[DOCS] Adds API docs for bert_ja text embedding tokenizer option (#96873)

docs/reference/ml/ml-shared.asciidoc

@@ -944,7 +944,9 @@ values are
 * `bert`: Use for BERT-style models
 * `mpnet`: Use for MPNet-style models
 * `roberta`: Use for RoBERTa-style and BART-style models
-* `xlm_roberta`: Use for XLMRoBERTa-style models
+* experimental:[] `xlm_roberta`: Use for XLMRoBERTa-style models
+* experimental:[] `bert_ja`: Use for BERT-style models trained for the Japanese
+language.
 --
 end::inference-config-nlp-tokenization[]
 
@@ -952,6 +954,11 @@ tag::inference-config-nlp-tokenization-bert[]
 BERT-style tokenization is to be performed with the enclosed settings.
 end::inference-config-nlp-tokenization-bert[]
 
+tag::inference-config-nlp-tokenization-bert-ja[]
+experimental:[] BERT-style tokenization for Japanese text is to be performed 
+with the enclosed settings.
+end::inference-config-nlp-tokenization-bert-ja[]
+
 tag::inference-config-nlp-tokenization-do-lower-case[]
 Specifies if the tokenization lower case the text sequence when building the
 tokens.
@@ -993,6 +1000,10 @@ Tokenize with special tokens. The tokens typically included in BERT-style tokeni
 --
 end::inference-config-nlp-tokenization-bert-with-special-tokens[]
 
+tag::inference-config-nlp-tokenization-bert-ja-with-special-tokens[]
+Tokenize with special tokens if `true`.
+end::inference-config-nlp-tokenization-bert-ja-with-special-tokens[]
+
 tag::inference-config-nlp-tokenization-max-sequence-length[]
 Specifies the maximum number of tokens allowed to be output by the tokenizer.
 end::inference-config-nlp-tokenization-max-sequence-length[]

docs/reference/ml/trained-models/apis/get-trained-models.asciidoc

@@ -269,6 +269,29 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
 ========
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+========
+`do_lower_case`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja-with-special-tokens]
+========
 =======
 `vocabulary`::::
 (Optional, object)
@@ -392,6 +415,29 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
 ========
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+========
+`do_lower_case`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja-with-special-tokens]
+========
 =======
 `vocabulary`::::
 (Optional, object)
@@ -508,6 +554,29 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
 ========
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+========
+`do_lower_case`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja-with-special-tokens]
+========
 =======
 `vocabulary`::::
 (Optional, object)
@@ -663,6 +732,33 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
 ========
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+========
+`do_lower_case`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`span`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja-with-special-tokens]
+========
 =======
 
 `vocabulary`::::
@@ -787,6 +883,29 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
 ========
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+========
+`do_lower_case`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja-with-special-tokens]
+========
 =======
 `vocabulary`::::
 (Optional, object)
@@ -922,6 +1041,33 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
 ========
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+========
+`do_lower_case`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`span`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja-with-special-tokens]
+========
 =======
 `vocabulary`::::
 (Optional, object)
@@ -1053,6 +1199,29 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
 ========
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+========
+`do_lower_case`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja-with-special-tokens]
+========
 =======
 `vocabulary`::::
 (Optional, object)

docs/reference/ml/trained-models/apis/infer-trained-model.asciidoc

@@ -168,6 +168,17 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, string)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 =======
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+=======
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+=======
 ======
 =====
 
@@ -233,6 +244,17 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, string)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 =======
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+=======
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+=======
 ======
 =====
 
@@ -298,6 +320,17 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, string)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 =======
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+=======
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+=======
 ======
 =====
 
@@ -391,6 +424,21 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, integer)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
 
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+=======
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+=======
+`span`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
+
 `truncate`::::
 (Optional, string)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
@@ -492,13 +540,28 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 .Properties of xlm_roberta
 [%collapsible%open]
 =======
+`span`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
+
 `truncate`::::
 (Optional, string)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
-
+=======
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+=======
 `span`::::
 (Optional, integer)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 =======
 ======
 =====
@@ -564,6 +627,17 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, string)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 =======
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+=======
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+=======
 ======
 =====
 `text_similarity`:::
@@ -640,13 +714,28 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 .Properties of xlm_roberta
 [%collapsible%open]
 =======
+`span`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
+
 `truncate`::::
 (Optional, string)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
-
+=======
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+=======
 `span`::::
 (Optional, integer)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja-with-special-tokens]
 =======
 ======
 =====
@@ -720,6 +809,17 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, string)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
 =======
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+=======
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+=======
 ======
 =====
 ====

docs/reference/ml/trained-models/apis/put-trained-models.asciidoc

@@ -532,6 +532,29 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
 =======
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+=======
+`do_lower_case`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja-with-special-tokens]
+=======
 ======
 =====
 
@@ -648,6 +671,29 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
 =======
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+=======
+`do_lower_case`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja-with-special-tokens]
+=======
 ======
 =====
 
@@ -757,6 +803,29 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
 =======
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+=======
+`do_lower_case`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja-with-special-tokens]
+=======
 ======
 =====
 
@@ -889,6 +958,33 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
 =======
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+=======
+`do_lower_case`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`span`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja-with-special-tokens]
+=======
 ======
 =====
 
@@ -1033,6 +1129,33 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
 =======
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+=======
+`do_lower_case`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`span`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja-with-special-tokens]
+=======
 ======
 =====
 `text_embedding`:::
@@ -1145,6 +1268,29 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
 =======
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+=======
+`do_lower_case`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja-with-special-tokens]
+=======
 ======
 =====
 `text_similarity`::::
@@ -1269,6 +1415,33 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
 =======
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+=======
+`do_lower_case`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`span`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-span]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja-with-special-tokens]
+=======
 ======
 =====
 `zero_shot_classification`:::
@@ -1393,6 +1566,29 @@ include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenizati
 (Optional, boolean)
 include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-roberta-with-special-tokens]
 =======
+`bert_ja`::::
+(Optional, object)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja]
++
+.Properties of bert_ja
+[%collapsible%open]
+=======
+`do_lower_case`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-do-lower-case]
+
+`max_sequence_length`::::
+(Optional, integer)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-max-sequence-length]
+
+`truncate`::::
+(Optional, string)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-truncate]
+
+`with_special_tokens`::::
+(Optional, boolean)
+include::{es-repo-dir}/ml/ml-shared.asciidoc[tag=inference-config-nlp-tokenization-bert-ja-with-special-tokens]
+=======
 ======
 =====
 ====