This reverts commit a547c523c2 or #2281
The current implementation can cause panics and performance degradation.
I will bring this back with more testing in
https://github.com/lancedb/lancedb/pull/2311
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
- **Documentation**
- Enhanced clarity on read consistency settings with updated
descriptions and default behavior.
- Removed outdated warnings about eventual consistency from the
troubleshooting guide.
- **Refactor**
- Streamlined the handling of the read consistency interval across
integrations, now defaulting to "None" for improved performance.
- Simplified internal logic to offer a more consistent experience.
- **Tests**
- Updated test expectations to reflect the new default representation
for the read consistency interval.
- Removed redundant tests related to "no consistency" settings for
streamlined testing.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Previously, when we loaded the next version of the table, we would block
all reads with a write lock. Now, we only do that if
`read_consistency_interval=0`. Otherwise, we load the next version
asynchronously in the background. This should mean that
`read_consistency_interval > 0` won't have a meaningful impact on
latency.
Along with this change, I felt it was safe to change the default
consistency interval to 5 seconds. The current default is `None`, which
means we will **never** check for a new version by default. I think that
default is contrary to most users expectations.
BREAKING CHANGE: the return value of `index_stats` method has changed
and all `index_stats` APIs now take index name instead of UUID. Also
several deprecated index statistics methods were removed.
* Removes deprecated methods for individual index statistics
* Aligns public `IndexStatistics` struct with API response from LanceDB
Cloud.
* Implements `index_stats` for remote Rust SDK and Python async API.
- changed the error msg for table.search with wrong query vector dim
- added missing fields for listIndices and indexStats to be consistent
with Python API - will make changes in node integ test
Fixes issue where we would throw `Either data or schema needs to
defined` when passing `data` to `createTable` as a property of the first
argument (an object).
```ts
await db.createTable({
name: 'table1',
data,
schema
})
```
Exposes `storage_options` in LanceDB. This is provided for Python async,
Node `lancedb`, and Node `vectordb` (and Rust of course). Python
synchronous is omitted because it's not compatible with the PyArrow
filesystems we use there currently. In the future, we will move the sync
API to wrap the async one, and then it will get support for
`storage_options`.
1. Fixes#1168
2. Closes#1165
3. Closes#1082
4. Closes#439
5. Closes#897
6. Closes#642
7. Closes#281
8. Closes#114
9. Closes#990
10. Deprecating `awsCredentials` and `awsRegion`. Users are encouraged
to use `storageOptions` instead.
- make open table behaviour consistent:
- remote tables will check if the table exists by calling /describe and
throwing an error if the call doesn't succeed
- this is similar to the behaviour for local tables where we will raise
an exception when opening the table if the local dataset doesn't exist
- The table names are cached in the client with a TTL
- Also fixes a small bug where if the remote error response was
deserialized from JSON as an object, we'd print it resulting in the
unhelpful error message: `Error: Server Error, status: 404, message: Not
Found: [object Object]`
This prevents an issue where users can do something like:
```js
db.createTable('my-table#123123')
```
The server has logic to determine that '#' character is not allowed in
the table name, but currently this is being returned as 404 error
because it routes to `/v1/my-table#123123/create` and `#123123/create`
will not be parsed as part of path
In Rust and Node, we have been swallowing filter validation errors. If
there was an error in parsing the filter, then the filter was silently
ignored, returning unfiltered results.
Fixes#1081
Arrow-js uses brittle `instanceof` checks throughout the code base.
These fail unless the library instance that produced the object matches
exactly the same instance the vectordb is using. At a minimum, this
means that a user using arrow version 15 (or any version that doesn't
match exactly the version that vectordb is using) will get strange
errors when they try and use vectordb.
However, there are even cases where the versions can be perfectly
identical, and the instanceof check still fails. One such example is
when using `vite` (e.g. https://github.com/vitejs/vite/issues/3910)
This PR solves the problem in a rather brute force, but workable,
fashion. If we encounter a schema that does not pass the `instanceof`
check then we will attempt to sanitize that schema by traversing the
object and, if it has all the correct properties, constructing an
appropriate `Schema` instance via deep cloning.
This PR adds the same consistency semantics as was added in #828. It
*does not* add the same lazy-loading of tables, since that breaks some
existing tests.
This closes#998.
---------
Co-authored-by: Weston Pace <weston.pace@gmail.com>
This PR also reworks the table creation utilities significantly so that
they are more consistent, built on top of each other, and thoroughly
documented.
A `count_rows` method that takes a filter was recently added to
`LanceTable`. This PR adds it everywhere else except `RemoteTable` (that
will come soon).
Allow passing API key as env var:
```shell
export LANCEDB_API_KEY=sh_123...
```
with this set, apiKey argument can omitted from `connect`
```js
const db = await vectordb.connect({
uri: "db://test-proj-01-ae8343",
region: "us-east-1",
})
```
```py
db = lancedb.connect(
uri="db://test-proj-01-ae8343",
region="us-east-1",
)
```
