haive.core.engine.document
==========================

.. py:module:: haive.core.engine.document

.. autoapi-nested-parse::

   📚 Document Engine - Intelligent Document Processing Revolution

   **THE OMNIPOTENT DOCUMENT CONSCIOUSNESS THAT UNDERSTANDS EVERYTHING**

   Welcome to the Document Engine - the revolutionary document intelligence platform
   that transforms static document processing into a living, adaptive understanding
   system. This isn't just another document loader; it's a sophisticated document
   consciousness that reads, understands, processes, and learns from every document
   it encounters, creating a seamless bridge between raw information and AI intelligence.

   ⚡ REVOLUTIONARY DOCUMENT INTELLIGENCE
   ------------------------------------

   The Document Engine represents a paradigm shift from traditional document processing to
   **intelligent, adaptive document understanding systems** that evolve with content:

   **🧠 Universal Document Understanding**: Processes any document type with intelligent format detection
   **🔄 Adaptive Processing Strategies**: Dynamic chunking and processing based on content analysis
   **⚡ Intelligent Source Detection**: AI-powered identification of optimal loading strategies
   **📊 Context-Aware Chunking**: Smart content segmentation that preserves semantic meaning
   **🎯 Multi-Source Intelligence**: Seamless processing from files, URLs, databases, and cloud storage

   🌟 CORE DOCUMENT INNOVATIONS
   ---------------------------

   **1. Intelligent Document Engine** 🚀
      Revolutionary document processing that thinks and adapts:

   .. rubric:: Examples

   >>> from haive.core.engine.document import DocumentEngine, DocumentEngineConfig
   >>> from haive.core.engine.document import ChunkingStrategy, ProcessingStrategy
   >>>
   >>> # Create intelligent document engine with learning capabilities
   >>> engine = DocumentEngine(
   >>> config=DocumentEngineConfig(
   >>> name="intelligent_processor",
   >>> chunking_strategy=ChunkingStrategy.SEMANTIC_AWARE,
   >>> processing_strategy=ProcessingStrategy.ADAPTIVE,
   >>> learning_enabled=True,
   >>> context_preservation=True
   >>> )
   >>> )
   >>>
   >>> # Engine automatically optimizes processing based on content
   >>> engine.enable_content_learning(
   >>> metrics=["chunk_quality", "semantic_coherence", "processing_speed"],
   >>> optimization_target="content_understanding"
   >>> )
   >>>
   >>> # Process documents with intelligent adaptation
   >>> result = engine.invoke([
   >>> "path/to/technical_manual.pdf",
   >>> "https://api.docs.example.com/v1/guide",
   >>> {"database": "mongodb://localhost", "collection": "documents"}
   >>> ])
   >>>
   >>> # Engine learns optimal processing strategies for each content type
   >>> processing_insights = engine.get_processing_insights()
   >>> content_analysis = engine.get_content_analysis_report()
   >>>
   >>> # Apply learned optimizations automatically
   >>> engine.apply_learned_optimizations(
   >>> confidence_threshold=0.85,
   >>> preserve_quality=True
   >>> )

   For complete examples and advanced patterns, see the documentation.



Submodules
----------

.. toctree::
   :maxdepth: 1

   /autoapi/haive/core/engine/document/agents/index
   /autoapi/haive/core/engine/document/config/index
   /autoapi/haive/core/engine/document/engine/index
   /autoapi/haive/core/engine/document/factory/index
   /autoapi/haive/core/engine/document/loaders/index
   /autoapi/haive/core/engine/document/path_analysis/index
   /autoapi/haive/core/engine/document/processors/index
   /autoapi/haive/core/engine/document/splitters/index
   /autoapi/haive/core/engine/document/transformers/index
   /autoapi/haive/core/engine/document/types/index
   /autoapi/haive/core/engine/document/universal_loader/index