init

vw-document-ai-indexer/env.yaml.example

@@ -0,0 +1,43 @@
+# Configuration file reference
+config: config.yaml
+
+# Processing settings
+njobs: 8  # Number of parallel processing jobs
+
+# Azure AI Search configuration
+search_service_name: "https://your-search-service.search.windows.net"
+search_admin_key: "your-search-admin-key"
+
+# Azure OpenAI Embedding service
+embedding_model_endpoint: "https://your-openai.openai.azure.com/openai/deployments/text-embedding-3-small/embeddings?api-version=2024-12-01-preview"
+embedding_model_key: "your-openai-key"
+VECTOR_DIMENSION: 1536
+FLAG_AOAI: "V3"  # Azure OpenAI version
+FLAG_EMBEDDING_MODEL: "AOAI"  # Embedding model type: "AOAI" or "qwen3-embedding-8b"
+
+# Document Intelligence configuration
+extract_method: "di+vision-llm"  # Extraction method: "di+vision-llm", "vision-llm", "di"
+form_rec_resource: "https://your-di-service.cognitiveservices.azure.com/"
+form_rec_key: "your-di-key"
+
+# Document Intelligence features
+di-hiRes: true  # High resolution OCR
+di-Formulas: true  # Mathematical expression detection
+di_allow_features_ext: "pdf;jpeg;jpg;png;bmp;tiff;heif"  # Supported file extensions
+
+# Vision and captioning models
+captioning_model_endpoint: "https://your-openai.openai.azure.com/openai/deployments/gpt-4o/chat/completions?api-version=2024-08-01-preview"
+captioning_model_key: "your-openai-key"
+vision_max_images: 200  # Maximum images to process per document (0 = no limit)
+vision_image_method: "openai"  # Image processing method: "openai"
+
+
+# Blob storage for figures and DI results
+FIGURE_BLOB_ACCOUNT_URL: "https://your-storage.blob.core.windows.net/container?sas-token"
+DI_BLOB_ACCOUNT_URL: "https://your-storage.blob.core.windows.net/container?sas-token"
+
+# Database configuration
+DB_URI: "postgresql://user:password@host:port/database_name"
+
+# Processing flags
+header_fix: false  # Enable/disable header fixing