docs(indexing): add rabitq performance guide#292
Closed
BubbleCal wants to merge 1 commit into
Closed
Conversation
Contributor
|
Preview deployment for your docs. Learn more about Mintlify Previews.
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Feature
What is the new feature?
approx_modetradeoffs.approx_modemodes.IvfRq(num_bits=5)snippet and links the new guide from indexing navigation, indexing overview, and quantization docs.Why do we need this feature?
IVF_RQneed a higher-level, marketing-friendly explanation of why multi-bit RaBitQ can deliver higher recall and lower tail latency without relying on raw-vector refine.IVF_PQ: PQ can stay small without refine, but high recall commonly needs raw vectors in the hot serving path, while multi-bitIVF_RQcan rerank with compact quantized codes.approx_modelets users adjust recall/performance per query instead of rebuilding indexes.How does it work?
docs/indexing/rabitq.mdxwith benchmark tables, SVG charts, implementation explanation, query-time mode guidance, and a shortIVF_RQsetup snippet.docs/docs.jsonso the page appears under Indexing.test_rabitq_create_indexsnippet source intests/py/test_indexing.pyand regeneratesdocs/snippets/indexing.mdx.Validation
jq empty docs/docs.jsongit diff --checkuv run pytest tests/py/test_indexing.py -k rabitq_create_indexuv run pytest tests/py/test_indexing.pyMintlify validation note:
mint broken-linkscould not be run becausemint,node,npm, andnpxare not installed in this environment.