g-despot · Sep 23, 2026 · Sep 28, 2026 · Sep 28, 2026 · Oct 6, 2026 · Oct 6, 2026
diff --git a/_includes/configuration/rq-compression-parameters.mdx b/_includes/configuration/rq-compression-parameters.mdx
@@ -2,5 +2,7 @@
 | :---------------------- | :------ | :------ | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `rq`: `bits`            | integer | `8`     | The number of bits used to quantize each data point. Value can be `8`, `4` or `1`, but not every index type accepts all three. The `hnsw` index type accepts `8`, `4` and `1`. The `flat` index type accepts only `8` and `1`. The `hfresh` index type accepts only `1`. <br/><br/>This parameter is fixed once RQ is enabled and cannot be changed afterwards. <br/> <br/>Learn more about [8-bit](/weaviate/concepts/vector-quantization#8-bit-rq), [4-bit](/weaviate/concepts/vector-quantization#4-bit-rq) and [1-bit](/weaviate/concepts/vector-quantization#1-bit-rq) RQ.                                         |
 | `rq`: `rescoreLimit`    | integer | `20` (`hnsw`, 8-bit and 4-bit)<br/>`512` (`hnsw`, 1-bit)<br/>`-1` (`flat`) | The minimum number of candidates to fetch before rescoring. Mutable at any time. <br/><br/>The default depends on the vector index type, and under `hnsw` also on `bits`: `20` for 8-bit and 4-bit RQ, and `512` for 1-bit RQ. Under the `flat` index type the default is `-1`, which lets Weaviate pick the limit. <br/><br/>The Java client sends this parameter under a field name that Weaviate does not read, so values set from that client are ignored and the server default applies. <br/><br/>These defaults apply to the `hnsw` and `flat` index types. For the HFresh index, see [HFresh index parameters](/weaviate/config-refs/indexing/vector-index#hfresh-index-parameters).                                                                                                                                                                                                                 |
+| `rq`: `centering`       | boolean | `false` | Centers the vectors on their mean before 4-bit RQ compression. Only valid on the `hnsw` index with `bits` set to `4`. Not supported for multi-vector embeddings without MUVERA. <br/><br/>Weaviate computes the mean from a sample of up to `trainingLimit` vectors. Compression starts once a shard holds more than `trainingLimit` vectors. <br/><br/>Cannot be changed once RQ is enabled. <br/><br/>Added in `v1.39.3` |
+| `rq`: `trainingLimit`   | integer | `10000` | The maximum number of vectors per shard sampled to compute the mean for `centering`. Must be greater than `0` when `centering` is `true`. Has no effect without `centering`. <br/><br/>Added in `v1.39.3` |
 | `rq` : `cache`          | boolean | `false` | Whether to cache the vectors in memory.<br/> (only when using the `flat` vector index type)                                                                                                                                                                                        |
 | `vectorCacheMaxObjects` | integer | `1e12`  | Maximum number of objects in the memory cache. By default, this limit is set to one trillion (`1e12`) objects when a new collection is created. For sizing recommendations, see [Vector cache considerations](/weaviate/concepts/vector-index#vector-cache-considerations). |
diff --git a/_includes/feature-notes/hfresh_multivector.mdx b/_includes/feature-notes/hfresh_multivector.mdx
@@ -0,0 +1,2 @@
+:::info Added in `v1.40`
+:::
diff --git a/_includes/feature-notes/meta.mdx b/_includes/feature-notes/meta.mdx
@@ -0,0 +1,2 @@
+:::info Added in `v1.39.3`
+:::
diff --git a/_includes/feature-notes/rq-4bit.mdx b/_includes/feature-notes/rq-4bit.mdx
@@ -1,5 +1,2 @@
-:::caution Preview — added in `v1.39.0`
-
-**4-bit Rotational quantization (RQ)** for the **HNSW vector index** was added in **`v1.39.0`** as a preview feature. The API may change in future releases.
-
+:::info Added in `v1.40`
 :::
diff --git a/_includes/multi-vector-compress.mdx b/_includes/multi-vector-compress.mdx
@@ -1,6 +1,6 @@
 :::info Added in `v1.30`
 :::
 
-Multi-vector embeddings (implemented through models like ColBERT, ColPali, or ColQwen) represent each object or query using multiple vectors instead of a single vector. Just like with single vectors, multi-vectors support [PQ](/weaviate/configuration/compression/pq-compression), [BQ](/weaviate/configuration/compression/bq-compression), [RQ](/weaviate/configuration/compression/rq-compression), [SQ](/weaviate/configuration/compression/sq-compression), or no compression.
+Multi-vector embeddings (implemented through models like ColBERT, ColPali, or ColQwen) represent each object or query using multiple vectors instead of a single vector. On an `hnsw` index, multi-vectors support [PQ](/weaviate/configuration/compression/pq-compression), [BQ](/weaviate/configuration/compression/bq-compression), [RQ](/weaviate/configuration/compression/rq-compression), [SQ](/weaviate/configuration/compression/sq-compression), or no compression. On an `hfresh` index (from `v1.40`), the MUVERA encoding is always compressed with 1-bit RQ.
 
 During the initial search phase, compressed vectors are used for efficiency. However, when computing the `MaxSim` operation, uncompressed vectors are utilized to ensure more precise similarity calculations. This approach balances the benefits of compression for search efficiency with the accuracy of uncompressed vectors during final scoring.