forked from lancedb/lancedb
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathtable.py
More file actions
545 lines (465 loc) · 18.8 KB
/
table.py
File metadata and controls
545 lines (465 loc) · 18.8 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright The LanceDB Authors
from datetime import timedelta
import logging
from functools import cached_property
from typing import Dict, Iterable, List, Optional, Union, Literal
import warnings
from lancedb._lancedb import IndexConfig
from lancedb.embeddings.base import EmbeddingFunctionConfig
from lancedb.index import FTS, BTree, Bitmap, HnswPq, HnswSq, IvfFlat, IvfPq, LabelList
from lancedb.remote.db import LOOP
import pyarrow as pa
from lancedb.common import DATA, VEC, VECTOR_COLUMN_NAME
from lancedb.merge import LanceMergeInsertBuilder
from lancedb.embeddings import EmbeddingFunctionRegistry
from ..query import LanceVectorQueryBuilder, LanceQueryBuilder
from ..table import AsyncTable, IndexStatistics, Query, Table
class RemoteTable(Table):
def __init__(
self,
table: AsyncTable,
db_name: str,
):
self._table = table
self.db_name = db_name
@property
def name(self) -> str:
"""The name of the table"""
return self._table.name
def __repr__(self) -> str:
return f"RemoteTable({self.db_name}.{self.name})"
def __len__(self) -> int:
self.count_rows(None)
@property
def schema(self) -> pa.Schema:
"""The [Arrow Schema](https://arrow.apache.org/docs/python/api/datatypes.html#)
of this Table
"""
return LOOP.run(self._table.schema())
@property
def version(self) -> int:
"""Get the current version of the table"""
return LOOP.run(self._table.version())
@cached_property
def embedding_functions(self) -> Dict[str, EmbeddingFunctionConfig]:
"""
Get the embedding functions for the table
Returns
-------
funcs: dict
A mapping of the vector column to the embedding function
or empty dict if not configured.
"""
return EmbeddingFunctionRegistry.get_instance().parse_functions(
self.schema.metadata
)
def list_versions(self):
"""List all versions of the table"""
return LOOP.run(self._table.list_versions())
def to_arrow(self) -> pa.Table:
"""to_arrow() is not yet supported on LanceDB cloud."""
raise NotImplementedError("to_arrow() is not yet supported on LanceDB cloud.")
def to_pandas(self):
"""to_pandas() is not yet supported on LanceDB cloud."""
return NotImplementedError("to_pandas() is not yet supported on LanceDB cloud.")
def checkout(self, version: int):
return LOOP.run(self._table.checkout(version))
def checkout_latest(self):
return LOOP.run(self._table.checkout_latest())
def list_indices(self) -> Iterable[IndexConfig]:
"""List all the indices on the table"""
return LOOP.run(self._table.list_indices())
def index_stats(self, index_uuid: str) -> Optional[IndexStatistics]:
"""List all the stats of a specified index"""
return LOOP.run(self._table.index_stats(index_uuid))
def create_scalar_index(
self,
column: str,
index_type: Literal["BTREE", "BITMAP", "LABEL_LIST", "scalar"] = "scalar",
*,
replace: bool = False,
):
"""Creates a scalar index
Parameters
----------
column : str
The column to be indexed. Must be a boolean, integer, float,
or string column.
index_type : str
The index type of the scalar index. Must be "scalar" (BTREE),
"BTREE", "BITMAP", or "LABEL_LIST",
replace : bool
If True, replace the existing index with the new one.
"""
if index_type == "scalar" or index_type == "BTREE":
config = BTree()
elif index_type == "BITMAP":
config = Bitmap()
elif index_type == "LABEL_LIST":
config = LabelList()
else:
raise ValueError(f"Unknown index type: {index_type}")
LOOP.run(self._table.create_index(column, config=config, replace=replace))
def create_fts_index(
self,
column: str,
*,
replace: bool = False,
with_position: bool = True,
# tokenizer configs:
base_tokenizer: str = "simple",
language: str = "English",
max_token_length: Optional[int] = 40,
lower_case: bool = True,
stem: bool = False,
remove_stop_words: bool = False,
ascii_folding: bool = False,
):
config = FTS(
with_position=with_position,
base_tokenizer=base_tokenizer,
language=language,
max_token_length=max_token_length,
lower_case=lower_case,
stem=stem,
remove_stop_words=remove_stop_words,
ascii_folding=ascii_folding,
)
LOOP.run(self._table.create_index(column, config=config, replace=replace))
def create_index(
self,
metric="L2",
vector_column_name: str = VECTOR_COLUMN_NAME,
index_cache_size: Optional[int] = None,
num_partitions: Optional[int] = None,
num_sub_vectors: Optional[int] = None,
replace: Optional[bool] = None,
accelerator: Optional[str] = None,
index_type="vector",
):
"""Create an index on the table.
Currently, the only parameters that matter are
the metric and the vector column name.
Parameters
----------
metric : str
The metric to use for the index. Default is "L2".
vector_column_name : str
The name of the vector column. Default is "vector".
Examples
--------
>>> import lancedb
>>> import uuid
>>> from lancedb.schema import vector
>>> db = lancedb.connect("db://...", api_key="...", # doctest: +SKIP
... region="...") # doctest: +SKIP
>>> table_name = uuid.uuid4().hex
>>> schema = pa.schema(
... [
... pa.field("id", pa.uint32(), False),
... pa.field("vector", vector(128), False),
... pa.field("s", pa.string(), False),
... ]
... )
>>> table = db.create_table( # doctest: +SKIP
... table_name, # doctest: +SKIP
... schema=schema, # doctest: +SKIP
... )
>>> table.create_index("L2", "vector") # doctest: +SKIP
"""
if num_partitions is not None:
logging.warning(
"num_partitions is not supported on LanceDB cloud."
"This parameter will be tuned automatically."
)
if num_sub_vectors is not None:
logging.warning(
"num_sub_vectors is not supported on LanceDB cloud."
"This parameter will be tuned automatically."
)
if accelerator is not None:
logging.warning(
"GPU accelerator is not yet supported on LanceDB cloud."
"If you have 100M+ vectors to index,"
"please contact us at contact@lancedb.com"
)
if replace is not None:
logging.warning(
"replace is not supported on LanceDB cloud."
"Existing indexes will always be replaced."
)
index_type = index_type.upper()
if index_type == "VECTOR" or index_type == "IVF_PQ":
config = IvfPq(distance_type=metric)
elif index_type == "IVF_HNSW_PQ":
config = HnswPq(distance_type=metric)
elif index_type == "IVF_HNSW_SQ":
config = HnswSq(distance_type=metric)
elif index_type == "IVF_FLAT":
config = IvfFlat(distance_type=metric)
else:
raise ValueError(
f"Unknown vector index type: {index_type}. Valid options are"
" 'IVF_FLAT', 'IVF_PQ', 'IVF_HNSW_PQ', 'IVF_HNSW_SQ'"
)
LOOP.run(self._table.create_index(vector_column_name, config=config))
def add(
self,
data: DATA,
mode: str = "append",
on_bad_vectors: str = "error",
fill_value: float = 0.0,
) -> int:
"""Add more data to the [Table](Table). It has the same API signature as
the OSS version.
Parameters
----------
data: DATA
The data to insert into the table. Acceptable types are:
- dict or list-of-dict
- pandas.DataFrame
- pyarrow.Table or pyarrow.RecordBatch
mode: str
The mode to use when writing the data. Valid values are
"append" and "overwrite".
on_bad_vectors: str, default "error"
What to do if any of the vectors are not the same size or contains NaNs.
One of "error", "drop", "fill".
fill_value: float, default 0.
The value to use when filling vectors. Only used if on_bad_vectors="fill".
"""
LOOP.run(
self._table.add(
data, mode=mode, on_bad_vectors=on_bad_vectors, fill_value=fill_value
)
)
def search(
self,
query: Union[VEC, str] = None,
vector_column_name: Optional[str] = None,
query_type="auto",
fts_columns: Optional[Union[str, List[str]]] = None,
fast_search: bool = False,
) -> LanceVectorQueryBuilder:
"""Create a search query to find the nearest neighbors
of the given query vector. We currently support [vector search][search]
All query options are defined in [Query][lancedb.query.Query].
Examples
--------
>>> import lancedb
>>> db = lancedb.connect("db://...", api_key="...", # doctest: +SKIP
... region="...") # doctest: +SKIP
>>> data = [
... {"original_width": 100, "caption": "bar", "vector": [0.1, 2.3, 4.5]},
... {"original_width": 2000, "caption": "foo", "vector": [0.5, 3.4, 1.3]},
... {"original_width": 3000, "caption": "test", "vector": [0.3, 6.2, 2.6]}
... ]
>>> table = db.create_table("my_table", data) # doctest: +SKIP
>>> query = [0.4, 1.4, 2.4]
>>> (table.search(query) # doctest: +SKIP
... .where("original_width > 1000", prefilter=True) # doctest: +SKIP
... .select(["caption", "original_width"]) # doctest: +SKIP
... .limit(2) # doctest: +SKIP
... .to_pandas()) # doctest: +SKIP
caption original_width vector _distance # doctest: +SKIP
0 foo 2000 [0.5, 3.4, 1.3] 5.220000 # doctest: +SKIP
1 test 3000 [0.3, 6.2, 2.6] 23.089996 # doctest: +SKIP
Parameters
----------
query: list/np.ndarray/str/PIL.Image.Image, default None
The targetted vector to search for.
- *default None*.
Acceptable types are: list, np.ndarray, PIL.Image.Image
vector_column_name: str, optional
The name of the vector column to search.
- If not specified then the vector column is inferred from
the table schema
- If the table has multiple vector columns then the *vector_column_name*
needs to be specified. Otherwise, an error is raised.
fast_search: bool, optional
Skip a flat search of unindexed data. This may improve
search performance but search results will not include unindexed data.
- *default False*.
Returns
-------
LanceQueryBuilder
A query builder object representing the query.
Once executed, the query returns
- selected columns
- the vector
- and also the "_distance" column which is the distance between the query
vector and the returned vector.
"""
return LanceQueryBuilder.create(
self,
query,
query_type,
vector_column_name=vector_column_name,
fts_columns=fts_columns,
fast_search=fast_search,
)
def _execute_query(
self, query: Query, batch_size: Optional[int] = None
) -> pa.RecordBatchReader:
return LOOP.run(self._table._execute_query(query, batch_size=batch_size))
def merge_insert(self, on: Union[str, Iterable[str]]) -> LanceMergeInsertBuilder:
"""Returns a [`LanceMergeInsertBuilder`][lancedb.merge.LanceMergeInsertBuilder]
that can be used to create a "merge insert" operation.
See [`Table.merge_insert`][lancedb.table.Table.merge_insert] for more details.
"""
return super().merge_insert(on)
def _do_merge(
self,
merge: LanceMergeInsertBuilder,
new_data: DATA,
on_bad_vectors: str,
fill_value: float,
):
LOOP.run(self._table._do_merge(merge, new_data, on_bad_vectors, fill_value))
def delete(self, predicate: str):
"""Delete rows from the table.
This can be used to delete a single row, many rows, all rows, or
sometimes no rows (if your predicate matches nothing).
Parameters
----------
predicate: str
The SQL where clause to use when deleting rows.
- For example, 'x = 2' or 'x IN (1, 2, 3)'.
The filter must not be empty, or it will error.
Examples
--------
>>> import lancedb
>>> data = [
... {"x": 1, "vector": [1, 2]},
... {"x": 2, "vector": [3, 4]},
... {"x": 3, "vector": [5, 6]}
... ]
>>> db = lancedb.connect("db://...", api_key="...", # doctest: +SKIP
... region="...") # doctest: +SKIP
>>> table = db.create_table("my_table", data) # doctest: +SKIP
>>> table.search([10,10]).to_pandas() # doctest: +SKIP
x vector _distance # doctest: +SKIP
0 3 [5.0, 6.0] 41.0 # doctest: +SKIP
1 2 [3.0, 4.0] 85.0 # doctest: +SKIP
2 1 [1.0, 2.0] 145.0 # doctest: +SKIP
>>> table.delete("x = 2") # doctest: +SKIP
>>> table.search([10,10]).to_pandas() # doctest: +SKIP
x vector _distance # doctest: +SKIP
0 3 [5.0, 6.0] 41.0 # doctest: +SKIP
1 1 [1.0, 2.0] 145.0 # doctest: +SKIP
If you have a list of values to delete, you can combine them into a
stringified list and use the `IN` operator:
>>> to_remove = [1, 3] # doctest: +SKIP
>>> to_remove = ", ".join([str(v) for v in to_remove]) # doctest: +SKIP
>>> table.delete(f"x IN ({to_remove})") # doctest: +SKIP
>>> table.search([10,10]).to_pandas() # doctest: +SKIP
x vector _distance # doctest: +SKIP
0 2 [3.0, 4.0] 85.0 # doctest: +SKIP
"""
LOOP.run(self._table.delete(predicate))
def update(
self,
where: Optional[str] = None,
values: Optional[dict] = None,
*,
values_sql: Optional[Dict[str, str]] = None,
):
"""
This can be used to update zero to all rows depending on how many
rows match the where clause.
Parameters
----------
where: str, optional
The SQL where clause to use when updating rows. For example, 'x = 2'
or 'x IN (1, 2, 3)'. The filter must not be empty, or it will error.
values: dict, optional
The values to update. The keys are the column names and the values
are the values to set.
values_sql: dict, optional
The values to update, expressed as SQL expression strings. These can
reference existing columns. For example, {"x": "x + 1"} will increment
the x column by 1.
Examples
--------
>>> import lancedb
>>> data = [
... {"x": 1, "vector": [1, 2]},
... {"x": 2, "vector": [3, 4]},
... {"x": 3, "vector": [5, 6]}
... ]
>>> db = lancedb.connect("db://...", api_key="...", # doctest: +SKIP
... region="...") # doctest: +SKIP
>>> table = db.create_table("my_table", data) # doctest: +SKIP
>>> table.to_pandas() # doctest: +SKIP
x vector # doctest: +SKIP
0 1 [1.0, 2.0] # doctest: +SKIP
1 2 [3.0, 4.0] # doctest: +SKIP
2 3 [5.0, 6.0] # doctest: +SKIP
>>> table.update(where="x = 2", values={"vector": [10, 10]}) # doctest: +SKIP
>>> table.to_pandas() # doctest: +SKIP
x vector # doctest: +SKIP
0 1 [1.0, 2.0] # doctest: +SKIP
1 3 [5.0, 6.0] # doctest: +SKIP
2 2 [10.0, 10.0] # doctest: +SKIP
"""
LOOP.run(
self._table.update(where=where, updates=values, updates_sql=values_sql)
)
def cleanup_old_versions(self, *_):
"""
cleanup_old_versions() is a no-op on LanceDB Cloud.
Tables are automatically cleaned up and optimized.
"""
warnings.warn(
"cleanup_old_versions() is a no-op on LanceDB Cloud. "
"Tables are automatically cleaned up and optimized."
)
pass
def compact_files(self, *_):
"""
compact_files() is a no-op on LanceDB Cloud.
Tables are automatically compacted and optimized.
"""
warnings.warn(
"compact_files() is a no-op on LanceDB Cloud. "
"Tables are automatically compacted and optimized."
)
pass
def optimize(
self,
*,
cleanup_older_than: Optional[timedelta] = None,
delete_unverified: bool = False,
):
"""
optimize() is a no-op on LanceDB Cloud.
Indices are optimized automatically.
"""
warnings.warn(
"optimize() is a no-op on LanceDB Cloud. "
"Indices are optimized automatically."
)
pass
def count_rows(self, filter: Optional[str] = None) -> int:
return LOOP.run(self._table.count_rows(filter))
def add_columns(self, transforms: Dict[str, str]):
return LOOP.run(self._table.add_columns(transforms))
def alter_columns(self, *alterations: Iterable[Dict[str, str]]):
return LOOP.run(self._table.alter_columns(*alterations))
def drop_columns(self, columns: Iterable[str]):
return LOOP.run(self._table.drop_columns(columns))
def uses_v2_manifest_paths(self) -> bool:
raise NotImplementedError(
"uses_v2_manifest_paths() is not supported on the LanceDB Cloud"
)
def migrate_v2_manifest_paths(self):
raise NotImplementedError(
"migrate_v2_manifest_paths() is not supported on the LanceDB Cloud"
)
def add_index(tbl: pa.Table, i: int) -> pa.Table:
return tbl.add_column(
0,
pa.field("query_index", pa.uint32()),
pa.array([i] * len(tbl), pa.uint32()),
)