django-cfg 1.4.21__py3-none-any.whl → 1.4.24__py3-none-any.whl

django_cfg/apps/knowbase/config/constance_fields.py

@@ -9,7 +9,9 @@ to ensure consistency across the application.
 """
 
 from typing import List
+
 from django_cfg.models.django.constance import ConstanceField
+
 from .settings import KnowledgeBaseConfig, get_openai_api_key, get_openrouter_api_key
 
 
@@ -25,7 +27,7 @@ def get_django_cfg_knowbase_constance_fields() -> List[ConstanceField]:
     """
     # Get default values from Pydantic config
     default_config = KnowledgeBaseConfig()
-    
+
     return [
         # === Core Processing Settings ===
         ConstanceField(
@@ -42,7 +44,7 @@ def get_django_cfg_knowbase_constance_fields() -> List[ConstanceField]:
             field_type="int",
             group="Knowledge Base",
         ),
-        
+
         # === Embedding Settings ===
         ConstanceField(
             name="EMBEDDING_MODEL",
@@ -58,7 +60,7 @@ def get_django_cfg_knowbase_constance_fields() -> List[ConstanceField]:
             field_type="int",
             group="Knowledge Base",
         ),
-        
+
         # === Search Threshold Settings ===
         ConstanceField(
             name="DOCUMENT_THRESHOLD",
@@ -68,14 +70,14 @@ def get_django_cfg_knowbase_constance_fields() -> List[ConstanceField]:
             group="Knowledge Base",
         ),
         ConstanceField(
-            name="ARCHIVE_THRESHOLD", 
+            name="ARCHIVE_THRESHOLD",
             default=default_config.search.archive_threshold,
             help_text=f"Similarity threshold for archive/code chunks (0.0-1.0). Default: {default_config.search.archive_threshold}. Medium precision for code similarity.",
             field_type="float",
             group="Knowledge Base",
         ),
         # Note: EXTERNAL_DATA_THRESHOLD removed - now configured per-object in ExternalData.similarity_threshold
-        
+
         # === AI Assistant Settings ===
         ConstanceField(
             name="BOT_IDENTITY",
@@ -105,7 +107,7 @@ def get_django_cfg_knowbase_field_validation_rules() -> dict:
     """
     # Get constraints from Pydantic config
     default_config = KnowledgeBaseConfig()
-    
+
     def validate_chunk_size(value):
         """Validate chunk size values using Pydantic constraints."""
         if not isinstance(value, int):
@@ -115,7 +117,7 @@ def get_django_cfg_knowbase_field_validation_rules() -> dict:
         if value > 8000:
             return False, "Chunk size should not exceed 8000 characters"
         return True, ""
-    
+
     def validate_batch_size(value):
         """Validate embedding batch size using Pydantic constraints."""
         if not isinstance(value, int):
@@ -125,7 +127,7 @@ def get_django_cfg_knowbase_field_validation_rules() -> dict:
         if value > 100:
             return False, "Batch size should not exceed 100 for stability"
         return True, ""
-    
+
     def validate_embedding_model(value):
         """Validate embedding model name."""
         if not isinstance(value, str):
@@ -134,13 +136,13 @@ def get_django_cfg_knowbase_field_validation_rules() -> dict:
             return False, "Embedding model cannot be empty"
         valid_models = [
             "text-embedding-ada-002",
-            "text-embedding-3-small", 
+            "text-embedding-3-small",
             "text-embedding-3-large"
         ]
         if value not in valid_models:
             return True, f"Warning: '{value}' is not a standard OpenAI model. Valid options: {', '.join(valid_models)}"
         return True, ""
-    
+
     def validate_bot_identity(value):
         """Validate bot identity text."""
         if not isinstance(value, str):
@@ -152,7 +154,7 @@ def get_django_cfg_knowbase_field_validation_rules() -> dict:
         if len(value) > 1000:
             return False, "Bot identity should not exceed 1000 characters"
         return True, ""
-    
+
     def validate_bot_message(value):
         """Validate bot message text."""
         if not isinstance(value, str):
@@ -164,7 +166,7 @@ def get_django_cfg_knowbase_field_validation_rules() -> dict:
         if len(value) > 500:
             return False, "Bot message should not exceed 500 characters"
         return True, ""
-    
+
     return {
         "DOCUMENT_CHUNK_SIZE": validate_chunk_size,
         "ARCHIVE_CHUNK_SIZE": validate_chunk_size,

django_cfg/apps/knowbase/config/constance_settings.py

@@ -5,14 +5,15 @@ This module provides a centralized way to access all Constance settings
 with proper fallbacks and type safety using Pydantic 2.
 """
 
-from typing import Optional, Dict, Any
-from pydantic import BaseModel, Field, validator
+from typing import Any, Dict
+
 from constance import config
+from pydantic import BaseModel, Field, validator
 
 
 class KnowledgeBaseConstanceSettings(BaseModel):
     """Pydantic model for Knowledge Base Constance settings with validation."""
-    
+
     # === AI Assistant Settings ===
     bot_identity: str = Field(
         default="I am Reforms.ai, an AI assistant specialized in helping with knowledge base queries and technical documentation. I was developed by the Reforms.ai team to provide accurate information based on your uploaded documents and code archives.",
@@ -20,14 +21,14 @@ class KnowledgeBaseConstanceSettings(BaseModel):
         max_length=1000,
         description="AI assistant identity and description"
     )
-    
+
     bot_no_context_message: str = Field(
         default="I can help you with questions about your knowledge base, technical documentation, and uploaded content. However, I don't currently have any specific context loaded for this conversation.",
         min_length=10,
         max_length=500,
         description="Message shown when AI has no specific context"
     )
-    
+
     # === Processing Settings ===
     document_chunk_size: int = Field(
         default=1000,
@@ -35,28 +36,28 @@ class KnowledgeBaseConstanceSettings(BaseModel):
         le=8000,
         description="Chunk size for document processing (characters)"
     )
-    
+
     archive_chunk_size: int = Field(
         default=800,
         ge=100,
         le=8000,
         description="Chunk size for archive processing (characters)"
     )
-    
+
     # === Embedding Settings ===
     embedding_model: str = Field(
         default="text-embedding-ada-002",
         min_length=1,
         description="OpenAI embedding model name"
     )
-    
+
     embedding_batch_size: int = Field(
         default=50,
         ge=1,
         le=100,
         description="Chunks per embedding batch"
     )
-    
+
     # === Search Threshold Settings ===
     document_threshold: float = Field(
         default=0.7,
@@ -64,29 +65,29 @@ class KnowledgeBaseConstanceSettings(BaseModel):
         le=1.0,
         description="Similarity threshold for document chunks"
     )
-    
+
     archive_threshold: float = Field(
         default=0.6,
         ge=0.0,
         le=1.0,
         description="Similarity threshold for archive chunks"
     )
-    
+
     # Note: external_data_threshold removed - now configured per-object in ExternalData.similarity_threshold
-    
+
     @validator('embedding_model')
     def validate_embedding_model(cls, v):
         """Validate embedding model name."""
         valid_models = [
             "text-embedding-ada-002",
-            "text-embedding-3-small", 
+            "text-embedding-3-small",
             "text-embedding-3-large"
         ]
         if v not in valid_models:
             # Warning, not error - allow custom models
             pass
         return v
-    
+
     class Config:
         """Pydantic configuration."""
         validate_assignment = True
@@ -94,7 +95,7 @@ class KnowledgeBaseConstanceSettings(BaseModel):
         json_encoders = {
             # Add custom encoders if needed
         }
-    
+
     @classmethod
     def from_constance(cls) -> 'KnowledgeBaseConstanceSettings':
         """Create instance from Constance settings with fallbacks."""
@@ -109,67 +110,67 @@ class KnowledgeBaseConstanceSettings(BaseModel):
                 document_threshold=getattr(config, 'DOCUMENT_THRESHOLD', cls.model_fields['document_threshold'].default),
                 archive_threshold=getattr(config, 'ARCHIVE_THRESHOLD', cls.model_fields['archive_threshold'].default),
             )
-        except Exception as e:
+        except Exception:
             # If any validation fails, return defaults
             return cls()
-    
+
     @classmethod
     def get_current(cls) -> 'KnowledgeBaseConstanceSettings':
         """Get current settings instance (cached for performance)."""
         # Always refresh cache to avoid stale data issues
         # TODO: Implement smarter cache invalidation based on Constance changes
         return cls.from_constance()
-    
+
     @classmethod
     def refresh_cache(cls):
         """Refresh cached settings instance."""
         if hasattr(cls, '_cached_instance'):
             delattr(cls, '_cached_instance')
-    
+
     # === Convenience Methods for Backward Compatibility ===
-    
+
     @classmethod
     def get_bot_identity(cls) -> str:
         """Get bot identity from current settings."""
         return cls.get_current().bot_identity
-    
+
     @classmethod
     def get_bot_no_context_message(cls) -> str:
         """Get bot no-context message from current settings."""
         return cls.get_current().bot_no_context_message
-    
+
     @classmethod
     def get_document_chunk_size(cls) -> int:
         """Get document chunk size from current settings."""
         return cls.get_current().document_chunk_size
-    
+
     @classmethod
     def get_archive_chunk_size(cls) -> int:
         """Get archive chunk size from current settings."""
         return cls.get_current().archive_chunk_size
-    
+
     @classmethod
     def get_embedding_model(cls) -> str:
         """Get embedding model from current settings."""
         return cls.get_current().embedding_model
-    
+
     @classmethod
     def get_embedding_batch_size(cls) -> int:
         """Get embedding batch size from current settings."""
         return cls.get_current().embedding_batch_size
-    
+
     @classmethod
     def get_document_threshold(cls) -> float:
         """Get document similarity threshold from current settings."""
         return cls.get_current().document_threshold
-    
+
     @classmethod
     def get_archive_threshold(cls) -> float:
         """Get archive similarity threshold from current settings."""
         return cls.get_current().archive_threshold
-    
+
     # Note: get_external_data_threshold removed - now configured per-object in ExternalData.similarity_threshold
-    
+
     @classmethod
     def get_threshold_for_type(cls, content_type: str) -> float:
         """Get appropriate threshold for content type."""
@@ -180,12 +181,12 @@ class KnowledgeBaseConstanceSettings(BaseModel):
             # Note: external_data now uses per-object thresholds from ExternalData.similarity_threshold
         }
         return thresholds.get(content_type, 0.7)  # fallback
-    
+
     @classmethod
     def get_all_settings(cls) -> Dict[str, Any]:
         """Get all settings as a dictionary."""
         return cls.get_current().model_dump()
-    
+
     @classmethod
     def validate_settings(cls) -> Dict[str, str]:
         """Validate current settings and return results."""

django_cfg/apps/knowbase/config/settings.py

@@ -5,10 +5,10 @@ This module provides a clean, type-safe configuration system that replaces
 the removed Constance settings with sensible defaults and validation.
 """
 
-from typing import Dict, Any, Optional
-from pydantic import BaseModel, Field, field_validator
 from pathlib import Path
-import os
+from typing import Any, Dict, Optional
+
+from pydantic import BaseModel, Field, field_validator
 
 # Import environment configuration for API keys
 try:
@@ -20,18 +20,18 @@ except ImportError:
 
 class CacheSettings(BaseModel):
     """Cache settings for LLMClient."""
-    
+
     cache_dir: Path = Field(..., description="Cache directory path")
     cache_ttl: int = Field(..., description="Cache TTL in seconds")
     max_cache_size: int = Field(..., description="Maximum cache size")
-    
+
     class Config:
         arbitrary_types_allowed = True  # Allow Path type
 
 
 class EmbeddingConfig(BaseModel):
     """Configuration for embedding processing."""
-    
+
     model: str = Field(
         default="text-embedding-ada-002",
         description="OpenAI embedding model to use"
@@ -70,7 +70,7 @@ class EmbeddingConfig(BaseModel):
         le=10000,
         description="Maximum number of items in memory cache"
     )
-    
+
     # >> Old variant, should be imported from CfgConfig
     # # API Keys from environment
     # @property
@@ -80,7 +80,7 @@ class EmbeddingConfig(BaseModel):
     #         return settings.api_keys.openai
     #     except AttributeError:
     #         return os.getenv("OPENAI_API_KEY")
-    
+
     # @property
     # def openrouter_api_key(self) -> Optional[str]:
     #     """Get OpenRouter API key from environment configuration."""
@@ -92,7 +92,7 @@ class EmbeddingConfig(BaseModel):
 
 class ChunkingConfig(BaseModel):
     """Configuration for text chunking."""
-    
+
     document_chunk_size: int = Field(
         default=1000,
         ge=100,
@@ -117,14 +117,14 @@ class ChunkingConfig(BaseModel):
         le=1000,
         description="Overlap between archive chunks (characters)"
     )
-    
+
     @field_validator('document_chunk_overlap')
     @classmethod
     def validate_document_overlap(cls, v, info):
         if info.data and 'document_chunk_size' in info.data and v >= info.data['document_chunk_size']:
             raise ValueError('Document chunk overlap must be less than chunk size')
         return v
-    
+
     @field_validator('archive_chunk_overlap')
     @classmethod
     def validate_archive_overlap(cls, v, info):
@@ -135,14 +135,14 @@ class ChunkingConfig(BaseModel):
 
 class SearchConfig(BaseModel):
     """Configuration for search functionality."""
-    
+
     results_limit: int = Field(
         default=10,
         ge=1,
         le=100,
         description="Maximum number of search results to return"
     )
-    
+
     # Type-specific similarity thresholds for better multilingual and content-type support
     document_threshold: float = Field(
         default=0.7,
@@ -157,7 +157,7 @@ class SearchConfig(BaseModel):
         description="Similarity threshold for archive chunks (medium precision for code)"
     )
     # Note: external_data_threshold removed - now configured per-object in ExternalData.similarity_threshold
-    
+
     # Legacy field for backward compatibility
     similarity_threshold: float = Field(
         default=0.7,
@@ -169,7 +169,7 @@ class SearchConfig(BaseModel):
 
 class ChatConfig(BaseModel):
     """Configuration for chat functionality."""
-    
+
     context_chunks: int = Field(
         default=5,
         ge=1,
@@ -192,7 +192,7 @@ class ChatConfig(BaseModel):
 
 class ProcessingConfig(BaseModel):
     """Configuration for processing limits and timeouts."""
-    
+
     max_document_size_mb: int = Field(
         default=10,
         ge=1,
@@ -215,17 +215,17 @@ class ProcessingConfig(BaseModel):
 
 class KnowledgeBaseConfig(BaseModel):
     """Main configuration for the Knowledge Base app."""
-    
+
     embedding: EmbeddingConfig = Field(default_factory=EmbeddingConfig)
     chunking: ChunkingConfig = Field(default_factory=ChunkingConfig)
     search: SearchConfig = Field(default_factory=SearchConfig)
     chat: ChatConfig = Field(default_factory=ChatConfig)
     processing: ProcessingConfig = Field(default_factory=ProcessingConfig)
-    
+
     class Config:
         env_prefix = "KNOWBASE_"
         case_sensitive = False
-        
+
     def get_chunking_params_for_type(self, content_type: str) -> Dict[str, Any]:
         """
         Get chunking parameters for SemanticChunker.
@@ -246,15 +246,15 @@ class KnowledgeBaseConfig(BaseModel):
                 'chunk_size': self.chunking.document_chunk_size,
                 'overlap': self.chunking.document_chunk_overlap
             }
-    
+
     def get_embedding_model(self) -> str:
         """Get the configured embedding model."""
         return self.embedding.model
-    
+
     def get_embedding_batch_size(self) -> int:
         """Get the configured embedding batch size."""
         return self.embedding.batch_size
-    
+
     def get_openai_api_key(self) -> Optional[str]:
         """Get OpenAI API key from django-cfg configuration."""
         try:
@@ -267,7 +267,7 @@ class KnowledgeBaseConfig(BaseModel):
 
         return None
 
-    
+
     def get_openrouter_api_key(self) -> Optional[str]:
         """Get OpenRouter API key from django-cfg configuration."""
         try:
@@ -277,20 +277,20 @@ class KnowledgeBaseConfig(BaseModel):
                 return config.api_keys.get_openrouter_key()
         except (ImportError, AttributeError):
             pass
-        
+
         return None
-    
+
     def get_cache_dir(self) -> Path:
         """Get cache directory path and ensure it exists."""
         from pathlib import Path
         cache_path = Path(self.embedding.cache_dir)
         if not cache_path.is_absolute():
             cache_path = Path.cwd() / cache_path
-        
+
         # Ensure cache directory exists
         cache_path.mkdir(parents=True, exist_ok=True)
         return cache_path
-    
+
     def get_cache_settings(self) -> CacheSettings:
         """Get cache settings for LLMClient."""
         return CacheSettings(
@@ -298,7 +298,7 @@ class KnowledgeBaseConfig(BaseModel):
             cache_ttl=self.embedding.cache_ttl,
             max_cache_size=self.embedding.cache_max_size
         )
-    
+
     def to_dict(self) -> Dict[str, Any]:
         """Convert config to dictionary for easy access."""
         return self.dict()