Skip to content

Document multi-vector embeddings and late-interaction search#1545

Merged
lukekim merged 2 commits into
trunkfrom
lukim/column-embeddings
Apr 21, 2026
Merged

Document multi-vector embeddings and late-interaction search#1545
lukekim merged 2 commits into
trunkfrom
lukim/column-embeddings

Conversation

@lukekim
Copy link
Copy Markdown
Contributor

@lukekim lukekim commented Apr 21, 2026

Summary

Documents multi-vector (column-of-vectors) embeddings and ColBERT-style late-interaction search — features that exist in spiceai but were previously undocumented.

Changes

  • New page website/docs/features/search/multi-vector.md — multi-vector vs chunking, configuration, aggregation strategies (max/mean/sum), max_elements_per_row, SQL usage, ColBERT-style late-interaction multi-query search, passthrough schemas, and limitations.
  • Search index (features/search/index.md) — added Multi-Vector as a first-class search method with an example.
  • Vector search (features/search/vector-search.md) — cross-reference to the new page.
  • Embeddings component (components/embeddings/index.md) — new Multi-Vector Embeddings section covering list-typed source columns and the aggregation / max_elements_per_row knobs.
  • Datasets reference (reference/spicepod/datasets.md) — documented the previously missing columns[*].embeddings[*].aggregation and columns[*].embeddings[*].max_elements_per_row fields.
  • SQL search reference (reference/sql/search.md) — documented the multi-query (late-interaction) form of vector_search.

Add a new Multi-Vector Search feature page covering column-of-vectors
embeddings (List<Utf8> source columns), aggregation strategies
(max/mean/sum), max_elements_per_row caps, and ColBERT-style
late-interaction multi-query vector_search.

Cross-link from the search index, vector search, and embeddings
component pages, and document the previously-missing aggregation and
max_elements_per_row fields in the datasets reference.
@github-actions
Copy link
Copy Markdown

github-actions Bot commented Apr 21, 2026

✅ Pull with Spice Passed

Passing checks:

  • ✅ Title meets minimum length requirement (10 characters)
  • ✅ Has at least one of the required labels: area/blog, area/docs, area/cookbook, dependencies
  • ✅ No banned labels detected
  • ✅ Has at least one assignee: lukekim

@lukekim lukekim self-assigned this Apr 21, 2026
@lukekim lukekim added this to the v2.0 milestone Apr 21, 2026
@lukekim lukekim enabled auto-merge (rebase) April 21, 2026 18:01
@github-actions
Copy link
Copy Markdown

🚀 deployed to https://ca151686.spiceai-org-website.pages.dev

@lukekim lukekim merged commit 08fd014 into trunk Apr 21, 2026
6 checks passed
@lukekim lukekim deleted the lukim/column-embeddings branch April 21, 2026 18:10
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants