                    return docs_chunks
+
         except Exception as e:
             logger.error(f"Error scraping webpage | url={url} | error={str(e)}")
             raise
 
     def find_relevant_chunks(
-        self, 
+        self,
-        query_embedding: List[float], 
+        query_embedding: List[float],
-        doc_embeddings: List[List[float]], 
+        doc_embeddings: List[List[float]],
-        docs: List[Document]
+        docs: List[Document],
     ) -> List[Document]:
         """Find most relevant document chunks using cosine similarity."""
         try:
             query_array = np.array(query_embedding)
             chunks_array = np.array(doc_embeddings)
-            
+
             similarities = np.dot(chunks_array, query_array) / (
                 np.linalg.norm(chunks_array, axis=1) * np.linalg.norm(query_array)
             )
-            
+
             top_indices = np.argsort(similarities)[-5:][::-1]
             return [docs[i] for i in top_indices]
-            
+
         except Exception as e:
             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])
-            
+
             system_prompt = """You are a professional fact-checking assistant. Analyze the provided context 
             and determine if the given statement is true, false, or if there isn't enough information.
             
@@ -123,32 +145,37 @@ class AIFactChecker:
                 "reasoning": "Your detailed analysis and reasoning",
                 "missing_info": "Any important missing information (if applicable)"
             }"""
-            
+
             user_prompt = f"""Context:
             {context}
             
             Statement to verify: "{query}"
             
             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,
+                system_prompt=system_prompt, user_prompt=user_prompt, max_tokens=800
-                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
                 "sources": sources,
                 "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:
             logger.error(f"Error verifying fact | error={str(e)}")
             raise
@@ -157,16 +184,18 @@ class AIFactChecker:
         """Main method to check a fact against a webpage."""
         try:
             docs = await self.scrape_webpage(url)
-            
+
             doc_texts = [doc.page_content for doc in docs]
             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
-            
+
         except Exception as e:
             logger.error(f"Error checking fact | error={str(e)}")
-            raise
+            raise

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",
+            "snopes.com",
-    "politifact.com",
+            "politifact.com",
-    "factcheck.org",
+            "factcheck.org",
-    "reuters.com/fact-check",
+            "reuters.com/fact-check",
-    "apnews.com/hub/ap-fact-check",
+            "apnews.com/hub/ap-fact-check",
-    "bbc.com/news/reality_check",
+            "bbc.com/news/reality_check",
-    "fullfact.org",
+            "fullfact.org",
-    "afp.com/fact-check",
+            "afp.com/fact-check",
-    "truthorfiction.com",
+            "truthorfiction.com",
-    "leadstories.com",
+            "leadstories.com",
-    "checkyourfact.com",
+            "checkyourfact.com",
-    "washingtonpost.com/news/fact-checker",
+            "washingtonpost.com/news/fact-checker",
-    "factcheck.kz",
+            "factcheck.kz",
-    "poynter.org/ifcn",
+            "poynter.org/ifcn",
-    "factcheckeu.info",
+            "factcheckeu.info",
-    "africacheck.org",
+            "africacheck.org",
-    "thequint.com/webqoof",
+            "thequint.com/webqoof",
-    "altnews.in",
+            "altnews.in",
-    "facta.news",
+            "facta.news",
-    "factcheckni.org",
+            "factcheckni.org",
-    "mythdetector.ge",
+            "mythdetector.ge",
-    "verificado.mx",
+            "verificado.mx",
-    "euvsdisinfo.eu",
+            "euvsdisinfo.eu",
-    "factcheck.afp.com",
+            "factcheck.afp.com",
-    "newtral.es",
+            "newtral.es",
-    "maldita.es",
+            "maldita.es",
-    "faktograf.hr",
+            "faktograf.hr",
-    "demagog.org.pl",
+            "demagog.org.pl",
-    "factnameh.com",
+            "factnameh.com",
-    "faktiskt.se",
+            "faktiskt.se",
-    "teyit.org",
+            "teyit.org",
-    "factly.in",
+            "factly.in",
-    "boom.live",
+            "boom.live",
-    "stopfake.org",
+            "stopfake.org",
-    "factcheck.ge",
+            "factcheck.ge",
-    "factcheck.kg",
+            "factcheck.kg",
-    "factcheck.uz",
+            "factcheck.uz",
-    "factcheck.tj",
+            "factcheck.tj",
-    "factcheck.az",
+            "factcheck.az",
-    "factcheck.am",
+            "factcheck.am",
-    "factcheck.md",
+            "factcheck.md",
-    "verafiles.org",
+            "verafiles.org",
-    "rappler.com/fact-check",
+            "rappler.com/fact-check",
-    "vera.com.gt",
+            "vera.com.gt",
-    "chequeado.com",
+            "chequeado.com",
-    "aosfatos.org",
+            "aosfatos.org",
-    "lasillavacia.com/detector-mentiras",
+            "lasillavacia.com/detector-mentiras",
-    "colombiacheck.com",
+            "colombiacheck.com",
-    "ecuadorchequea.com",
+            "ecuadorchequea.com",
-    "elsurti.com/checado",
+            "elsurti.com/checado",
-    "verificat.cat",
+            "verificat.cat",
-    "mafindo.or.id",
+            "mafindo.or.id",
-    "tempo.co/cek-fakta",
+            "tempo.co/cek-fakta",
-    "factcheck.mk",
+            "factcheck.mk",
-    "raskrinkavanje.ba",
+            "raskrinkavanje.ba",
-    "faktograf.hr",
+            "faktograf.hr",
-    "demagog.cz",
+            "demagog.cz",
-    "faktabaari.fi",
+            "faktabaari.fi",
-    "correctiv.org",
+            "correctiv.org",
-    "mimikama.at",
+            "mimikama.at",
-    "factcheck.vlaanderen",
+            "factcheck.vlaanderen",
-    "factuel.afp.com",
+            "factuel.afp.com",
-    "nieuwscheckers.nl",
+            "nieuwscheckers.nl",
-    "faktisk.no",
+            "faktisk.no",
-    "tjekdet.dk",
+            "tjekdet.dk",
-    "ellinikahoaxes.gr",
+            "ellinikahoaxes.gr",
-    "faktograf.id",
+            "faktograf.id",
-    "stopfake.kz",
+            "stopfake.kz",
-    "pesacheck.org",
+            "pesacheck.org",
-    "dubawa.org",
+            "dubawa.org",
-    "namibiafactcheck.org.na",
+            "namibiafactcheck.org.na",
-    "zimfact.org",
+            "zimfact.org",
-    "ghanafact.com",
+            "ghanafact.com",
-    "factspace.africa",
+            "factspace.africa",
-    "factcrescendo.com",
+            "factcrescendo.com",
-    "vishvasnews.com",
+            "vishvasnews.com",
-    "factcheck.lk",
+            "factcheck.lk",
-    "newschecker.in",
+            "newschecker.in",
-    "boomlive.in",
+            "boomlive.in",
-    "digiteye.in",
+            "digiteye.in",
-    "indiatoday.in/fact-check",
+            "indiatoday.in/fact-check",
-    "factcrescendo.com",
+            "factcrescendo.com",
-    "piyasa.com/fact-check",
+            "piyasa.com/fact-check",
-    "taiwanese.facts.news",
+            "taiwanese.facts.news",
-    "taiwanfactcheck.com",
+            "taiwanfactcheck.com",
-    "mygopen.com",
+            "mygopen.com",
-    "tfc-taiwan.org.tw",
+            "tfc-taiwan.org.tw",
-    "cofacts.tw",
+            "cofacts.tw",
-    "rumor.taipei",
+            "rumor.taipei",
-    "fact.qq.com",
+            "fact.qq.com",
-    "factcheck.afp.com/list",
+            "factcheck.afp.com/list",
-    "acfta.org",
+            "acfta.org",
-    "crosscheck.firstdraftnews.org",
+            "crosscheck.firstdraftnews.org",
-    "healthfeedback.org",
+            "healthfeedback.org",
-    "climatefeedback.org",
+            "climatefeedback.org",
-    "sciencefeedback.co",
+            "sciencefeedback.co",
-    "factcheck.aap.com.au",
+            "factcheck.aap.com.au",
-    "emergent.info",
+            "emergent.info",
-    "hoax-slayer.net",
+            "hoax-slayer.net",
-    "truthorfiction.com",
+            "truthorfiction.com",
-    "factcheck.media",
+            "factcheck.media",
-    "mediawise.org",
+            "mediawise.org",
-    "thejournal.ie/factcheck",
+            "thejournal.ie/factcheck",
-    "journalistsresource.org",
+            "journalistsresource.org",
-    "metafact.io",
+            "metafact.io",
-    "reporterslab.org/fact-checking"
+            "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,
+    api_key: str, base_url: str, query: str, site: FactCheckSource
-    base_url: str,
-    query: str,
-    site: FactCheckSource
 ) -> Dict:
     """
     Fetch fact checks from a specific site using the Google Fact Check API
@@ -156,9 +159,9 @@ async def fetch_fact_checks(
             "query": query,
             "languageCode": "en-US",
             "reviewPublisherSiteFilter": site.domain,
-            "pageSize": 10
+            "pageSize": 10,
         }
-        
+
         response = requests.get(base_url, params=params)
         response.raise_for_status()
         return response.json()
@@ -168,23 +171,22 @@ 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"
+                path="/check-facts",
-            ).dict()
+            ).dict(),
         )
     except ValueError as e:
         raise HTTPException(
             status_code=500,
             detail=ErrorResponse(
-                detail=str(e),
+                detail=str(e), error_code="CONFIGURATION_ERROR", path="/check-facts"
-                error_code="CONFIGURATION_ERROR",
+            ).dict(),
-                path="/check-facts"
-            ).dict()
         )
 
+
 def get_all_sources() -> List[FactCheckSource]:
     """
     Get all sources sorted by priority
     """
     # all_sources = SOURCES["fact_checkers"] + SOURCES["news_sites"]
-    all_sources = SOURCES["fact_checkers"] 
+    all_sources = SOURCES["fact_checkers"]
-    return sorted(all_sources, key=lambda x: x.priority)
+    return sorted(all_sources, key=lambda x: x.priority)

docker-compose.yaml

@@ -0,0 +1,5 @@
+services:
+  backend:
+    build: .
+    container_name: backend-service
+    restart: always

main.py

@@ -7,25 +7,14 @@ from app.config import FRONTEND_URL
 
 # Initialize FastAPI app
 app = FastAPI(
-    title="Your API Title",
+    title="Your API Title", description="Your API Description", version="1.0.0"
-    description="Your API Description",
-    version="1.0.0"
 )
 
 # CORS configuration
-origins = [
-    FRONTEND_URL,
-    "http://localhost",
-    "http://localhost:5173",
-    "http://0.0.0.0",
-    "http://0.0.0.0:5173",
-]
-
-
 app.add_middleware(
     CORSMiddleware,
-    allow_origins=origins,
+    allow_origins=["*"],  # Only wildcard
-    allow_credentials=True,
+    allow_credentials=False,  # Changed to False to work with wildcard
     allow_methods=["*"],
     allow_headers=["*"],
 )
@@ -44,10 +33,6 @@ app.include_router(fact_check_router, prefix="")
 app.include_router(aifact_check_router, prefix="")
 app.include_router(scrap_websites_router, prefix="")
 
-# Include routers (uncomment and modify as needed)
-# from routes import some_router
-# app.include_router(some_router, prefix="/your-prefix", tags=["your-tag"])
-
 if __name__ == "__main__":
     import uvicorn
     uvicorn.run("main:app", host="0.0.0.0", port=8000, reload=True)

requirements.txt

@@ -1,6 +1,88 @@
-certifi==2024.8.30
+aiofiles==24.1.0
+aiohappyeyeballs==2.4.4
+aiohttp==3.11.10
+aiosignal==1.3.2
+annotated-types==0.7.0
+anyio==4.7.0
+attrs==24.3.0
+beautifulsoup4==4.12.3
+black==24.10.0
+certifi==2024.12.14
 charset-normalizer==3.4.0
+click==8.1.7
+dataclasses-json==0.6.7
+dnspython==2.7.0
+email_validator==2.2.0
+fastapi==0.115.6
+fastapi-cli==0.0.7
+flake8==7.1.1
+frozenlist==1.5.0
+greenlet==3.1.1
+gunicorn==23.0.0
+h11==0.14.0
+httpcore==1.0.7
+httptools==0.6.4
+httpx==0.28.1
+httpx-sse==0.4.0
 idna==3.10
+iniconfig==2.0.0
+itsdangerous==2.2.0
+Jinja2==3.1.4
+jsonpatch==1.33
+jsonpointer==3.0.0
+langchain==0.3.12
+langchain-community==0.3.12
+langchain-core==0.3.25
+langchain-text-splitters==0.3.3
+langsmith==0.2.3
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.23.1
+mccabe==0.7.0
+mdurl==0.1.2
+multidict==6.1.0
+mypy-extensions==1.0.0
+numpy==1.26.4
+openai==1.23.6
+orjson==3.10.12
+packaging==24.2
+pathspec==0.12.1
+pillow==11.0.0
+platformdirs==4.3.6
+pluggy==1.5.0
+propcache==0.2.1
+pycodestyle==2.12.1
+pydantic==2.10.3
+pydantic-extra-types==2.10.1
+pydantic-settings==2.7.0
+pydantic_core==2.27.1
+pyflakes==3.2.0
+Pygments==2.18.0
+pytest==8.3.4
+python-dateutil==2.9.0.post0
 python-dotenv==1.0.1
+python-json-logger==3.2.1
+python-multipart==0.0.20
+PyYAML==6.0.2
 requests==2.32.3
+requests-toolbelt==1.0.0
+rich==13.9.4
+rich-toolkit==0.12.0
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+soupsieve==2.6
+SQLAlchemy==2.0.36
+starlette==0.41.3
+tenacity==9.0.0
+tqdm==4.67.1
+typer==0.15.1
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+ujson==5.10.0
 urllib3==2.2.3
+uvicorn==0.34.0
+uvloop==0.21.0
+watchfiles==1.0.3
+websockets==14.1
+yarl==1.18.3

tests/test_main.py

@@ -0,0 +1,18 @@
+from fastapi.testclient import TestClient
+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"] == "*"