thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-09-20 00:30:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #50942 from ClickHouse/fix-ann-page

Browse Source 
Fixes to ANN docs page
This commit is contained in:
Robert Schulze 2023-06-13 17:57:00 +02:00 committed by GitHub
commit 22670aebf8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
docs/en/engines/table-engines/mergetree-family/annindexes.md
View File

@ -54,7 +54,7 @@ CREATE TABLE table
(
`id` Int64,
`vectors` Array(Float32),
INDEX <ann_index_name> vectors TYPE <ann_index_type>(<ann_index_parameters>) [GRANULARITY <N>]
INDEX [ann_index_name vectors TYPE [ann_index_type]([ann_index_parameters]) [GRANULARITY [N]]
)
ENGINE = MergeTree
ORDER BY id;
@ -67,7 +67,7 @@ CREATE TABLE table
(
`id` Int64,
`vectors` Tuple(Float32[, Float32[, ...]]),
INDEX <ann_index_name> vectors TYPE <ann_index_type>(<ann_index_parameters>) [GRANULARITY <N>]
INDEX [ann_index_name] vectors TYPE [ann_index_type]([ann_index_parameters]) [GRANULARITY [N]]
)
ENGINE = MergeTree
ORDER BY id;
@ -114,7 +114,7 @@ without `LIMIT` clause cannot utilize ANN indexes. Also ANN indexes are only use
approximate neighbor search.
**Differences to Skip Indexes** Similar to regular [skip indexes](https://clickhouse.com/docs/en/optimize/skipping-indexes), ANN indexes are
constructed over granules and each indexed block consists of `GRANULARITY = <N>`-many granules (`<N>` = 1 by default for normal skip
constructed over granules and each indexed block consists of `GRANULARITY = [N]`-many granules (`[N]` = 1 by default for normal skip
indexes). For example, if the primary index granularity of the table is 8192 (setting `index_granularity = 8192`) and `GRANULARITY = 2`,
then each indexed block will contain 16384 rows. However, data structures and algorithms for approximate neighborhood search (usually
provided by external libraries) are inherently row-oriented. They store a compact representation of a set of rows and also return rows for
@ -130,7 +130,8 @@ skip data at the granularity of index blocks.
The `GRANULARITY` parameter determines how many ANN sub-indexes are created. Bigger `GRANULARITY` values mean fewer but larger ANN
sub-indexes, up to the point where a column (or a column's data part) has only a single sub-index. In that case, the sub-index has a
"global" view of all column rows and can directly return all granules of the column (part) with relevant rows (there are at most
`LIMIT <N>`-many such granules). In a second step, ClickHouse will load these granules and identify the actually best rows by performing a
`LIMIT [N]`-many such granules). In a second step, ClickHouse will load these granules and identify the actually best rows by performing a
brute-force distance calculation over all rows of the granules. With a small `GRANULARITY` value, each of the sub-indexes returns up to
`LIMIT N`-many granules. As a result, more granules need to be loaded and post-filtered. Note that the search accuracy is with both cases
equally good, only the processing performance differs. It is generally recommended to use a large `GRANULARITY` for ANN indexes and fall
@ -169,7 +170,7 @@ CREATE TABLE table
(
id Int64,
vectors Array(Float32),
INDEX <ann_index_name> vectors TYPE annoy([Distance[, NumTrees]]) [GRANULARITY N]
INDEX [ann_index_name] vectors TYPE annoy([Distance[, NumTrees]]) [GRANULARITY N]
)
ENGINE = MergeTree
ORDER BY id;
@ -182,7 +183,7 @@ CREATE TABLE table
(
id Int64,
vectors Tuple(Float32[, Float32[, ...]]),
INDEX <ann_index_name> vectors TYPE annoy([Distance[, NumTrees]]) [GRANULARITY N]
INDEX [ann_index_name] vectors TYPE annoy([Distance[, NumTrees]]) [GRANULARITY N]
)
ENGINE = MergeTree
ORDER BY id;