congqixia
7b21032d19
fix: Check all values for trie.predictive_search ( #35943 )
...
Related to #35941
For marisa trie `predictive_search` default behavior, it value iterated
is not in lexicographic order.
This PR is a brute force fix to make range operator returns correct
values.
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-09-05 15:01:04 +08:00
Zhen Ye
f68df9a11e
fix: SkipIndex cause segment fault ( #35907 )
...
issue: #35882
Signed-off-by: chyezh <chyezh@outlook.com>
2024-09-03 17:15:03 +08:00
zhagnlu
671112d17b
enhance: add more info to hybrid index log ( #35808 )
...
#32900
Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2024-08-29 21:07:04 +08:00
Patrick Weizhi Xu
b3089b5bdc
feat: support range search pagination retains order ( #35738 )
...
issue: #35464
Signed-off-by: Patrick Weizhi Xu <weizhi.xu@zilliz.com>
2024-08-29 14:09:00 +08:00
smellthemoon
b51b4a2838
fix: try get not exist file after upgrade ( #35740 )
...
https://github.com/milvus-io/milvus/issues/35741
Signed-off-by: lixinguo <xinguo.li@zilliz.com>
Co-authored-by: lixinguo <xinguo.li@zilliz.com>
2024-08-29 11:09:01 +08:00
Jiquan Long
a52ba3d09d
enhance: allow many segments for inverted index ( #35616 )
...
fix: https://github.com/milvus-io/milvus/issues/35615
---------
Signed-off-by: longjiquan <jiquan.long@zilliz.com>
2024-08-28 11:30:59 +08:00
zhagnlu
4d2f96c760
enhance: support bitmap mmap ( #35399 )
...
#32900
Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2024-08-27 16:34:59 +08:00
cai.zhang
615a653988
fix: Fix offset out of range for creating Trie index ( #35553 )
...
issue: #35550
Signed-off-by: Cai Zhang <cai.zhang@zilliz.com>
2024-08-25 15:50:57 +08:00
zhagnlu
42f7800b5b
enhance: add bitmap offset cache to speed up retrieve raw data ( #35498 )
...
#35458
Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2024-08-24 01:40:58 +08:00
Zhen Ye
a773836b89
enhance: optimize milvus core building ( #35610 )
...
issue: #35549,#35611,#35633
- remove milvus_segcore milvus_indexbuilder..., add libmilvus_core
- core building only link once
- move opendal compilation into cmake
- fix odr
---------
Signed-off-by: chyezh <chyezh@outlook.com>
2024-08-23 12:35:02 +08:00
smellthemoon
80dbe87759
enhance: support null value in index ( #35238 )
...
#31728
---------
Signed-off-by: lixinguo <xinguo.li@zilliz.com>
Co-authored-by: lixinguo <xinguo.li@zilliz.com>
2024-08-16 15:30:54 +08:00
zhagnlu
626b1b2f5e
fix:redefine hybrid internal index type ( #35314 )
...
#32900
Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2024-08-08 10:32:16 +08:00
zhagnlu
c19fe95154
fix: support string match for hybrid and bitmap index ( #35294 )
...
#34841
Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2024-08-07 09:54:22 +08:00
Cai Yudong
3c9a47c8db
feat: Encode traceID and spanID as hex string ( #34807 )
...
Issue: https://github.com/zilliztech/knowhere/pull/714
Signed-off-by: Cai Yudong <yudong.cai@zilliz.com>
2024-08-06 15:20:16 +08:00
Jiquan Long
91df03afe8
feat: put inverted index into ram ( #35222 )
...
fix: https://github.com/milvus-io/milvus/issues/35224
---------
Signed-off-by: longjiquan <jiquan.long@zilliz.com>
2024-08-06 11:54:16 +08:00
zhagnlu
f8c1b138a8
fix:fix get array error for int type ( #35154 )
...
#35055
Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2024-08-01 14:30:12 +08:00
zhenshan.cao
aa247f192d
enhance: remove unused code for StorageV2 ( #35132 )
...
issue: https://github.com/milvus-io/milvus/issues/34168
Signed-off-by: zhenshan.cao <zhenshan.cao@zilliz.com>
2024-08-01 12:08:13 +08:00
zhagnlu
804ec24c02
fix:fix retrieve raw data from bitmap array index ( #34848 )
...
#34795
Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2024-07-27 01:53:47 +08:00
smellthemoon
5616b7e8d2
enhance: support null in c data_datacodec and load null value ( #32183 )
...
1. support read and write null in segcore
will store valid_data(use uint8_t type to save memory) in fieldData.
2. support load null
binlog reader read and write data into column(sealed segment),
insertRecord(growing segment). In sealed segment, store valid_data
directly. In growing segment, considering prior implementation and easy
code reading, it covert uint8_t to fbvector<bool>, which may optimize in
future.
3. retrieve valid_data.
parse valid_data in search/query.
#31728
---------
Signed-off-by: lixinguo <xinguo.li@zilliz.com>
Co-authored-by: lixinguo <xinguo.li@zilliz.com>
2024-07-23 16:07:51 +08:00
Min Tian
a4aed9b0b5
enhance: new knowhere param for range_search ( #34686 )
...
issue: #34685
knowhere needs a new json param `range_search_k` for RangeSearch to
early terminate the iterator.
Signed-off-by: min.tian <min.tian.cn@gmail.com>
2024-07-23 11:45:43 +08:00
foxspy
8e64bf929c
enhance: add scalar filtering and vector search latency metrics ( #34785 )
...
add scalar filtering and vector search latency metrics to distinguish
the cost of scalar filtering.
To add metrics in query chain, add a monitor module and move the metric
files from original storage module.
issue: #34780
Signed-off-by: xianliang.li <xianliang.li@zilliz.com>
2024-07-19 14:01:39 +08:00
zhagnlu
f1b2f7b640
enhance: refactor bitmap index and internal hybrid index ( #34450 )
...
#32900
Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2024-07-18 10:39:42 +08:00
Patrick Weizhi Xu
104d0966b7
feat: support partition key isolation ( #34336 )
...
issue: #34332
---------
Signed-off-by: Patrick Weizhi Xu <weizhi.xu@zilliz.com>
2024-07-11 19:01:35 +08:00
zhagnlu
cc1bc07bfd
enhance: add log to bitmap index ( #34197 )
...
#32900
Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2024-06-30 20:02:06 +08:00
Cai Yudong
ad90360162
enhance: Update knowhere commit ( #34223 )
...
Signed-off-by: Cai Yudong <yudong.cai@zilliz.com>
2024-06-27 18:20:06 +08:00
zhagnlu
03a3f50892
enhance: add skip using array index when some situation ( #33947 )
...
#32900
Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2024-06-23 21:26:02 +08:00
zhagnlu
0d7ea8ec42
enhance: Enhance and correct exception module ( #33705 )
...
#33704
Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2024-06-23 21:22:01 +08:00
Gao
0d20303e54
fix: fix binary vector data size ( #33750 )
...
issue: https://github.com/milvus-io/milvus/issues/22837
- fix byte size wrong for binary vectors
- fix the expect/actual error msg
Signed-off-by: chasingegg <chao.gao@zilliz.com>
2024-06-18 21:39:59 +08:00
zhagnlu
d43ec4db0b
enhance: support array bitmap index ( #33527 )
...
#32900
---------
Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2024-06-16 21:51:58 +08:00
Buqian Zheng
47b04ea167
enhance: support sparse cardinal hnsw index ( #33656 )
...
issue: #29419
Signed-off-by: Buqian Zheng <zhengbuqian@gmail.com>
2024-06-12 16:57:55 +08:00
Jiquan Long
ecf2bcee42
enhance: speed up array-equal operator via inverted index ( #33633 )
...
fix : #33632
---------
Signed-off-by: longjiquan <jiquan.long@zilliz.com>
2024-06-11 14:13:54 +08:00
cqy123456
703fc73f71
enhance: disk index support binary vector ( #33631 )
...
issue:https://github.com/milvus-io/milvus/issues/22837
related https://github.com/milvus-io/milvus/pull/33575
Signed-off-by: cqy123456 <qianya.cheng@zilliz.com>
2024-06-05 19:37:57 +08:00
Gao
545d4725fb
fix: correct get vector data size for bf16/fp16/binary vector ( #33377 )
...
related #22837
Signed-off-by: chasingegg <chao.gao@zilliz.com>
2024-06-05 14:31:57 +08:00
Jiquan Long
0c5d8660aa
feat: support inverted index for array ( #33452 )
...
issue: https://github.com/milvus-io/milvus/issues/27704
---------
Signed-off-by: longjiquan <jiquan.long@zilliz.com>
2024-05-31 09:47:47 +08:00
zhagnlu
589d4dfd82
enhance: optimize bitmap index ( #33358 )
...
#32900
Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2024-05-30 13:09:43 +08:00
Buqian Zheng
c5918ffbdb
enhance: mark sparse inverted index as mmap-able ( #33281 )
...
issue: #29419
Signed-off-by: Buqian Zheng <zhengbuqian@gmail.com>
2024-05-23 14:11:42 +08:00
zhagnlu
d669fbcf46
enhance: support bitmap index for scalar type ( #32902 )
...
#32900
Signed-off-by: luzhang <luzhang@zilliz.com>
Co-authored-by: luzhang <luzhang@zilliz.com>
2024-05-19 21:49:38 +08:00
Bingyi Sun
fecd9c21ba
feat: LRU cache implementation ( #32567 )
...
issue: https://github.com/milvus-io/milvus/issues/32783
This pr is the implementation of lru cache on branch lru-dev.
Signed-off-by: sunby <sunbingyi1992@gmail.com>
Co-authored-by: chyezh <chyezh@outlook.com>
Co-authored-by: MrPresent-Han <chun.han@zilliz.com>
Co-authored-by: Ted Xu <ted.xu@zilliz.com>
Co-authored-by: jaime <yun.zhang@zilliz.com>
Co-authored-by: wayblink <anyang.wang@zilliz.com>
2024-05-06 20:29:30 +08:00
Gao
0fab265eed
enhance: update knowhere and some header changes ( #32468 )
...
Signed-off-by: chasingegg <chao.gao@zilliz.com>
2024-04-22 15:47:26 +08:00
Chun Han
337cc0756d
fix: lack good results for insufficient ef( #29883 ) ( #32080 )
...
related: #29883
Signed-off-by: MrPresent-Han <chun.han@zilliz.com>
2024-04-13 22:13:23 +08:00
Jiquan Long
4fb85be525
fix: put inverted index into local storage ( #32209 )
...
issue: https://github.com/milvus-io/milvus/issues/32154
Signed-off-by: longjiquan <jiquan.long@zilliz.com>
2024-04-13 21:57:19 +08:00
cai.zhang
1b767669a4
enhance: Throw error instead of crash when index cannot be built ( #31844 )
...
issue: #27589
---------
Signed-off-by: Cai Zhang <cai.zhang@zilliz.com>
2024-04-09 11:51:18 +08:00
cqy123456
aba4993c6c
fix: fix some fp16/bf16 code miss in segcore. ( #31771 )
...
issue：https://github.com/milvus-io/milvus/issues/22837
Signed-off-by: cqy123456 <qianya.cheng@zilliz.com>
2024-04-07 14:13:16 +08:00
Cai Yudong
246586be27
enhance: Unify data type check APIs under internal/core ( #31800 )
...
Issue: #22837
Move and rename following C++ APIs:
datatype_sizeof() ==> GetDataTypeSize()
datatype_name() ==> GetDataTypeName()
datatype_is_vector() / IsVectorType() ==> IsVectorDataType()
datatype_is_variable() ==> IsVariableDataType()
datatype_is_sparse_vector() ==> IsSparseFloatVectorDataType()
datatype_is_string() / IsString() ==> IsDataTypeString()
datatype_is_floating() / IsFloat() ==> IsDataTypeFloat()
datatype_is_binary() ==> IsDataTypeBinary()
datatype_is_json() ==> IsDataTypeJson()
datatype_is_array() ==> IsDataTypeArray()
datatype_is_variable() == IsDataTypeVariable()
datatype_is_integer() / IsIntegral() ==> IsDataTypeInteger()
Signed-off-by: Cai Yudong <yudong.cai@zilliz.com>
2024-04-02 19:15:14 +08:00
Cai Yudong
675a5dc822
fix: Save traceID and spanID as std::vector into search config ( #31278 )
...
Issue: #30961
Signed-off-by: Yudong Cai <yudong.cai@zilliz.com>
2024-03-29 14:29:11 +08:00
Buqian Zheng
96cfae55a5
feat: [Sparse Float Vector] segcore to support sparse vector search and get raw vector by id ( #30629 )
...
This PR adds the ability to search/get sparse float vectors in segcore,
and added unit tests by modifying lots of existing tests into
parameterized ones.
https://github.com/milvus-io/milvus/issues/29419
Signed-off-by: Buqian Zheng <zhengbuqian@gmail.com>
2024-03-12 09:16:30 -07:00
Buqian Zheng
070dfc77bf
feat: [Sparse Float Vector] segcore basics and index building ( #30357 )
...
This commit adds sparse float vector support to segcore with the
following:
1. data type enum declarations
2. Adds corresponding data structures for handling sparse float vectors
in various scenarios, including:
* FieldData as a bridge between the binlog and the in memory data
structures
* mmap::Column as the in memory representation of a sparse float vector
column of a sealed segment;
* ConcurrentVector as the in memory representation of a sparse float
vector of a growing segment which supports inserts.
3. Adds logic in payload reader/writer to serialize/deserialize from/to
binlog
4. Adds the ability to allow the index node to build sparse float vector
index
5. Adds the ability to allow the query node to build growing index for
growing segment and temp index for sealed segment without index built
This commit also includes some code cleanness, comment improvement, and
some unit tests for sparse vector.
https://github.com/milvus-io/milvus/issues/29419
Signed-off-by: Buqian Zheng <zhengbuqian@gmail.com>
2024-03-11 14:45:02 +08:00
Cai Yudong
a99143dd52
fix: Save traceID and spanID as hex string into search config ( #31071 )
...
Issue: #30961
Signed-off-by: Yudong Cai <yudong.cai@zilliz.com>
2024-03-11 14:21:01 +08:00
Cai Yudong
122981aeb9
fix: Disable knowhere trace as a quick fix ( #31055 )
...
Issue: #30961
Signed-off-by: Yudong Cai <yudong.cai@zilliz.com>
2024-03-08 15:27:01 +08:00
MrPresent-Han
29f44f840a
enhance: refine groupBy error msg( #29968 ) ( #30920 )
...
related: #29968
Signed-off-by: MrPresent-Han <chun.han@zilliz.com>
2024-03-01 18:53:03 +08:00
