[python] Bump version: 0.1.12 → 0.1.13

Support both Pydantic v1 and v2 (breaking changes)

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.1.14
+current_version = 0.1.15
 commit = True
 message = Bump version: {current_version} → {new_version}
 tag = True

Cargo.toml

@@ -11,6 +11,6 @@ arrow-array = "42.0"
 arrow-data = "42.0"
 arrow-schema = "42.0"
 arrow-ipc = "42.0"
-half = { "version" = "2.2.1", default-features = false }
+half = { "version" = "=2.2.1", default-features = false }
 object_store = "0.6.1"
 

node/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "vectordb",
-  "version": "0.1.14",
+  "version": "0.1.15",
   "lockfileVersion": 2,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.1.14",
+      "version": "0.1.15",
       "cpu": [
         "x64",
         "arm64"
@@ -51,11 +51,11 @@
         "typescript": "*"
       },
       "optionalDependencies": {
-        "vectordb-darwin-arm64": "0.1.14",
-        "vectordb-darwin-x64": "0.1.14",
-        "vectordb-linux-arm64-gnu": "0.1.14",
-        "vectordb-linux-x64-gnu": "0.1.14",
-        "vectordb-win32-x64-msvc": "0.1.14"
+        "vectordb-darwin-arm64": "0.1.15",
+        "vectordb-darwin-x64": "0.1.15",
+        "vectordb-linux-arm64-gnu": "0.1.15",
+        "vectordb-linux-x64-gnu": "0.1.15",
+        "vectordb-win32-x64-msvc": "0.1.15"
       }
     },
     "node_modules/@apache-arrow/ts": {
@@ -4297,42 +4297,6 @@
       "integrity": "sha512-wa7YjyUGfNZngI/vtK0UHAN+lgDCxBPCylVXGp0zu59Fz5aiGtNXaq3DhIov063MorB+VfufLh3JlF2KdTK3xg==",
       "dev": true
     },
-    "node_modules/vectordb-darwin-arm64": {
-      "version": "0.1.14",
-      "resolved": "https://registry.npmjs.org/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.1.14.tgz",
-      "integrity": "sha512-5doSFMUR4scxseo73thCxScmO3Wpb+cqPsIa7+2uneTEtBSViMbkw/1mGTC+rV4NTCnxhoiqHk9pJzZVeDMkPg==",
-      "cpu": [
-        "arm64"
-      ],
-      "optional": true,
-      "os": [
-        "darwin"
-      ]
-    },
-    "node_modules/vectordb-darwin-x64": {
-      "version": "0.1.14",
-      "resolved": "https://registry.npmjs.org/vectordb-darwin-x64/-/vectordb-darwin-x64-0.1.14.tgz",
-      "integrity": "sha512-x+qVaKNhAG65HdENL6GRJjxl1hZ7erRm3a2rhplyYoQyzuRPPBILeWzxkE01G1fb0+47dehe7Q4f/8BDaghcCQ==",
-      "cpu": [
-        "x64"
-      ],
-      "optional": true,
-      "os": [
-        "darwin"
-      ]
-    },
-    "node_modules/vectordb-linux-x64-gnu": {
-      "version": "0.1.14",
-      "resolved": "https://registry.npmjs.org/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.1.14.tgz",
-      "integrity": "sha512-hvA2YYwTZK92k6nPH99Jn5N0CwagDOdnwMmjtCpzFOEYK7dY/2kcTOoQNlBwwNP9MYvgN6jdFD/Cwkih1X/qjA==",
-      "cpu": [
-        "x64"
-      ],
-      "optional": true,
-      "os": [
-        "linux"
-      ]
-    },
     "node_modules/vscode-oniguruma": {
       "version": "1.7.0",
       "resolved": "https://registry.npmjs.org/vscode-oniguruma/-/vscode-oniguruma-1.7.0.tgz",
@@ -7638,24 +7602,6 @@
       "integrity": "sha512-wa7YjyUGfNZngI/vtK0UHAN+lgDCxBPCylVXGp0zu59Fz5aiGtNXaq3DhIov063MorB+VfufLh3JlF2KdTK3xg==",
       "dev": true
     },
-    "vectordb-darwin-arm64": {
-      "version": "0.1.14",
-      "resolved": "https://registry.npmjs.org/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.1.14.tgz",
-      "integrity": "sha512-5doSFMUR4scxseo73thCxScmO3Wpb+cqPsIa7+2uneTEtBSViMbkw/1mGTC+rV4NTCnxhoiqHk9pJzZVeDMkPg==",
-      "optional": true
-    },
-    "vectordb-darwin-x64": {
-      "version": "0.1.14",
-      "resolved": "https://registry.npmjs.org/vectordb-darwin-x64/-/vectordb-darwin-x64-0.1.14.tgz",
-      "integrity": "sha512-x+qVaKNhAG65HdENL6GRJjxl1hZ7erRm3a2rhplyYoQyzuRPPBILeWzxkE01G1fb0+47dehe7Q4f/8BDaghcCQ==",
-      "optional": true
-    },
-    "vectordb-linux-x64-gnu": {
-      "version": "0.1.14",
-      "resolved": "https://registry.npmjs.org/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.1.14.tgz",
-      "integrity": "sha512-hvA2YYwTZK92k6nPH99Jn5N0CwagDOdnwMmjtCpzFOEYK7dY/2kcTOoQNlBwwNP9MYvgN6jdFD/Cwkih1X/qjA==",
-      "optional": true
-    },
     "vscode-oniguruma": {
       "version": "1.7.0",
       "resolved": "https://registry.npmjs.org/vscode-oniguruma/-/vscode-oniguruma-1.7.0.tgz",

node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vectordb",
-  "version": "0.1.14",
+  "version": "0.1.15",
   "description": " Serverless, low-latency vector database for AI applications",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -78,10 +78,10 @@
     }
   },
   "optionalDependencies": {
-    "vectordb-darwin-arm64": "0.1.14",
-    "vectordb-darwin-x64": "0.1.14",
-    "vectordb-linux-arm64-gnu": "0.1.14",
-    "vectordb-linux-x64-gnu": "0.1.14",
-    "vectordb-win32-x64-msvc": "0.1.14"
+    "vectordb-darwin-arm64": "0.1.15",
+    "vectordb-darwin-x64": "0.1.15",
+    "vectordb-linux-arm64-gnu": "0.1.15",
+    "vectordb-linux-x64-gnu": "0.1.15",
+    "vectordb-win32-x64-msvc": "0.1.15"
   }
 }

node/src/index.ts

@@ -44,6 +44,9 @@ export interface ConnectionOptions {
   apiKey?: string
   // Region to connect
   region?: string
+
+  // override the host for the remote connections
+  hostOverride?: string
 }
 
 /**

node/src/remote/client.ts

@@ -19,7 +19,11 @@ import { tableFromIPC, type Table as ArrowTable } from 'apache-arrow'
 export class HttpLancedbClient {
   private readonly _url: string
 
-  public constructor (url: string, private readonly _apiKey: string) {
+  public constructor (
+    url: string,
+    private readonly _apiKey: string,
+    private readonly _dbName?: string
+  ) {
     this._url = url
   }
 
@@ -49,7 +53,8 @@ export class HttpLancedbClient {
               {
                 headers: {
                   'Content-Type': 'application/json',
-                  'x-api-key': this._apiKey
+                  'x-api-key': this._apiKey,
+                  ...(this._dbName !== undefined ? { 'x-lancedb-database': this._dbName } : {})
                 },
                 responseType: 'arraybuffer',
                 timeout: 10000

node/src/remote/index.ts

@@ -37,8 +37,13 @@ export class RemoteConnection implements Connection {
     }
 
     this._dbName = opts.uri.slice('db://'.length)
-    const server = `https://${this._dbName}.${opts.region}.api.lancedb.com`
-    this._client = new HttpLancedbClient(server, opts.apiKey)
+    let server: string
+    if (opts.hostOverride === undefined) {
+      server = `https://${this._dbName}.${opts.region}.api.lancedb.com`
+    } else {
+      server = opts.hostOverride
+    }
+    this._client = new HttpLancedbClient(server, opts.apiKey, opts.hostOverride === undefined ? undefined : this._dbName)
   }
 
   get uri (): string {

python/.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.1.12
+current_version = 0.1.13
 commit = True
 message = [python] Bump version: {current_version} → {new_version}
 tag = True

python/lancedb/pydantic.py

@@ -11,7 +11,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 
-"""Pydantic adapter for LanceDB"""
+"""Pydantic (v1 / v2) adapter for LanceDB"""
 
 from __future__ import annotations
 
@@ -19,11 +19,19 @@ import inspect
 import sys
 import types
 from abc import ABC, abstractmethod
-from typing import Any, List, Type, Union, _GenericAlias
+from typing import Any, Callable, Dict, Generator, List, Type, Union, _GenericAlias
 
+import numpy as np
 import pyarrow as pa
 import pydantic
-from pydantic_core import CoreSchema, core_schema
+import semver
+
+PYDANTIC_VERSION = semver.Version.parse(pydantic.__version__)
+try:
+    from pydantic_core import CoreSchema, core_schema
+except ImportError:
+    if PYDANTIC_VERSION >= (2,):
+        raise
 
 
 class FixedSizeListMixin(ABC):
@@ -73,6 +81,9 @@ def vector(
 
     # TODO: make a public parameterized type.
     class FixedSizeList(list, FixedSizeListMixin):
+        def __repr__(self):
+            return f"FixedSizeList(dim={dim})"
+
         @staticmethod
         def dim() -> int:
             return dim
@@ -94,6 +105,25 @@ def vector(
                 ),
             )
 
+        @classmethod
+        def __get_validators__(cls) -> Generator[Callable, None, None]:
+            yield cls.validate
+
+        # For pydantic v1
+        @classmethod
+        def validate(cls, v):
+            if not isinstance(v, (list, range, np.ndarray)) or len(v) != dim:
+                raise TypeError("A list of numbers or numpy.ndarray is needed")
+            return v
+
+        if PYDANTIC_VERSION < (2, 0):
+
+            @classmethod
+            def __modify_schema__(cls, field_schema: Dict[str, Any]):
+                field_schema["items"] = {"type": "number"}
+                field_schema["maxItems"] = dim
+                field_schema["minItems"] = dim
+
     return FixedSizeList
 
 
@@ -120,11 +150,20 @@ def _py_type_to_arrow_type(py_type: Type[Any]) -> pa.DataType:
     )
 
 
-def _pydantic_model_to_fields(model: pydantic.BaseModel) -> List[pa.Field]:
-    fields = []
-    for name, field in model.model_fields.items():
-        fields.append(_pydantic_to_field(name, field))
-    return fields
+if PYDANTIC_VERSION.major < 2:
+
+    def _pydantic_model_to_fields(model: pydantic.BaseModel) -> List[pa.Field]:
+        return [
+            _pydantic_to_field(name, field) for name, field in model.__fields__.items()
+        ]
+
+else:
+
+    def _pydantic_model_to_fields(model: pydantic.BaseModel) -> List[pa.Field]:
+        return [
+            _pydantic_to_field(name, field)
+            for name, field in model.model_fields.items()
+        ]
 
 
 def _pydantic_to_arrow_type(field: pydantic.fields.FieldInfo) -> pa.DataType:

python/pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "lancedb"
-version = "0.1.12"
-dependencies = ["pylance~=0.5.8", "ratelimiter", "retry", "tqdm", "aiohttp", "pydantic>=2", "attr"]
+version = "0.1.13"
+dependencies = ["pylance~=0.5.8", "ratelimiter", "retry", "tqdm", "aiohttp", "pydantic", "attr", "semver"]
 description = "lancedb"
 authors = [
     { name = "LanceDB Devs", email = "dev@lancedb.com" },
@@ -52,3 +52,6 @@ requires = [
   "wheel",
 ]
 build-backend = "setuptools.build_meta"
+
+[tool.isort]
+profile = "black"

python/tests/test_pydantic.py

@@ -20,7 +20,7 @@ import pyarrow as pa
 import pydantic
 import pytest
 
-from lancedb.pydantic import pydantic_to_schema, vector
+from lancedb.pydantic import PYDANTIC_VERSION, pydantic_to_schema, vector
 
 
 @pytest.mark.skipif(
@@ -111,10 +111,16 @@ def test_fixed_size_list_field():
         li: List[int]
 
     data = TestModel(vec=list(range(16)), li=[1, 2, 3])
-    assert json.loads(data.model_dump_json()) == {
-        "vec": list(range(16)),
-        "li": [1, 2, 3],
-    }
+    if PYDANTIC_VERSION >= (2,):
+        assert json.loads(data.model_dump_json()) == {
+            "vec": list(range(16)),
+            "li": [1, 2, 3],
+        }
+    else:
+        assert data.dict() == {
+            "vec": list(range(16)),
+            "li": [1, 2, 3],
+        }
 
     schema = pydantic_to_schema(TestModel)
     assert schema == pa.schema(
@@ -124,7 +130,11 @@ def test_fixed_size_list_field():
         ]
     )
 
-    json_schema = TestModel.model_json_schema()
+    if PYDANTIC_VERSION >= (2,):
+        json_schema = TestModel.model_json_schema()
+    else:
+        json_schema = TestModel.schema()
+
     assert json_schema == {
         "properties": {
             "vec": {

rust/ffi/node/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "vectordb-node"
-version = "0.1.14"
+version = "0.1.15"
 description = "Serverless, low-latency vector database for AI applications"
 license = "Apache-2.0"
 edition = "2018"

rust/vectordb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "vectordb"
-version = "0.1.14"
+version = "0.1.15"
 edition = "2021"
 description = "Serverless, low-latency vector database for AI applications"
 license = "Apache-2.0"