Commit Graph

1112 Commits

Author SHA1 Message Date
Ayush Chaurasia
513926960d docs: add rrf docs and update reranking notebook with Jina reranker results (#1474)
- RRF reranker
- Jina Reranker results

---------

Co-authored-by: Weston Pace <weston.pace@gmail.com>
2024-07-25 22:29:46 +05:30
inn-0
cc507ca766 docs: add missing whitespace before markdown table to fix rendering issue (#1471)
### Fix markdown table rendering issue

This PR adds a missing whitespace before a markdown table in the
documentation. This issue causes the table to not render properly in
mkdocs, while it does render properly in GitHub's markdown viewer.

#### Change Details:
- Added a single line of whitespace before the markdown table to ensure
proper rendering in mkdocs.

#### Note:
- I wasn't able to test this fix in the mkdocs environment, but it
should be safe as it only involves adding whitespace which won't break
anything.


---


Cohere supports following input types:

| Input Type               | Description                          |
|-------------------------|---------------------------------------|
| "`search_document`"     | Used for embeddings stored in a vector|
|                         | database for search use-cases.        |
| "`search_query`"        | Used for embeddings of search queries |
|                         | run against a vector DB               |
| "`semantic_similarity`" | Specifies the given text will be used |
|                         | for Semantic Textual Similarity (STS) |
| "`classification`"      | Used for embeddings passed through a  |
|                         | text classifier.                      |
| "`clustering`"          | Used for the embeddings run through a |
|                         | clustering algorithm                  |

Usage Example:
2024-07-24 22:26:28 +05:30
Cory Grinstead
492d0328fe chore: update readme to point to lancedb package (#1470) 2024-07-23 13:46:32 -07:00
Chang She
374c1e7aba fix: infer schema from huggingface dataset (#1444)
Closes #1383

When creating a table from a HuggingFace dataset, infer the arrow schema
directly
2024-07-23 13:12:34 -07:00
Gagan Bhullar
30047a5566 fix: remove source .ts code from published npm package (#1467)
This PR is for issue - https://github.com/lancedb/lancedb/issues/1358
2024-07-23 13:11:54 -07:00
Bert
85ccf9e22b feat!: correct timeout argument lancedb nodejs sdk (#1468)
Correct the timeout argument to `connect` in @lancedb/lancedb node SDK.
`RemoteConnectionOptions` specified two fields `connectionTimeout` and
`readTimeout`, probably to be consistent with the python SDK, but only
`connectionTimeout` was being used and it was passed to axios in such a
way that this covered the enture remote request (connect + read). This
change adds a single parameter `timeout` which makes the args to
`connect` consistent with the legacy vectordb sdk.

BREAKING CHANGE: This is a breaking change b/c users who would have
previously been passing `connectionTimeout` will now be expected to pass
`timeout`.
2024-07-23 14:02:46 -03:00
Ayush Chaurasia
0255221086 feat: add reciprocal rank fusion reranker (#1456)
Implements https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf

Refactors the hybrid search only rerrankers test to avoid repetition.
2024-07-23 21:37:17 +05:30
Lance Release
4ee229490c Updating package-lock.json 2024-07-23 13:49:13 +00:00
Lance Release
93e24f23af Bump version: 0.7.2-beta.0 → 0.7.2 v0.7.2 2024-07-23 13:48:58 +00:00
Lance Release
8f141e1e33 Bump version: 0.7.1 → 0.7.2-beta.0 2024-07-23 13:48:58 +00:00
Lance Release
1d5da1d069 Bump version: 0.10.2-beta.0 → 0.10.2 python-v0.10.2 2024-07-23 13:48:48 +00:00
Lance Release
0c0ec1c404 Bump version: 0.10.1 → 0.10.2-beta.0 2024-07-23 13:48:47 +00:00
Weston Pace
d4aad82aec fix: don't use v2 by default on empty table (#1469) 2024-07-23 06:47:49 -07:00
Will Jones
4f601a2d4c fix: handle camelCase column names in select (#1460)
Fixes #1385
2024-07-22 12:53:17 -07:00
Cory Grinstead
391fa26175 feat(rust): huggingface sentence-transformers (#1447)
Co-authored-by: Will Jones <willjones127@gmail.com>
2024-07-22 13:47:57 -05:00
Lei Xu
c9c61eb060 docs: expose merge_insert doc for remote python SDK (#1464)
`merge_insert` API is not shown up on
[`RemoteTable`](https://lancedb.github.io/lancedb/python/saas-python/#lancedb.remote.table.RemoteTable)
today

* Also bump `ruff` version as well
2024-07-22 10:48:16 -07:00
Cory Grinstead
69295548cc docs: minor updates for js migration guides (#1451)
Co-authored-by: Will Jones <willjones127@gmail.com>
2024-07-22 10:26:49 -07:00
Cory Grinstead
2276b114c5 docs: add installation note about yarn (#1459)
I noticed that setting up a simple project with
[Yarn](https://yarnpkg.com/) failed because unlike others [npm, pnpm,
bun], yarn does not automatically resolve peer dependencies, so i added
a quick note about it in the installation guide.
2024-07-19 18:48:24 -05:00
Cory Grinstead
3b88f15774 fix(nodejs): lancedb arrow dependency (#1458)
previously if you tried to install both vectordb and @lancedb/lancedb,
you would get a peer dependency issue due to `vectordb` requiring
`14.0.2` and `@lancedb/lancedb` requiring `15.0.0`. now
`@lancedb/lancedb` should just work with any arrow version 13-17
2024-07-19 11:21:55 -05:00
Ayush Chaurasia
ed7bd45c17 chore: choose appropriate args for concat_table based on pyarrow version & refactor reranker tests (#1455) 2024-07-18 21:04:59 +05:30
Magnus
dc609a337d fix: added support for trust_remote_code (#1454)
Closes #1285 

Added trust_remote_code to the SentenceTransformerEmbeddings class.
Defaults to `False`
2024-07-18 19:37:52 +05:30
Will Jones
d564f6eacb ci: fix vectordb release process (#1450)
* Labelled jobs `vectordb` and `lancedb` so it's clear which package
they are for
* Fix permission issue in aarch64 Linux `vectordb` build that has been
blocking release for two months.
* Added Slack notifications for failure of these publish jobs.
v0.7.1
2024-07-17 11:17:33 -07:00
Lance Release
ed5d1fb557 Updating package-lock.json 2024-07-17 14:04:56 +00:00
Lance Release
85046a1156 Bump version: 0.7.1-beta.0 → 0.7.1 2024-07-17 14:04:45 +00:00
Lance Release
b67689e1be Bump version: 0.7.0 → 0.7.1-beta.0 2024-07-17 14:04:45 +00:00
Lance Release
2c36767f20 Bump version: 0.10.1-beta.0 → 0.10.1 python-v0.10.1 2024-07-17 14:04:40 +00:00
Lance Release
1fa7e96aa1 Bump version: 0.10.0 → 0.10.1-beta.0 2024-07-17 14:04:39 +00:00
Cory Grinstead
7ae327242b docs: update migration.md (#1445) 2024-07-15 18:20:23 -05:00
Bert
1f4a051070 feat: make timeout configurable for vectordb node SDK (#1443) 2024-07-15 13:23:13 -02:30
Lance Release
92c93b08bf Updating package-lock.json 2024-07-13 08:56:11 +00:00
Lance Release
a363b02ca7 Bump version: 0.7.0-beta.0 → 0.7.0 v0.7.0 2024-07-13 08:55:44 +00:00
Lance Release
ff8eaab894 Bump version: 0.6.0 → 0.7.0-beta.0 2024-07-13 08:55:44 +00:00
Lance Release
11959cc5d6 Bump version: 0.10.0-beta.0 → 0.10.0 python-v0.10.0 2024-07-13 08:55:22 +00:00
Lance Release
7c65cec8d7 Bump version: 0.9.0 → 0.10.0-beta.0 2024-07-13 08:55:22 +00:00
Adam Azzam
82621d5b13 chore: typing for lance.connect (#1441)
Feel free to close if this is a distraction, but untyped keywords in
lance.connect is throwing pylance errors in strict mode.

<img width="683" alt="Screenshot 2024-07-11 at 1 21 04 PM"
src="https://github.com/lancedb/lancedb/assets/33043305/fe6cd4d9-4e59-413d-87f2-aabb9ff84cc4">
2024-07-12 10:39:28 -07:00
Lei Xu
0708428357 feat: support update over binary field (#1440) 2024-07-12 09:22:00 -07:00
BubbleCal
137d86d3c5 chore: bump lance to 0.14.1 (#1442)
Signed-off-by: BubbleCal <bubble-cal@outlook.com>
2024-07-12 21:41:59 +08:00
Ayush Chaurasia
bb2e624ff0 docs: add fine tuning section in retriever guide and minor fixes (#1438) 2024-07-11 17:34:29 +05:30
Cory Grinstead
fdc949bafb feat(nodejs): update({values | valuesSql}) (#1439) 2024-07-10 14:09:39 -05:00
Cory Grinstead
31be9212da docs(nodejs): add @lancedb/lancedb examples everywhere (#1411)
Co-authored-by: Will Jones <willjones127@gmail.com>
2024-07-10 13:29:03 -05:00
Joan Fontanals
cef24801f4 docs: add jina reranker to index (#1427)
PR to add JinaReranker documentation page to the rerankers index
2024-07-09 14:39:35 +05:30
forrestmckee
b4436e0804 refactor: update type hint and remove unused import (#1436)
change typehint on `_invert_score` from `List[float]` to `float`. remove
unnecessary typing import
2024-07-09 13:56:45 +05:30
Lei Xu
58c2cd01a5 docs: add fast search to openapi.yml (#1435) 2024-07-08 11:55:45 -07:00
Cory Grinstead
a1a1891c0c fix(nodejs): explain plan (#1434) 2024-07-08 13:07:24 -05:00
Lei Xu
3c6c21c137 feat(rust): enable fast search flag in rust (#1432) 2024-07-07 09:46:41 -07:00
Lei Xu
fd5ca20f34 chore: bump lance to 0.14 (#1430) 2024-07-06 14:10:42 -07:00
Lei Xu
ef30f87fd1 chore: propagate error for table index stats (#1426) 2024-07-04 14:53:49 -07:00
Joan Fontanals
08d25c5a80 feat: add Jina integration in Python for Embedding and Reranker (#1424)
Integration of Jina Embeddings and Rerankers through its API
2024-07-05 01:34:43 +05:30
Raghav Dixit
a5ff623443 docs: update lntegration docs & fixed links (#1423)
1. Updated langchain docs. 
2. Minor update to llamaindex doc.
3. Added notebook examples and linked them correctly
2024-07-03 21:50:33 +05:30
Cory Grinstead
b8ccea9f71 feat(nodejs): make tbl.search chainable (#1421)
so this was annoying me when writing the docs. 

for a `search` query, one needed to chain `async` calls.

```ts
const res = await (await tbl.search("greetings")).toArray()
```

now the promise will be deferred until the query is collected, leading
to a more functional API

```ts
const res = await tbl.search("greetings").toArray()
```
2024-07-02 14:31:57 -05:00