Input
ExecutionExecution trigger to start summarization.
AI/Processing
Creates an intelligent summary of document pages using AI with configurable strategies and detail levels. Handles long documents via chunked summarization with multiple strategy options.
Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.
Execution trigger to start summarization.
Document pages to summarize.
AI model to use for summarization.
Summary detail level: Low (very concise), Medium (balanced), High (comprehensive).
Whether to include a table of contents with page references.
Summarization strategy: • Refine — sequential, best coherence, no parallelism • MapReduce — parallel chunking, fast, may lose cross-chunk context • Hierarchical — structure-aware tree, best for headed documents • Hybrid — MapReduce speed + Refine coherence polish • SlidingWindow — fixed memory buffer, best for very long documents
Post-processing to increase information density: • None — use the strategy output as-is • ChainOfDensity — iteratively compress to optimal density
Maximum characters per summarization chunk (adjust based on model context window).
Overlap between adjacent chunks as percentage (0-50). Prevents information loss at boundaries (default: 10).
Extract and track named entities across chunks to prevent information loss.
Number of chunks to process in parallel for MapReduce/Hybrid strategies. 0 = unlimited (default: 4).
Number of Chain of Density refinement steps when densification is enabled (1-5, default: 3).
Execution output after summarization completes.
The generated document summary.
Reference to content location within the document