mirror of
https://github.com/lancedb/lancedb.git
synced 2026-01-12 23:02:59 +00:00
282 lines
9.4 KiB
Python
282 lines
9.4 KiB
Python
# Copyright 2023 LanceDB Developers
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import uuid
|
|
from functools import cached_property
|
|
from typing import Optional, Union
|
|
|
|
import pyarrow as pa
|
|
from lance import json_to_schema
|
|
|
|
from lancedb.common import DATA, VEC, VECTOR_COLUMN_NAME
|
|
|
|
from ..query import LanceVectorQueryBuilder
|
|
from ..table import Query, Table, _sanitize_data
|
|
from .arrow import to_ipc_binary
|
|
from .client import ARROW_STREAM_CONTENT_TYPE
|
|
from .db import RemoteDBConnection
|
|
|
|
|
|
class RemoteTable(Table):
|
|
def __init__(self, conn: RemoteDBConnection, name: str):
|
|
self._conn = conn
|
|
self._name = name
|
|
|
|
def __repr__(self) -> str:
|
|
return f"RemoteTable({self._conn.db_name}.{self._name})"
|
|
|
|
@cached_property
|
|
def schema(self) -> pa.Schema:
|
|
"""The [Arrow Schema](https://arrow.apache.org/docs/python/api/datatypes.html#)
|
|
of this Table
|
|
|
|
"""
|
|
resp = self._conn._loop.run_until_complete(
|
|
self._conn._client.post(f"/v1/table/{self._name}/describe/")
|
|
)
|
|
schema = json_to_schema(resp["schema"])
|
|
return schema
|
|
|
|
@property
|
|
def version(self) -> int:
|
|
"""Get the current version of the table"""
|
|
resp = self._conn._loop.run_until_complete(
|
|
self._conn._client.post(f"/v1/table/{self._name}/describe/")
|
|
)
|
|
return resp["version"]
|
|
|
|
def to_arrow(self) -> pa.Table:
|
|
"""to_arrow() is not supported on the LanceDB cloud
|
|
|
|
"""
|
|
raise NotImplementedError("to_arrow() is not supported on the LanceDB cloud")
|
|
|
|
def to_pandas(self):
|
|
"""to_pandas() is not supported on the LanceDB cloud
|
|
|
|
"""
|
|
return NotImplementedError("to_pandas() is not supported on the LanceDB cloud")
|
|
|
|
def create_index(
|
|
self,
|
|
metric="L2",
|
|
vector_column_name: str = VECTOR_COLUMN_NAME,
|
|
index_cache_size: Optional[int] = None,
|
|
):
|
|
"""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
|
|
>>> conn = lancedb.connect("db://...", api_key="...", region="...")
|
|
>>> 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 = conn.create_table(
|
|
>>> table_name,
|
|
>>> schema=schema,
|
|
>>> )
|
|
>>> table.create_index("L2", "vector")
|
|
"""
|
|
index_type = "vector"
|
|
|
|
data = {
|
|
"column": vector_column_name,
|
|
"index_type": index_type,
|
|
"metric_type": metric,
|
|
"index_cache_size": index_cache_size,
|
|
}
|
|
resp = self._conn._loop.run_until_complete(
|
|
self._conn._client.post(f"/v1/table/{self._name}/create_index/", data=data)
|
|
)
|
|
return resp
|
|
|
|
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".
|
|
|
|
"""
|
|
data = _sanitize_data(
|
|
data,
|
|
self.schema,
|
|
metadata=None,
|
|
on_bad_vectors=on_bad_vectors,
|
|
fill_value=fill_value,
|
|
)
|
|
payload = to_ipc_binary(data)
|
|
|
|
request_id = uuid.uuid4().hex
|
|
|
|
self._conn._loop.run_until_complete(
|
|
self._conn._client.post(
|
|
f"/v1/table/{self._name}/insert/",
|
|
data=payload,
|
|
params={"request_id": request_id, "mode": mode},
|
|
content_type=ARROW_STREAM_CONTENT_TYPE,
|
|
)
|
|
)
|
|
|
|
def search(
|
|
self, query: Union[VEC, str], vector_column_name: str = VECTOR_COLUMN_NAME
|
|
) -> 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="...", region="...")
|
|
>>> 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)
|
|
>>> query = [0.4, 1.4, 2.4]
|
|
>>> (table.search(query, vector_column_name="vector")
|
|
... .where("original_width > 1000", prefilter=True)
|
|
... .select(["caption", "original_width"])
|
|
... .limit(2)
|
|
... .to_pandas())
|
|
caption original_width vector _distance
|
|
0 foo 2000 [0.5, 3.4, 1.3] 5.220000
|
|
1 test 3000 [0.3, 6.2, 2.6] 23.089996
|
|
|
|
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
|
|
|
|
- If None then the select/where/limit clauses are applied to filter
|
|
the table
|
|
vector_column_name: str
|
|
The name of the vector column to search.
|
|
*default "vector"*
|
|
|
|
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 LanceVectorQueryBuilder(self, query, vector_column_name)
|
|
|
|
def _execute_query(self, query: Query) -> pa.Table:
|
|
result = self._conn._client.query(self._name, query)
|
|
return self._conn._loop.run_until_complete(result).to_arrow()
|
|
|
|
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="...", region="...")
|
|
>>> table = db.create_table("my_table", data)
|
|
>>> table.search([10,10]).to_pandas()
|
|
x vector _distance
|
|
0 3 [5.0, 6.0] 41.0
|
|
1 2 [3.0, 4.0] 85.0
|
|
2 1 [1.0, 2.0] 145.0
|
|
>>> table.delete("x = 2")
|
|
>>> table.search([10,10]).to_pandas()
|
|
x vector _distance
|
|
0 3 [5.0, 6.0] 41.0
|
|
1 1 [1.0, 2.0] 145.0
|
|
|
|
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]
|
|
>>> to_remove = ", ".join([str(v) for v in to_remove])
|
|
>>> to_remove
|
|
'1, 3'
|
|
>>> table.delete(f"x IN ({to_remove})")
|
|
>>> table.search([10,10]).to_pandas()
|
|
x vector _distance
|
|
0 2 [3.0, 4.0] 85.0
|
|
"""
|
|
payload = {"predicate": predicate}
|
|
self._conn._loop.run_until_complete(
|
|
self._conn._client.post(f"/v1/table/{self._name}/delete/", data=payload)
|
|
)
|