Better Vector Search for Long Documents: Chunking Inside Manticore Search

说明与用途

Manticore 在插入时自动将长文档拆分为块，显著提升 recall@5（55.1%→83.3%）和 MRR，且仅略微增加内存和摄取时间。

问题

Embedding models with limited token windows truncate long documents, causing loss of content and poor search recall.

结果

Using Manticore’s chunk_strategy increased recall@5 from 55.1% to 83.3% and MRR from 0.44 to 0.70 on a 189‑page manual, with only ~2.5× RAM and ~4× ingest time overhead.

工作流

• Create a table with a float_vector_array column and set chunk_strategy (e.g., 'sentence'), max_tokens, and overlap_tokens.
• Insert documents; Manticore splits each document into chunks, generates embeddings for each chunk, and stores them in the array column.
• Run vector queries; Manticore searches all chunks and returns the document once, reporting the nearest chunk distance.
• Optionally adjust chunking parameters (max_tokens, overlap_tokens, max_chunks) to tune performance and recall.
• Monitor recall@5 and MRR to validate improvements.

证据

Recall@5 went from 55.1% → 83.3% and MRR from 0.44 → 0.70, at ~2.5× the RAM and ~4× the ingest time.

来源