{"id":47756,"date":"2026-10-06T07:25:17","date_gmt":"2026-10-06T05:25:17","guid":{"rendered":"https:\/\/www.dbi-services.com\/blog\/?p=47756"},"modified":"2026-10-06T07:32:51","modified_gmt":"2026-10-06T05:32:51","slug":"goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting","status":"publish","type":"post","link":"https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/","title":{"rendered":"GoldenGate AI Service bug confirmed in the Maximum Input Characters setting"},"content":{"rendered":"\n

In a previous blog<\/a>, I noted that there might be a bug with the Maximum Input Characters<\/code> setting in GoldenGate 26ai AI Service. The bug was confirmed by Oracle, so let\u2019s see what it is exactly.<\/p>\n\n\n\n

Bug found in GoldenGate 26ai AI Service<\/h2>\n\n\n\n

Maximum Input Characters<\/code> is a setting in the AI Service. You can set it when registering a new model in the web UI.<\/p>\n\n\n

\n
\"\"<\/figure>\n<\/div>\n\n\n

In the Oracle documentation<\/a>, the parameter is described as a cap on how much text is sent to the embedding model before it leaves GoldenGate. This ensures that an @AISERVICE<\/code> mapping cannot send more than intended, and does not reach a token limit, or increase your consumption.<\/p>\n\n\n\n

If this setting worked, a model with Maximum Input Characters<\/code> set to 1<\/code> should truncate any input to a single character before calling the AI Service. This is not what I found when testing it.<\/p>\n\n\n\n

Proof of the bug<\/h2>\n\n\n\n

Model registration<\/h3>\n\n\n\n

I registered two AI Service models against the same Gemini provider and the same remote model (gemini-embedding-001<\/code>). They differ only in Maximum Input Characters<\/code>: one set to 1000<\/code>, the other to 1<\/code>.<\/p>\n\n\n

\n
\"\"<\/figure>\n<\/div>\n\n
\n
\"\"<\/figure>\n<\/div>\n\n\n

If I query both models with the REST API, I can see the settings properly saved, in limits.maxInputCharacters<\/code>:<\/p>\n\n\n\n

{\n    \"id\": \"gemini_embed_max1000\",\n    \"name\": \"gemini-embedding-max1000\",\n    \"type\": \"remote\",\n    \"enabled\": true,\n    \"loaded\": false,\n    \"description\": \"Model with 1000 character limit\",\n    \"capabilities\": [\n        \"embed\"\n    ],\n    \"providerId\": \"gemini\",\n    \"remoteModelName\": \"gemini-embedding-001\",\n    \"parameters\": {},\n    \"limits\": {\n        \"maxInputCharacters\": 1000\n    }\n}<\/code><\/pre>\n\n\n\n
{\n    \"id\": \"gemini_embed_max1\",\n    \"name\": \"gemini-embedding-max1\",\n    \"type\": \"remote\",\n    \"enabled\": true,\n    \"loaded\": false,\n    \"description\": \"Model with 1 character limit\",\n    \"capabilities\": [\n        \"embed\"\n    ],\n    \"providerId\": \"gemini\",\n    \"remoteModelName\": \"gemini-embedding-001\",\n    \"parameters\": {},\n    \"limits\": {\n        \"maxInputCharacters\": 1\n    }\n}<\/code><\/pre>\n\n\n\n
Replicat used in the test<\/h3>\n\n\n\n
I built an EXTAI<\/code>\/REPAI<\/code> pair between PDB1.APP_PDB1.PRODUCTS<\/code> on the source and PDB26.APP_PDB26.PRODUCTS<\/code> on the target. Its COLMAP<\/code> maps the description<\/code> column through three separate @AISERVICE<\/code> calls into three different VECTOR(3072, FLOAT32)<\/code> columns:<\/p>\n\n\n\n
MAP PDB1.APP_PDB1.PRODUCTS, TARGET APP_PDB26.PRODUCTS,\nCOLMAP (\n    USEDEFAULTS,\n    desc_vector_max1000 = @AISERVICE(embed, 'gemini_embed_max1000', description),\n    desc_vector_max1000_run2 = @AISERVICE(embed, 'gemini_embed_max1000', description),\n    desc_vector_max1 = @AISERVICE(embed, 'gemini_embed_max1', description));<\/code><\/pre>\n\n\n\n
The first two calls use the same model (gemini_embed_max1000<\/code>). This is to show the baseline argument that the same input, embedded with the same model twice, produce the same vector. The third call uses the 1 character model, to test the bug.<\/p>\n\n\n\n
Baseline and embedding noise<\/h2>\n\n\n\n
The truncation is only relevant if identical inputs reliably produce identical output. Before comparing vectors across models, I first confirmed the embedding had no noise, by inserting the same 100 character description<\/code> into two source rows and let both flow through the pipeline:<\/p>\n\n\n\n
INSERT INTO app_pdb1.products (id, name, description) VALUES (101, 'AI Service Max Input Chars Test Row 1', 'GoldenGate 26ai AI Service test row for comparing embeddings across the max1000 and max1 test models');\nINSERT INTO app_pdb1.products (id, name, description) VALUES (102, 'AI Service Max Input Chars Test Row 2', 'GoldenGate 26ai AI Service test row for comparing embeddings across the max1000 and max1 test models');\nCOMMIT;<\/code><\/pre>\n\n\n\n
Then, I compared the gemini_embed_max1000<\/code> vector between the two rows. I also compared the two separate @AISERVICE<\/code> calls to the same model within row 101 itself. Both come back with a cosine distance of 0<\/code>:<\/p>\n\n\n\n
SQL> SELECT VECTOR_DISTANCE(a.desc_vector_max1000, b.desc_vector_max1000, COSINE) dist_101_vs_102_same_input\nFROM app_pdb26.products a, app_pdb26.products b\nWHERE a.id = 101\nAND b.id = 102;\n\nDIST_101_VS_102_SAME_INPUT\n--------------------------\n                         0\n<\/code><\/pre>\n\n\n\n
The conclusion is that gemini-embedding-001<\/code> is deterministic for identical input. Now, if the max1<\/code> vector is identical to the max1000<\/code> vector, we can rule out embedding noise.<\/p>\n\n\n\n
Does the 1 character limit change anything?<\/h2>\n\n\n\n
With the same transaction, let\u2019s look at the two different @AISERVICE<\/code> calls, against a model capped at 1000 characters and one capped at 1:<\/p>\n\n\n\n
SQL> SELECT id, VECTOR_DISTANCE(desc_vector_max1000, desc_vector_max1, COSINE) dist_max1000_vs_max1, VECTOR_DISTANCE(desc_vector_max1000, desc_vector_max1000_run2, COSINE) dist_max1000_vs_rerun\nFROM app_pdb26.products\nWHERE id IN (101, 102);\n\nID  DIST_MAX1000_VS_MAX1 DIST_MAX1000_VS_RERUN\n--- -------------------- ---------------------\n101                    0                     0\n102                    0                     0<\/code><\/pre>\n\n\n\n
On both models, the distance between the resulting vectors is zero. If the Maximum Input Characters<\/code> were enforced, the vectors should be different<\/strong> between both models. This proves that the Maximum Input Characters<\/code> setting saved as 1<\/code> had no effect on what was sent to Gemini.<\/p>\n\n\n\n
GoldenGate even has a documented warning<\/a> for a situation where the input would exceed the limit. OGG-30677<\/code> is defined as @AISERVICE source column {0} contains {1} characters, exceeding model {2}'s maximum input limit of {3} characters<\/code>. But in my case, the warning never appeared in the log files.<\/p>\n\n\n\n
What can break?<\/h2>\n\n\n\n
I added a fourth @AISERVICE<\/code> call to the same replicat, mapping a CLOB<\/code> column (big_description<\/code>) through the 1000 character model. I then tried pushing progressively larger inputs.<\/p>\n\n\n\n
With 100000 characters, the countTokens<\/code> endpoint reports this input at 23679 tokens, way more than the documented inputTokenLimit<\/code> of gemini-embedding-001<\/code>. It applied without any error and produced a real 3072 dimension vector, distinct from every other vector in this blog.<\/p>\n\n\n\n
SQL> SELECT id, VECTOR_DIMS(desc_vector_bigtest) dims\nFROM app_pdb26.products\nWHERE id = 103;\n\nID  DIMS\n--- ----\n103 3072<\/code><\/pre>\n\n\n\n
Here, we can see that even the documented token limit of your provider might not stop the AI Service to work.<\/p>\n\n\n\n
Reaching quota limit<\/h3>\n\n\n\n
On top of the per-request token limit, depending on your billing settings, you might have a usage quota on the API key. A request can be rejected by Gemini, and this error is raised in AIService.log<\/code>:<\/p>\n\n\n\n
{\n    \"error\": {\n        \"code\": 429,\n        \"message\": \"You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https:\/\/ai.google.dev\/gemini-api\/docs\/rate-limits. To monitor your current usage, head to: https:\/\/ai.dev\/rate-limit. \",\n        \"status\": \"RESOURCE_EXHAUSTED\"\n    }\n}<\/code><\/pre>\n\n\n\n
And in this case, the replicat abends with the following error:<\/p>\n\n\n\n
2026-09-27 08:22:21  WARNING OGG-30679  Response from EMBED endpoint using model gemini_embed_max1000 returned error: code REMOTE_INFERENCE_FAILED, message 'HTTP 429 - Too Many Requests: {\n  \"error\": {\n    \"code\": 429,\n    \"message\": \"You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https:\/\/ai.google.dev\/gemini-api\/docs\/rate-limits. To monitor your current usage, head to: https:\/\/ai.dev\/rate-limit. \",\n    \"status\": \"RESOURCE_EXHAUSTED\"\n  }\n}\n'.\n\n2026-09-27 08:22:21  WARNING OGG-01431  Canceled grouped transaction on PDB26.APP_PDB26.PRODUCTS, Mapping error.\n2026-09-27 08:22:27  ERROR   OGG-01668  PROCESS ABENDING.<\/code><\/pre>\n\n\n\n
Summary<\/h2>\n\n\n\n
Maximum Input Characters<\/code> does not protect a replicat from an oversized @AISERVICE<\/code> mapping. Because of this, the only real limit to your embeddings in GoldenGate is a usage quota. This can affect your replication, whether you rely on the setting for functional truncation or to lower your costs. Until the bug is fixed, be careful when using the AI Service!<\/p>\n","protected":false},"excerpt":{"rendered":"
In a previous blog, I noted that there might be a bug with the Maximum Input Characters setting in GoldenGate 26ai AI Service. The bug was confirmed by Oracle, so let\u2019s see what it is exactly. Bug found in GoldenGate 26ai AI Service Maximum Input Characters is a setting in the AI Service. You can […]<\/p>\n","protected":false},"author":152,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":"","_members_access_role":[],"_members_access_error":""},"categories":[3787,59],"tags":[3827,3804,3825,3652,4243,328,4280,3229,3730,44,4242],"type_dbi":[3828,3823,4245,4248,4247,3740,4279,3231,3881,4175,4246],"class_list":["post-47756","post","type-post","status-publish","format-standard","hentry","category-goldengate","category-oracle","tag-3827","tag-26ai","tag-ai-service","tag-embeddings","tag-gemini","tag-goldengate","tag-maximum","tag-microservices","tag-ogg","tag-troubleshooting","tag-vector","type-3828","type-26ai","type-ai-service","type-embeddings","type-gemini","type-goldengate","type-maximum","type-microservices","type-ogg","type-troubleshooting","type-vector"],"acf":[],"yoast_head":"\nGoldenGate AI Service bug confirmed in the Maximum Input Characters setting - dbi Blog<\/title>\n<meta name=\"description\" content=\"Proof that the GoldenGate Maximum Input Characters setting of the 26ai AI Service does nothing: same Gemini vectors at 1 and 1000 chars.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"GoldenGate AI Service bug confirmed in the Maximum Input Characters setting\" \/>\n<meta property=\"og:description\" content=\"Proof that the GoldenGate Maximum Input Characters setting of the 26ai AI Service does nothing: same Gemini vectors at 1 and 1000 chars.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/\" \/>\n<meta property=\"og:site_name\" content=\"dbi Blog\" \/>\n<meta property=\"article:published_time\" content=\"2026-10-06T05:25:17+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-10-06T05:32:51+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.dbi-services.com\/blog\/wp-content\/uploads\/sites\/2\/2026\/10\/001_goldengate-26ai-ai-service-max-input-add-model-dialog.png\" \/>\n\t<meta property=\"og:image:width\" content=\"700\" \/>\n\t<meta property=\"og:image:height\" content=\"580\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Julien Delattre\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Julien Delattre\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\\\/\"},\"author\":{\"name\":\"Julien Delattre\",\"@id\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/#\\\/schema\\\/person\\\/764ab019cc9dec42655b4c6b9b8e474e\"},\"headline\":\"GoldenGate AI Service bug confirmed in the Maximum Input Characters setting\",\"datePublished\":\"2026-10-06T05:25:17+00:00\",\"dateModified\":\"2026-10-06T05:32:51+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\\\/\"},\"wordCount\":652,\"commentCount\":0,\"image\":{\"@id\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/wp-content\\\/uploads\\\/sites\\\/2\\\/2026\\\/10\\\/001_goldengate-26ai-ai-service-max-input-add-model-dialog.png\",\"keywords\":[\"26\",\"26ai\",\"ai service\",\"embeddings\",\"gemini\",\"GoldenGate\",\"maximum\",\"microservices\",\"ogg\",\"Troubleshooting\",\"vector\"],\"articleSection\":[\"GoldenGate\",\"Oracle\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\\\/\",\"url\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\\\/\",\"name\":\"GoldenGate AI Service bug confirmed in the Maximum Input Characters setting - dbi Blog\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/wp-content\\\/uploads\\\/sites\\\/2\\\/2026\\\/10\\\/001_goldengate-26ai-ai-service-max-input-add-model-dialog.png\",\"datePublished\":\"2026-10-06T05:25:17+00:00\",\"dateModified\":\"2026-10-06T05:32:51+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/#\\\/schema\\\/person\\\/764ab019cc9dec42655b4c6b9b8e474e\"},\"description\":\"Proof that the GoldenGate Maximum Input Characters setting of the 26ai AI Service does nothing: same Gemini vectors at 1 and 1000 chars.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\\\/#primaryimage\",\"url\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/wp-content\\\/uploads\\\/sites\\\/2\\\/2026\\\/10\\\/001_goldengate-26ai-ai-service-max-input-add-model-dialog.png\",\"contentUrl\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/wp-content\\\/uploads\\\/sites\\\/2\\\/2026\\\/10\\\/001_goldengate-26ai-ai-service-max-input-add-model-dialog.png\",\"width\":700,\"height\":580},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Accueil\",\"item\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"GoldenGate AI Service bug confirmed in the Maximum Input Characters setting\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/#website\",\"url\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/\",\"name\":\"dbi Blog\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/#\\\/schema\\\/person\\\/764ab019cc9dec42655b4c6b9b8e474e\",\"name\":\"Julien Delattre\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a97d00e680bbf237126e24b65281cbcb66cd20bd1ed2d14bf928991b2bf68eb5?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a97d00e680bbf237126e24b65281cbcb66cd20bd1ed2d14bf928991b2bf68eb5?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a97d00e680bbf237126e24b65281cbcb66cd20bd1ed2d14bf928991b2bf68eb5?s=96&d=mm&r=g\",\"caption\":\"Julien Delattre\"},\"url\":\"https:\\\/\\\/www.dbi-services.com\\\/blog\\\/author\\\/juliendelattre\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"GoldenGate AI Service bug confirmed in the Maximum Input Characters setting - dbi Blog","description":"Proof that the GoldenGate Maximum Input Characters setting of the 26ai AI Service does nothing: same Gemini vectors at 1 and 1000 chars.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/","og_locale":"en_US","og_type":"article","og_title":"GoldenGate AI Service bug confirmed in the Maximum Input Characters setting","og_description":"Proof that the GoldenGate Maximum Input Characters setting of the 26ai AI Service does nothing: same Gemini vectors at 1 and 1000 chars.","og_url":"https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/","og_site_name":"dbi Blog","article_published_time":"2026-10-06T05:25:17+00:00","article_modified_time":"2026-10-06T05:32:51+00:00","og_image":[{"width":700,"height":580,"url":"https:\/\/www.dbi-services.com\/blog\/wp-content\/uploads\/sites\/2\/2026\/10\/001_goldengate-26ai-ai-service-max-input-add-model-dialog.png","type":"image\/png"}],"author":"Julien Delattre","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Julien Delattre","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/#article","isPartOf":{"@id":"https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/"},"author":{"name":"Julien Delattre","@id":"https:\/\/www.dbi-services.com\/blog\/#\/schema\/person\/764ab019cc9dec42655b4c6b9b8e474e"},"headline":"GoldenGate AI Service bug confirmed in the Maximum Input Characters setting","datePublished":"2026-10-06T05:25:17+00:00","dateModified":"2026-10-06T05:32:51+00:00","mainEntityOfPage":{"@id":"https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/"},"wordCount":652,"commentCount":0,"image":{"@id":"https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/#primaryimage"},"thumbnailUrl":"https:\/\/www.dbi-services.com\/blog\/wp-content\/uploads\/sites\/2\/2026\/10\/001_goldengate-26ai-ai-service-max-input-add-model-dialog.png","keywords":["26","26ai","ai service","embeddings","gemini","GoldenGate","maximum","microservices","ogg","Troubleshooting","vector"],"articleSection":["GoldenGate","Oracle"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/","url":"https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/","name":"GoldenGate AI Service bug confirmed in the Maximum Input Characters setting - dbi Blog","isPartOf":{"@id":"https:\/\/www.dbi-services.com\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/#primaryimage"},"image":{"@id":"https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/#primaryimage"},"thumbnailUrl":"https:\/\/www.dbi-services.com\/blog\/wp-content\/uploads\/sites\/2\/2026\/10\/001_goldengate-26ai-ai-service-max-input-add-model-dialog.png","datePublished":"2026-10-06T05:25:17+00:00","dateModified":"2026-10-06T05:32:51+00:00","author":{"@id":"https:\/\/www.dbi-services.com\/blog\/#\/schema\/person\/764ab019cc9dec42655b4c6b9b8e474e"},"description":"Proof that the GoldenGate Maximum Input Characters setting of the 26ai AI Service does nothing: same Gemini vectors at 1 and 1000 chars.","breadcrumb":{"@id":"https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/#primaryimage","url":"https:\/\/www.dbi-services.com\/blog\/wp-content\/uploads\/sites\/2\/2026\/10\/001_goldengate-26ai-ai-service-max-input-add-model-dialog.png","contentUrl":"https:\/\/www.dbi-services.com\/blog\/wp-content\/uploads\/sites\/2\/2026\/10\/001_goldengate-26ai-ai-service-max-input-add-model-dialog.png","width":700,"height":580},{"@type":"BreadcrumbList","@id":"https:\/\/www.dbi-services.com\/blog\/goldengate-ai-service-bug-confirmed-in-the-maximum-input-characters-setting\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Accueil","item":"https:\/\/www.dbi-services.com\/blog\/"},{"@type":"ListItem","position":2,"name":"GoldenGate AI Service bug confirmed in the Maximum Input Characters setting"}]},{"@type":"WebSite","@id":"https:\/\/www.dbi-services.com\/blog\/#website","url":"https:\/\/www.dbi-services.com\/blog\/","name":"dbi Blog","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.dbi-services.com\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.dbi-services.com\/blog\/#\/schema\/person\/764ab019cc9dec42655b4c6b9b8e474e","name":"Julien Delattre","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/a97d00e680bbf237126e24b65281cbcb66cd20bd1ed2d14bf928991b2bf68eb5?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/a97d00e680bbf237126e24b65281cbcb66cd20bd1ed2d14bf928991b2bf68eb5?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/a97d00e680bbf237126e24b65281cbcb66cd20bd1ed2d14bf928991b2bf68eb5?s=96&d=mm&r=g","caption":"Julien Delattre"},"url":"https:\/\/www.dbi-services.com\/blog\/author\/juliendelattre\/"}]}},"_links":{"self":[{"href":"https:\/\/www.dbi-services.com\/blog\/wp-json\/wp\/v2\/posts\/47756","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.dbi-services.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.dbi-services.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.dbi-services.com\/blog\/wp-json\/wp\/v2\/users\/152"}],"replies":[{"embeddable":true,"href":"https:\/\/www.dbi-services.com\/blog\/wp-json\/wp\/v2\/comments?post=47756"}],"version-history":[{"count":2,"href":"https:\/\/www.dbi-services.com\/blog\/wp-json\/wp\/v2\/posts\/47756\/revisions"}],"predecessor-version":[{"id":47763,"href":"https:\/\/www.dbi-services.com\/blog\/wp-json\/wp\/v2\/posts\/47756\/revisions\/47763"}],"wp:attachment":[{"href":"https:\/\/www.dbi-services.com\/blog\/wp-json\/wp\/v2\/media?parent=47756"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.dbi-services.com\/blog\/wp-json\/wp\/v2\/categories?post=47756"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.dbi-services.com\/blog\/wp-json\/wp\/v2\/tags?post=47756"},{"taxonomy":"type","embeddable":true,"href":"https:\/\/www.dbi-services.com\/blog\/wp-json\/wp\/v2\/type_dbi?post=47756"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}