[v1.34] Release docs

_includes/code/howto/configure-rq/rq-compression-v4.py

@@ -101,6 +101,10 @@
         quantizer=Configure.VectorIndex.Quantizer.rq(
             bits=8,  # Optional: Number of bits
             rescore_limit=20,  # Optional: Number of candidates to fetch before rescoring
+            cache=True,  # Optional: Enable caching for flat index (enabled by default for for HNSW)
+        ),
+        vector_index_config=Configure.VectorIndex.flat(
+            vector_cache_max_objects=100000,  # Optional: Maximum number of objects in the memory cache
         ),
         # highlight-end
     ),

_includes/code/howto/manage-data.collections.py

@@ -202,7 +202,7 @@
         vector_index_config=Configure.VectorIndex.hnsw(
             ef_construction=300,
             distance_metric=VectorDistances.COSINE,
-            filter_strategy=VectorFilterStrategy.SWEEPING,  # or ACORN (Available from Weaviate v1.27.0)
+            filter_strategy=VectorFilterStrategy.ACORN,
         ),
         # highlight-end
     ),

_includes/code/howto/manage-data.import.py

@@ -558,48 +558,48 @@ def add_object(obj) -> None:
 client.collections.delete("NewCollection")
 
 
-# # ==================================================
-# # ===== Server-side (automatic) batch import =====
-# # ==================================================
-
-# # Re-create the collection
-# client.collections.delete("MyCollection")
-# client.collections.create(
-#     "MyCollection",
-#     vector_config=Configure.Vectors.self_provided()
-# )
-
-# # START ServerSideBatchImportExample
-# data_rows = [
-#     {"title": f"Object {i+1}"} for i in range(5)
-# ]
-
-# collection = client.collections.get("MyCollection")
-
-# # highlight-start
-# # Use `automatic` for server-side batching. The client will send data
-# # in chunks and the server will dynamically manage the import process.
-# with collection.batch.automatic() as batch:
-#     for data_row in data_rows:
-#         batch.add_object(
-#             properties=data_row,
-#         )
-# # highlight-end
-#         if batch.number_errors > 10:
-#             print("Batch import stopped due to excessive errors.")
-#             break
-
-# failed_objects = collection.batch.failed_objects
-# if failed_objects:
-#     print(f"Number of failed imports: {len(failed_objects)}")
-#     print(f"First failed object: {failed_objects[0]}")
-# # END ServerSideBatchImportExample
-
-# result = collection.aggregate.over_all(total_count=True)
-# assert result.total_count == 5
-
-# # Clean up
-# client.collections.delete(collection.name)
+# ==================================================
+# ===== Server-side (automatic) batch import =====
+# ==================================================
+
+# Re-create the collection
+client.collections.delete("MyCollection")
+client.collections.create(
+    "MyCollection",
+    vector_config=Configure.Vectors.self_provided()
+)
+
+# START ServerSideBatchImportExample
+data_rows = [
+    {"title": f"Object {i+1}"} for i in range(5)
+]
+
+collection = client.collections.get("MyCollection")
+
+# highlight-start
+# Use `experimental` for server-side batching. The client will send data
+# in chunks and the server will dynamically manage the import process.
+with collection.batch.experimental() as batch:
+    for data_row in data_rows:
+        batch.add_object(
+            properties=data_row,
+        )
+# highlight-end
+        if batch.number_errors > 10:
+            print("Batch import stopped due to excessive errors.")
+            break
+
+failed_objects = collection.batch.failed_objects
+if failed_objects:
+    print(f"Number of failed imports: {len(failed_objects)}")
+    print(f"First failed object: {failed_objects[0]}")
+# END ServerSideBatchImportExample
+
+result = collection.aggregate.over_all(total_count=True)
+assert result.total_count == 5
+
+# Clean up
+client.collections.delete(collection.name)
 
 
 client.close()

_includes/configuration/rq-compression-parameters.mdx

@@ -1,4 +1,6 @@
-| Parameter            | Type    | Default | Details                                                                                                                                                                                                                      |
-| :------------------- | :------ | :------ | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `rq`: `bits`         | integer | `8`     | The number of bits used to quantize each data point. Value can be `8` or `1`. <br/> <br/>Learn more about [8-bit](/weaviate/concepts/vector-quantization#8-bit-rq) and [1-bit](/weaviate/concepts/vector-quantization#1-bit-rq) RQ. |
-| `rq`: `rescoreLimit` | integer | `-1`    | The minimum number of candidates to fetch before rescoring.                                                                                                                                                                  |
+| Parameter               | Type    | Default | Details                                                                                                                                                                                                                                                                     |
+| :---------------------- | :------ | :------ | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `rq`: `bits`            | integer | `8`     | The number of bits used to quantize each data point. Value can be `8` or `1`. <br/> <br/>Learn more about [8-bit](/weaviate/concepts/vector-quantization#8-bit-rq) and [1-bit](/weaviate/concepts/vector-quantization#1-bit-rq) RQ.                                         |
+| `rq`: `rescoreLimit`    | integer | `-1`    | The minimum number of candidates to fetch before rescoring.                                                                                                                                                                                                                 |
+| `rq` : `cache`          | boolean | `false` | Whether to use the vector cache.<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). |

_includes/named-vector-compress.mdx

@@ -1,4 +1 @@
-:::info Added in `v1.24`
-:::
-
 Collections can have multiple [named vectors](/weaviate/config-refs/collections#named-vectors). The vectors in a collection can have their own configurations, and compression must be enabled independently for each vector. Every vector is independent and can use [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.

docs/deploy/configuration/env-vars/index.md

@@ -75,7 +75,7 @@ import APITable from '@site/src/components/APITable';
 | `QUERY_MAXIMUM_RESULTS` | Sets the maximum total number of objects that can be retrieved. | `string - number` | `10000` |
 | `QUERY_SLOW_LOG_ENABLED` | Log slow queries for debugging. Requires a restart to update. <br/> (New in 1.24.16, 1.25.3) | `boolean` | `False` |
 | `QUERY_SLOW_LOG_THRESHOLD` | Set a threshold time for slow query logging. Requires a restart to update. <br/> (New in 1.24.16, 1.25.3) | `string` | `2s` <br/> Values are times: `3h`, `2s`, `100ms` |
-| `REINDEX_SET_TO_ROARINGSET_AT_STARTUP` | Allow Weaviate to perform a one-off re-indexing to [use Roaring Bitmaps](/weaviate/concepts/filtering.md#migration-to-indexFilterable). <br/><br/>Available in versions `1.18` and higher. | `boolean` | `true` |
+| `REINDEX_SET_TO_ROARINGSET_AT_STARTUP` | Allow Weaviate to perform a one-off re-indexing to use Roaring Bitmaps. <br/><br/>Available in versions `1.18` and higher. | `boolean` | `true` |
 | `TOKENIZER_CONCURRENCY_COUNT` | Limit the combined number of GSE and Kagome tokenizers running at the same time. Default: `GOMAXPROCS` | `string - number` | `NUMBER_OF_CPU_CORES` |
 | `TOMBSTONE_DELETION_CONCURRENCY` | The maximum number of cores to use for tombstone deletion. Set this to limit the number of cores used for cleanup. Default: Half of the available cores. (New in `v1.24.0`) | `string - int` | `4` |
 | `TOMBSTONE_DELETION_MAX_PER_CYCLE` | Maximum number of tombstones to delete per cleanup cycle. Set this to limit cleanup cycles, as they are resource-intensive. As an example, set a maximum of 10000000 (10M) for a cluster with 300 million-object shards. Default: none | `string - int` (New in `v1.24.15` / `v1.25.2`) | `10000000` |