Files
lancedb/docs/web/integrations/reranking/watsonx.mdx
T
Jack YeandClaude Sonnet 5 de95ed3f6d docs: overhaul curation, feature engineering, security and deployment guides (#4748)
A broad documentation pass across the areas LanceDB Enterprise and
Embedded
diverge on most:

**Data Curation** -- GPU Function execution, Slurm scheduling (and what
Slurm is, for readers new to it), blob late materialization as its own
page, joins, aggregation/profiling, sampling, near-duplicate detection,
chunking, distributed shuffle, and IVF-partition clustering.

**Feature Engineering** -- computed columns and materialized views,
restructured to lead with the Function-based path and show the SQL form
side by side with Python throughout; a single Auto Refresh page instead
of
duplicating scheduling details on every refresh page; adaptive
execution;
checkpointing; GPU and Slurm placement for refresh workers; a Training
Cache page for the PyTorch data loader's automatic cache benefit.

**Security & Governance** -- an Audit Log reference (schema, access,
grants), Secrets promoted to an ordinary catalog object with their own
SQL
DDL and a vending/rotation guide, and privilege-table fixes verified
against the authorization source.

**Deployment & Maintenance** -- Horizontal Scaling and OpenTelemetry
moved
into a real Deployment area; Automated Cleanup folded into Intelligent
Auto-Maintenance (every other maintenance decision already lived there);
RTE Compaction and Advanced Conflict Resolution documented in depth.

**Landing page** -- the Enterprise feature comparison table reorganized
(several redundant or stale rows removed, several new areas added), and
the
"why Enterprise" bullets replaced with ones tied to a concrete page
(Performance, Scale, Fault tolerance, Multicloud deployment, Simplify
operations) instead of vague promises.

Plus a full pass addressing lancedb-gatekeeper's review: a real
test-safety
bug (a quickstart test could silently overwrite and delete a
deployment's
own `frames` table), a fabricated SQL statement with no backing
implementation, an actual dedup-guarantee bug in `take_row_ids`, and
dozens
of documentation-accuracy fixes verified against source rather than
taken
on faith -- each either fixed, or left with an explicit note on why it
needs a feature or deployment owner's sign-off instead of being guessed
at.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

https://claude.ai/code/session_018PXMCbRH6i5w47TsjeEUMT

---------

Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
2026-11-03 16:17:24 -08:00

68 lines
3.6 KiB
Plaintext

---
title: Watsonx Reranker
sidebarTitle: "IBM watsonx.ai"
description: Rerank LanceDB search results with the IBM watsonx.ai text rerank API. Supports vector, FTS, and hybrid search with configurable models, projects, and spaces.
---
import { PyRerankingWatsonxUsage } from '/snippets/provider_examples.mdx';
# Watsonx Reranker
This reranker uses the [IBM watsonx.ai](https://cloud.ibm.com/docs/apis/watsonx-ai#text-rerank) text rerank API to reorder search results. Pass `WatsonxReranker()` to the `rerank()` method on a query. Credentials come from the `WATSONX_API_KEY` and `WATSONX_PROJECT_ID` (or `WATSONX_SPACE_ID`) environment variables, or can be passed explicitly as arguments.
> **Note:** Supported query types: Hybrid, Vector, and FTS.
<CodeGroup>
```bash Bash icon="terminal"
pip install ibm-watsonx-ai
```
</CodeGroup>
Replace the credential placeholders with your provider credentials. In application code, load credentials from environment variables or a secrets manager.
<CodeGroup>
<CodeBlock filename="Python" language="Python" icon="python">
{PyRerankingWatsonxUsage}
</CodeBlock>
</CodeGroup>
## Accepted Arguments {#accepted-arguments}
| Argument | Type | Default | Description |
| --- | --- | --- | --- |
| `model_name` | `str` | `"cross-encoder/ms-marco-minilm-l-12-v2"` | The rerank model ID. See [supported rerank models](https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models-embed.html?context=wx#rerank). |
| `column` | `str` | `"text"` | The name of the table column to use as document input. |
| `top_n` | `int` | `None` | The number of results to return. If `None`, all results are returned. |
| `return_score` | `str` | `"relevance"` | Options are `"relevance"` or `"all"`. Controls which score columns are kept on the result. |
| `api_key` | `str` | `None` | IBM Cloud API key. Falls back to the `WATSONX_API_KEY` environment variable. |
| `project_id` | `str` | `None` | watsonx.ai project ID. Falls back to `WATSONX_PROJECT_ID`. Mutually exclusive with `space_id`. |
| `space_id` | `str` | `None` | watsonx.ai deployment space ID. Falls back to `WATSONX_SPACE_ID`. Mutually exclusive with `project_id`. |
| `url` | `str` | `"https://us-south.ml.cloud.ibm.com"` | watsonx.ai service URL. |
| `truncate_input_tokens` | `int` | `None` | Truncate each document to this many tokens before scoring. |
<Info>
You must supply exactly one of `project_id` or `space_id` (either as an argument or via its environment variable). Setting both, or neither, raises a `ValueError`.
</Info>
## Supported scores for each query type {#supported-scores-for-each-query-type}
You can specify the type of scores you want the reranker to return. The following are the supported scores for each query type:
### Hybrid Search {#hybrid-search}
|`return_score`| Status | Description |
| --- | --- | --- |
| `relevance` | ✅ Supported | Results only have the `_relevance_score` column. |
| `all` | ❌ Not Supported | Results have vector(`_distance`) and FTS(`score`) along with Hybrid Search score(`_relevance_score`). |
### Vector Search {#vector-search}
|`return_score`| Status | Description |
| --- | --- | --- |
| `relevance` | ✅ Supported | Results only have the `_relevance_score` column. |
| `all` | ✅ Supported | Results have vector(`_distance`) along with Hybrid Search score(`_relevance_score`). |
### FTS Search {#fts-search}
|`return_score`| Status | Description |
| --- | --- | --- |
| `relevance` | ✅ Supported | Results only have the `_relevance_score` column. |
| `all` | ✅ Supported | Results have FTS(`score`) along with Hybrid Search score(`_relevance_score`). |