Spaces:
Sleeping
Sleeping
| # ============================================================================= | |
| # DEPLOYMENT CONFIGURATION FOR GRADIO SPACES | |
| # ============================================================================= | |
| import os | |
| from dotenv import load_dotenv | |
| # Load environment variables | |
| load_dotenv() | |
| # ============================================================================= | |
| # OPENAI CONFIGURATION | |
| # ============================================================================= | |
| # API Key (required for deployment) | |
| OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") | |
| if not OPENAI_API_KEY: | |
| print("⚠️ Warning: OPENAI_API_KEY not found in environment variables") | |
| # Embedding model configuration | |
| OPENAI_EMBEDDING_MODEL = "text-embedding-3-large" | |
| EMBEDDING_DIMENSIONS = 3072 | |
| # ============================================================================= | |
| # QDRANT CONFIGURATION | |
| # ============================================================================= | |
| # Qdrant URL (cloud deployment will need external Qdrant) | |
| QDRANT_URL = os.getenv("QDRANT_URL", "http://localhost:6333") | |
| QDRANT_API_KEY = os.getenv("QDRANT_API_KEY") # For cloud Qdrant | |
| # Collection configuration | |
| QDRANT_COLLECTION_NAME = "chunks_collection" | |
| # ============================================================================= | |
| # CHUNKING CONFIGURATION | |
| # ============================================================================= | |
| # Available chunking methods | |
| CHUNKING_METHODS = ["fixed", "sentence", "adaptive"] | |
| # Fixed chunking parameters | |
| FIXED_CHUNK_SIZE = 1000 | |
| FIXED_CHUNK_OVERLAP = 200 | |
| # Sentence chunking parameters | |
| SENTENCE_MIN_CHUNK_SIZE = 100 | |
| SENTENCE_MAX_CHUNK_SIZE = 1000 | |
| # Adaptive chunking parameters | |
| ADAPTIVE_MIN_CHUNK_SIZE = 200 | |
| ADAPTIVE_MAX_CHUNK_SIZE = 800 | |
| ADAPTIVE_SIMILARITY_THRESHOLD = 0.5 | |
| # ============================================================================= | |
| # SEARCH AND RETRIEVAL CONFIGURATION | |
| # ============================================================================= | |
| # Number of chunks to return in search results | |
| TOP_K_RESULTS = 10 | |
| # Minimum similarity score for search results | |
| MIN_SIMILARITY_SCORE = 0.5 | |
| # ============================================================================= | |
| # LOGGING CONFIGURATION | |
| # ============================================================================= | |
| # Logging level for deployment | |
| LOG_LEVEL = "INFO" | |
| # ============================================================================= | |
| # DEPLOYMENT NOTES | |
| # ============================================================================= | |
| """ | |
| For Gradio Spaces deployment: | |
| 1. Set environment variables in Space settings: | |
| - OPENAI_API_KEY: Your OpenAI API key | |
| - QDRANT_URL: URL to your cloud Qdrant instance | |
| - QDRANT_API_KEY: API key for cloud Qdrant (if required) | |
| 2. Consider using Qdrant Cloud or self-hosted Qdrant instance | |
| since Gradio Spaces don't support Docker containers | |
| 3. The app will show warning messages if components fail to initialize | |
| but will still launch for configuration troubleshooting | |
| """ |