Spaces:
Sleeping
Sleeping
File size: 8,881 Bytes
e0aa230 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 |
"""
Configuration Manager Module
This module handles loading and managing configuration settings
for the RAG AI system.
"""
import os
import yaml
import logging
from typing import Dict, Any, Optional
from pathlib import Path
class ConfigManager:
"""
Manages configuration settings for the RAG AI system.
Features:
- YAML configuration file loading
- Environment variable override
- Default configuration values
- Configuration validation
"""
def __init__(self, config_path: Optional[str] = None):
"""
Initialize the ConfigManager.
Args:
config_path: Path to the configuration file (defaults to config/config.yaml)
"""
self.logger = logging.getLogger(__name__)
# Set default config path
if config_path is None:
config_path = os.path.join(
os.path.dirname(__file__), "..", "..", "config", "config.yaml"
)
self.config_path = Path(config_path)
self.config = self._load_config()
def _load_config(self) -> Dict[str, Any]:
"""
Load configuration from file and environment variables.
Returns:
Configuration dictionary
"""
# Start with default configuration
config = self._get_default_config()
# Load from YAML file if it exists
if self.config_path.exists():
try:
with open(self.config_path, "r", encoding="utf-8") as f:
file_config = yaml.safe_load(f) or {}
config = self._merge_configs(config, file_config)
self.logger.info(f"Loaded configuration from {self.config_path}")
except Exception as e:
self.logger.warning(
f"Failed to load config file {self.config_path}: {str(e)}"
)
else:
self.logger.warning(f"Config file not found: {self.config_path}")
# Override with environment variables
config = self._apply_env_overrides(config)
# Validate configuration
self._validate_config(config)
return config
def _get_default_config(self) -> Dict[str, Any]:
"""
Get default configuration values.
Returns:
Default configuration dictionary
"""
return {
"api_keys": {
"gemini_api_key": "",
"pinecone_api_key": "",
"openai_api_key": "",
},
"vector_db": {
"provider": "pinecone",
"index_name": "rag-ai-index",
"dimension": 3072, # ✅ Fixed: Match Gemini embedding dimension
"metric": "cosine",
"environment": "us-west1-gcp",
},
"embedding": {
"model": "gemini-embedding-exp-03-07",
"batch_size": 5,
"max_retries": 3,
"retry_delay": 1,
},
"document_processing": {
"chunk_size": 1000,
"chunk_overlap": 200,
"min_chunk_size": 100,
"max_file_size_mb": 50,
},
"url_processing": {
"max_depth": 1,
"follow_links": True,
"max_pages": 10,
"timeout": 10,
},
"rag": {
"top_k": 5,
"similarity_threshold": 0.7,
"max_context_length": 4000,
"model": "gpt-3.5-turbo",
"max_tokens": 500,
"temperature": 0.7,
},
"ui": {
"title": "AI Embedded Knowledge Agent",
"description": "Upload documents or provide URLs to build your knowledge base, then ask questions!",
"theme": "default",
"share": False,
"port": 7860,
},
"logging": {
"level": "INFO",
"format": "%(asctime)s - %(name)s - %(levelname)s - %(message)s",
},
}
def _merge_configs(
self, base: Dict[str, Any], override: Dict[str, Any]
) -> Dict[str, Any]:
"""
Recursively merge two configuration dictionaries.
Args:
base: Base configuration dictionary
override: Override configuration dictionary
Returns:
Merged configuration dictionary
"""
result = base.copy()
for key, value in override.items():
if (
key in result
and isinstance(result[key], dict)
and isinstance(value, dict)
):
result[key] = self._merge_configs(result[key], value)
else:
result[key] = value
return result
def _apply_env_overrides(self, config: Dict[str, Any]) -> Dict[str, Any]:
"""
Apply environment variable overrides to configuration.
Args:
config: Configuration dictionary
Returns:
Configuration with environment overrides applied
"""
# API Keys
if os.environ.get("GEMINI_API_KEY"):
config["api_keys"]["gemini_api_key"] = os.environ["GEMINI_API_KEY"]
if os.environ.get("PINECONE_API_KEY"):
config["api_keys"]["pinecone_api_key"] = os.environ["PINECONE_API_KEY"]
if os.environ.get("OPENAI_API_KEY"):
config["api_keys"]["openai_api_key"] = os.environ["OPENAI_API_KEY"]
# Pinecone settings
if os.environ.get("PINECONE_ENVIRONMENT"):
config["vector_db"]["environment"] = os.environ["PINECONE_ENVIRONMENT"]
if os.environ.get("PINECONE_INDEX_NAME"):
config["vector_db"]["index_name"] = os.environ["PINECONE_INDEX_NAME"]
# UI settings
if os.environ.get("GRADIO_SHARE"):
config["ui"]["share"] = os.environ["GRADIO_SHARE"].lower() == "true"
if os.environ.get("PORT"):
try:
config["ui"]["port"] = int(os.environ["PORT"])
except ValueError:
self.logger.warning(f"Invalid PORT value: {os.environ['PORT']}")
return config
def _validate_config(self, config: Dict[str, Any]) -> None:
"""
Validate configuration values.
Args:
config: Configuration dictionary to validate
"""
# Check required API keys
if not config["api_keys"]["gemini_api_key"]:
self.logger.warning("Gemini API key not configured")
if not config["api_keys"]["pinecone_api_key"]:
self.logger.warning("Pinecone API key not configured")
# Validate numeric values
if config["document_processing"]["chunk_size"] <= 0:
raise ValueError("chunk_size must be positive")
if config["rag"]["top_k"] <= 0:
raise ValueError("top_k must be positive")
if not 0 <= config["rag"]["similarity_threshold"] <= 1:
raise ValueError("similarity_threshold must be between 0 and 1")
def get(self, key: str, default: Any = None) -> Any:
"""
Get a configuration value using dot notation.
Args:
key: Configuration key (e.g., 'vector_db.index_name')
default: Default value if key not found
Returns:
Configuration value
"""
keys = key.split(".")
value = self.config
try:
for k in keys:
value = value[k]
return value
except (KeyError, TypeError):
return default
def set(self, key: str, value: Any) -> None:
"""
Set a configuration value using dot notation.
Args:
key: Configuration key (e.g., 'vector_db.index_name')
value: Value to set
"""
keys = key.split(".")
config = self.config
for k in keys[:-1]:
if k not in config:
config[k] = {}
config = config[k]
config[keys[-1]] = value
def get_section(self, section: str) -> Dict[str, Any]:
"""
Get an entire configuration section.
Args:
section: Section name
Returns:
Configuration section dictionary
"""
return self.config.get(section, {})
def reload(self) -> None:
"""Reload configuration from file."""
self.config = self._load_config()
self.logger.info("Configuration reloaded")
|