Initial commit

app/core/__init__.py

@@ -0,0 +1 @@
+"""Core functionality for the Mini SpecsComply Pro application."""

app/core/config.py

@@ -0,0 +1,44 @@
+import os
+from typing import Optional
+from pydantic import BaseModel
+from dotenv import load_dotenv
+
+# Load environment variables from .env file
+load_dotenv()
+
+class Settings(BaseModel):
+    """Application settings loaded from environment variables."""
+    
+    # Application information
+    APP_NAME: str = os.getenv("APP_NAME", "Mini SpecsComply Pro")
+    APP_VERSION: str = os.getenv("APP_VERSION", "0.1.0")
+    DEBUG: bool = os.getenv("DEBUG", "False").lower() in ("true", "1", "t")
+    
+    # API keys
+    GROQ_API_KEY: Optional[str] = os.getenv("GROQ_API_KEY")
+    COHERE_API_KEY: Optional[str] = os.getenv("COHERE_API_KEY")
+    
+    # Vector database settings
+    # Pinecone
+    PINECONE_API_KEY: Optional[str] = os.getenv("PINECONE_API_KEY")
+    PINECONE_INDEX_NAME: str = os.getenv("PINECONE_INDEX_NAME", "specscomply_documents")
+    
+    # Weaviate
+    WEAVIATE_URL: Optional[str] = os.getenv("WEAVIATE_URL")
+    WEAVIATE_API_KEY: Optional[str] = os.getenv("WEAVIATE_API_KEY")
+    
+    # Models
+    EMBEDDING_MODEL: str = "embed-english-v3.0"  # Default embedding model
+    RERANKER_MODEL: str = "rerank-english-v2.0"  # Default reranker model
+    REASONING_MODEL: str = "llama-3.3-70b-versatile"  # Default reasoning model
+    PROCESSING_MODEL: str = "llama-3.3-70b-versatile"  # Default quick processing model
+    
+    # Vector database selector (pinecone or weaviate)
+    VECTOR_DB: str = os.getenv("VECTOR_DB", "pinecone").lower()
+    
+    class Config:
+        env_file = ".env"
+        case_sensitive = True
+
+# Create global settings instance
+settings = Settings()

app/core/models.py

@@ -0,0 +1,127 @@
+# Data models
+from pydantic import BaseModel, Field
+from typing import List, Dict, Optional, Any, Union
+from datetime import datetime
+from enum import Enum
+import uuid
+
+class DocumentStatus(str, Enum):
+    """Enum for document processing status."""
+    PENDING = "pending"
+    PROCESSING = "processing"
+    COMPLETED = "completed"
+    FAILED = "failed"
+
+class ComplianceLevel(str, Enum):
+    """Enum for compliance severity levels."""
+    CRITICAL = "critical"
+    MAJOR = "major"
+    MINOR = "minor"
+    INFO = "info"
+
+class ComplianceIssue(BaseModel):
+    """Model for compliance issues found in the document."""
+    id: str = Field(default_factory=lambda: str(uuid.uuid4()))
+    section: str
+    description: str
+    level: ComplianceLevel
+    line_number: Optional[int] = None
+    reasoning: str = ""  # Detailed explanation of why this is an issue
+    standard_references: List[str] = []  # References to specific standards or requirements
+    recommendation: str
+
+class DocumentMetadata(BaseModel):
+    """Model for document metadata."""
+    filename: str
+    file_type: str
+    file_size: int  # In bytes
+    upload_timestamp: datetime = Field(default_factory=datetime.now)
+    last_modified: Optional[datetime] = None
+
+class DocumentEmbedding(BaseModel):
+    """Model for document embeddings."""
+    embedding_id: str
+    embedding_model: str
+    vector_db: str
+    sections: Dict[str, str]  # Section name to section ID in vector DB
+
+class ComplianceReport(BaseModel):
+    """Model for the generated compliance report."""
+    report_id: str = Field(default_factory=lambda: str(uuid.uuid4()))
+    document_id: str
+    timestamp: datetime = Field(default_factory=datetime.now)
+    compliance_score: float  # 0.0 to 1.0
+    summary: str
+    issues: List[ComplianceIssue] = []
+    applied_standards: List[str] = []  # Standards used for analysis
+
+    @property
+    def critical_issues_count(self) -> int:
+        return sum(1 for issue in self.issues if issue.level == ComplianceLevel.CRITICAL)
+
+    @property
+    def major_issues_count(self) -> int:
+        return sum(1 for issue in self.issues if issue.level == ComplianceLevel.MAJOR)
+
+    @property
+    def minor_issues_count(self) -> int:
+        return sum(1 for issue in self.issues if issue.level == ComplianceLevel.MINOR)
+
+    @property
+    def info_issues_count(self) -> int:
+        return sum(1 for issue in self.issues if issue.level == ComplianceLevel.INFO)
+
+class Document(BaseModel):
+    """Model for document tracking."""
+    id: str = Field(default_factory=lambda: str(uuid.uuid4()))
+    metadata: DocumentMetadata
+    embedding: Optional[DocumentEmbedding] = None
+    status: DocumentStatus = DocumentStatus.PENDING
+    version: int = 1  # Incremented on resubmissions
+    reports: List[str] = []  # List of report IDs
+
+class DocumentUploadResponse(BaseModel):
+    """Response model for document uploads."""
+    document_id: str
+    filename: str
+    status: DocumentStatus
+    message: str
+
+class DocumentAnalysisResponse(BaseModel):
+    """Response model for document analysis retrieval."""
+    document_id: str
+    status: DocumentStatus
+    report: Optional[ComplianceReport] = None
+    message: str
+
+
+class RequirementSeverity(str, Enum):
+    """Enum for requirement severity levels."""
+    CRITICAL = "critical"
+    MAJOR = "major"
+    MINOR = "minor"
+    INFO = "info"
+
+
+class Requirement(BaseModel):
+    """Model for a compliance requirement."""
+    id: str = Field(default_factory=lambda: str(uuid.uuid4()))
+    description: str
+    severity: RequirementSeverity
+    details: Optional[str] = None
+
+
+class Standard(BaseModel):
+    """Model for a compliance standard."""
+    id: str = Field(default_factory=lambda: str(uuid.uuid4()))
+    name: str
+    description: str
+    requirements: List[Requirement] = []
+
+
+class StandardUploadResponse(BaseModel):
+    """Response model for standard uploads."""
+    standard_id: str
+    name: str
+    requirement_count: int
+    message: str