enhanced_process_large_content
Read-only
Chunk large content and apply BM25 filtering to extract relevant parts. Persist chunks and summaries as JSON to disk for efficient retrieval.
Instructions
Process large content with chunking and BM25 filtering. Use output_path to persist chunks + summaries to disk as JSON and receive a slim response.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL to process | |
| overwrite | No | Overwrite an existing output file at output_path. Defaults to False. | |
| output_path | No | Absolute file path (auto .json extension) to persist the full chunks + summaries as JSON. When set, the response is slimmed to metadata+file path (chunks, chunk_summaries, merged_summary, final_summary removed). | |
| filter_query | No | Keywords for BM25 filtering | |
| chunk_overlap | No | Overlap tokens | |
| merge_strategy | No | 'hierarchical'|'linear' | linear |
| max_chunk_tokens | No | Max tokens per chunk | |
| summarize_chunks | No | Summarize chunks | |
| chunking_strategy | No | 'topic'|'sentence'|'overlap'|'regex' | sentence |
| extract_top_chunks | No | Top chunks to extract | |
| filtering_strategy | No | 'bm25'|'pruning'|'llm' | bm25 |
| final_summary_length | No | 'short'|'medium'|'long' | short |
| similarity_threshold | No | Min similarity 0-1 | |
| include_content_in_response | No | When True (with output_path set), also include chunks/summaries in the response. Defaults to False. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||