format

Cargo.toml

@@ -20,11 +20,13 @@ keywords = ["lancedb", "lance", "database", "vector", "search"]
 categories = ["database-implementations"]
 
 [workspace.dependencies]
-lance = { "version" = "=0.13.0", "features" = ["dynamodb"] }
-lance-index = { "version" = "=0.13.0" }
-lance-linalg = { "version" = "=0.13.0" }
-lance-testing = { "version" = "=0.13.0" }
-lance-datafusion = { "version" = "=0.13.0" }
+lance = { "version" = "=0.12.2", "features" = [
+    "dynamodb",
+], git = "https://github.com/lancedb/lance.git", tag = "v0.12.2-beta.2" }
+lance-index = { "version" = "=0.12.2", git = "https://github.com/lancedb/lance.git", tag = "v0.12.2-beta.2" }
+lance-linalg = { "version" = "=0.12.2", git = "https://github.com/lancedb/lance.git", tag = "v0.12.2-beta.2" }
+lance-testing = { "version" = "=0.12.2", git = "https://github.com/lancedb/lance.git", tag = "v0.12.2-beta.2" }
+lance-datafusion = { "version" = "=0.12.2", git = "https://github.com/lancedb/lance.git", tag = "v0.12.2-beta.2" }
 # Note that this one does not include pyarrow
 arrow = { version = "51.0", optional = false }
 arrow-array = "51.0"

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.9.0-beta.3"
+current_version = "0.8.2"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.9.0-beta.3"
+version = "0.8.2"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true

python/pyproject.toml

@@ -3,7 +3,7 @@ name = "lancedb"
 # version in Cargo.toml
 dependencies = [
     "deprecation",
-    "pylance==0.13.0",
+    "pylance==0.12.2-beta.2",
     "ratelimiter~=1.0",
     "requests>=2.31.0",
     "retry>=0.9.2",
@@ -13,7 +13,6 @@ dependencies = [
     "packaging",
     "cachetools",
     "overrides>=0.7",
-    "urllib3==1.26.19"
 ]
 description = "lancedb"
 authors = [{ name = "LanceDB Devs", email = "dev@lancedb.com" }]

python/python/lancedb/__init__.py

@@ -35,7 +35,6 @@ def connect(
     host_override: Optional[str] = None,
     read_consistency_interval: Optional[timedelta] = None,
     request_thread_pool: Optional[Union[int, ThreadPoolExecutor]] = None,
-    storage_options: Optional[Dict[str, str]] = None,
     **kwargs,
 ) -> DBConnection:
     """Connect to a LanceDB database.
@@ -71,9 +70,6 @@ def connect(
         executor will be used for making requests. This is for LanceDB Cloud
         only and is only used when making batch requests (i.e., passing in
         multiple queries to the search method at once).
-    storage_options: dict, optional
-        Additional options for the storage backend. See available options at
-        https://lancedb.github.io/lancedb/guides/storage/
 
     Examples
     --------
@@ -109,16 +105,12 @@ def connect(
             region,
             host_override,
             request_thread_pool=request_thread_pool,
-            storage_options=storage_options,
             **kwargs,
         )
 
     if kwargs:
         raise ValueError(f"Unknown keyword arguments: {kwargs}")
-    return LanceDBConnection(
-        uri,
-        read_consistency_interval=read_consistency_interval,
-    )
+    return LanceDBConnection(uri, read_consistency_interval=read_consistency_interval)
 
 
 async def connect_async(

python/python/lancedb/remote/client.py

@@ -55,13 +55,11 @@ class RestfulLanceDBClient:
     region: str
     api_key: Credential
     host_override: Optional[str] = attrs.field(default=None)
-    db_prefix: Optional[str] = attrs.field(default=None)
 
     closed: bool = attrs.field(default=False, init=False)
 
     connection_timeout: float = attrs.field(default=120.0, kw_only=True)
     read_timeout: float = attrs.field(default=300.0, kw_only=True)
-    storage_options: Optional[Dict[str, str]] = attrs.field(default=None, kw_only=True)
 
     @functools.cached_property
     def session(self) -> requests.Session:
@@ -94,18 +92,6 @@ class RestfulLanceDBClient:
             headers["Host"] = f"{self.db_name}.{self.region}.api.lancedb.com"
         if self.host_override:
             headers["x-lancedb-database"] = self.db_name
-        if self.storage_options:
-            if self.storage_options.get("account_name") is not None:
-                headers["x-azure-storage-account-name"] = self.storage_options[
-                    "account_name"
-                ]
-            if self.storage_options.get("azure_storage_account_name") is not None:
-                headers["x-azure-storage-account-name"] = self.storage_options[
-                    "azure_storage_account_name"
-                ]
-        if self.db_prefix:
-            headers["x-lancedb-database-prefix"] = self.db_prefix
-
         return headers
 
     @staticmethod
@@ -259,6 +245,7 @@ def retry_adapter(options: Dict[str, Any]) -> HTTPAdapter:
             connect=connect_retries,
             read=read_retries,
             backoff_factor=backoff_factor,
+            backoff_jitter=backoff_jitter,
             status_forcelist=statuses,
             allowed_methods=methods,
         )

python/python/lancedb/remote/db.py

@@ -15,7 +15,7 @@ import inspect
 import logging
 import uuid
 from concurrent.futures import ThreadPoolExecutor
-from typing import Dict, Iterable, List, Optional, Union
+from typing import Iterable, List, Optional, Union
 from urllib.parse import urlparse
 
 from cachetools import TTLCache
@@ -44,25 +44,20 @@ class RemoteDBConnection(DBConnection):
         request_thread_pool: Optional[ThreadPoolExecutor] = None,
         connection_timeout: float = 120.0,
         read_timeout: float = 300.0,
-        storage_options: Optional[Dict[str, str]] = None,
     ):
         """Connect to a remote LanceDB database."""
         parsed = urlparse(db_url)
         if parsed.scheme != "db":
             raise ValueError(f"Invalid scheme: {parsed.scheme}, only accepts db://")
         self.db_name = parsed.netloc
-        prefix = parsed.path.lstrip("/")
-        self.db_prefix = None if not prefix else prefix
         self.api_key = api_key
         self._client = RestfulLanceDBClient(
             self.db_name,
             region,
             api_key,
             host_override,
-            self.db_prefix,
             connection_timeout=connection_timeout,
             read_timeout=read_timeout,
-            storage_options=storage_options,
         )
         self._request_thread_pool = request_thread_pool
         self._table_cache = TTLCache(maxsize=10000, ttl=300)

python/python/lancedb/rerankers/base.py

@@ -119,7 +119,9 @@ class Reranker(ABC):
         fts_results : pa.Table
             The results from the FTS search
         """
-        combined = pa.concat_tables([vector_results, fts_results], promote=True)
+        combined = pa.concat_tables(
+            [vector_results, fts_results], promote_options="default"
+        )
         row_id = combined.column("_rowid")
 
         # deduplicate

python/python/tests/test_table.py

@@ -735,7 +735,7 @@ def test_create_scalar_index(db):
     indices = table.to_lance().list_indices()
     assert len(indices) == 1
     scalar_index = indices[0]
-    assert scalar_index["type"] == "BTree"
+    assert scalar_index["type"] == "Scalar"
 
     # Confirm that prefiltering still works with the scalar index column
     results = table.search().where("x = 'c'").to_arrow()