Gemini Embeddings 问题：Discourse 更新到 3.6.0 Beta 2 后

支持
1

Discourse 更新到 2.6.0 beta 2 后，嵌入功能停止工作，我似乎找不到原因。

我正在使用 Gemini Flash 和 Flash Lite LLM，它们工作得很好，AI 机器人也能正常工作。

但是，当我转到嵌入模型并对 Gemini 嵌入运行 test 时，我会收到此错误（日志中也充满了此错误）：

 Trying to contact the model returned this error: { "error": { "code": 429, "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.\n* Quota exceeded for metric: generativelanguage.googleapis.com/embed_content_free_tier_requests, limit: 0\n* Quota exceeded for metric: generativelanguage.googleapis.com/embed_content_free_tier_requests, limit: 0\n* Quota exceeded for metric: generativelanguage.googleapis.com/embed_content_free_tier_requests, limit: 0\n* Quota exceeded for metric: generativelanguage.googleapis.com/embed_content_free_tier_requests, limit: 0", "status": "RESOURCE_EXHAUSTED", "details": [ { "@type": "type.googleapis.com/google.rpc.QuotaFailure", "violations": [ { "quotaMetric": "generativelanguage.googleapis.com/embed_content_free_tier_requests", "quotaId": "EmbedContentRequestsPerMinutePerProjectPerModel-FreeTier" }, { "quotaMetric": "generativelanguage.googleapis.com/embed_content_free_tier_requests", "quotaId": "EmbedContentRequestsPerMinutePerUserPerProjectPerModel-FreeTier" }, { "quotaMetric": "generativelanguage.googleapis.com/embed_content_free_tier_requests", "quotaId": "EmbedContentRequestsPerDayPerUserPerProjectPerModel-FreeTier" }, { "quotaMetric": "generativelanguage.googleapis.com/embed_content_free_tier_requests", "quotaId": "EmbedContentRequestsPerDayPerProjectPerModel-FreeTier" } ] }, { "@type": "type.googleapis.com/google.rpc.Help", "links": [ { "description": "Learn more about Gemini API quotas", "url": "https://ai.google.dev/gemini-api/docs/rate-limits" } ] } ] } }

这在 3.6.0 beta 1 之前一直工作正常，更新到 beta 2 后开始出现此错误。我使用的嵌入密钥与 LLM 使用的密钥相同。我甚至尝试生成新密钥，等待 48 小时等，但似乎都没有解决问题。

有人能告诉我为什么它突然停止工作，为什么 LLM AI 机器人可以工作但嵌入不行，以及如何修复它吗？

2

我要自己回复我的帖子。问题不在于构建，而在于时机。10 月份，Google 使当前的嵌入模型（embedding-001）过时，因此它停止工作了。新模型是 gemini-embedding-001。

您需要将嵌入配置从
https://generativelanguage.googleapis.com/v1beta/models/embedding-001:embedContent
更改为
https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:embedContent

您可以在此处找到详细信息：https://ai.google.dev/gemini-api/docs/embeddings

@Falco 也许 discourse 中的默认 gemini 配置需要更新，在创建新的 gemini 嵌入时，它仍然使用 embedding-001 而不是 gemini-embedding-001。

1 个赞
3

…并且似乎 discourse 没有设置为处理新的 gemini-embedding-001 模型。运行测试工作正常，但当我尝试搜索论坛时，我在日志中看到了这些错误：

消息（报告了 2 份副本）

错误 ERROR:  expected 768 dimensions, not 3072
 querying embeddings for model gemini

回溯

/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/activesupport-8.0.3/lib/active_support/broadcast_logger.rb:218:in `block in dispatch'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/activesupport-8.0.3/lib/active_support/broadcast_logger.rb:217:in `map'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/activesupport-8.0.3/lib/active_support/broadcast_logger.rb:217:in `dispatch'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/activesupport-8.0.3/lib/active_support/broadcast_logger.rb:129:in `error'
/var/www/discourse/plugins/discourse-ai/lib/embeddings/schema.rb:192:in `rescue in asymmetric_similarity_search'
/var/www/discourse/plugins/discourse-ai/lib/embeddings/schema.rb:139:in `asymmetric_similarity_search'
/var/www/discourse/plugins/discourse-ai/lib/embeddings/semantic_search.rb:89:in `search_for_topics'
/var/www/discourse/plugins/discourse-ai/app/controllers/discourse_ai/embeddings/embeddings_controller.rb:56:in `block in search'
/var/www/discourse/lib/hijack.rb:68:in `instance_eval'
/var/www/discourse/lib/hijack.rb:68:in `block (2 levels) in hijack'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/i18n-1.14.7/lib/i18n.rb:353:in `with_locale'
/var/www/discourse/lib/hijack.rb:68:in `block in hijack'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/concurrent-ruby-1.3.5/lib/concurrent-ruby/concurrent/promises.rb:911:in `callback_on_resolution'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/concurrent-ruby-1.3.5/lib/concurrent-ruby/concurrent/promises.rb:797:in `call_callback'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/concurrent-ruby-1.3.5/lib/concurrent-ruby/concurrent/promises.rb:803:in `call_callbacks'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/concurrent-ruby-1.3.5/lib/concurrent-ruby/concurrent/promises.rb:692:in `resolve_with'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/concurrent-ruby-1.3.5/lib/concurrent-ruby/concurrent/promises.rb:1325:in `resolve'
/var/www/discourse/lib/scheduler/defer.rb:125:in `block in do_work'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/rails_multisite-7.0.0/lib/rails_multisite/connection_management/null_instance.rb:49:in `with_connection'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/rails_multisite-7.0.0/lib/rails_multisite/connection_management.rb:17:in `with_connection'
/var/www/discourse/lib/scheduler/defer.rb:119:in `do_work'
/var/www/discourse/lib/scheduler/defer.rb:105:in `block (2 levels) in start_thread'

消息（报告了 2 份副本）

未能正确处理劫持响应：DiscourseAi::Embeddings::Schema::MissingEmbeddingError : DiscourseAi::Embeddings::Schema::MissingEmbeddingError

回溯

/var/www/discourse/plugins/discourse-ai/lib/embeddings/schema.rb:193:in `rescue in asymmetric_similarity_search'
/var/www/discourse/plugins/discourse-ai/lib/embeddings/schema.rb:139:in `asymmetric_similarity_search'
/var/www/discourse/plugins/discourse-ai/lib/embeddings/semantic_search.rb:89:in `search_for_topics'
/var/www/discourse/plugins/discourse-ai/app/controllers/discourse_ai/embeddings/embeddings_controller.rb:56:in `block in search'
/var/www/discourse/lib/hijack.rb:68:in `instance_eval'
/var/www/discourse/lib/hijack.rb:68:in `block (2 levels) in hijack'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/i18n-1.14.7/lib/i18n.rb:353:in `with_locale'
/var/www/discourse/lib/hijack.rb:68:in `block in hijack'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/concurrent-ruby-1.3.5/lib/concurrent-ruby/concurrent/promises.rb:911:in `callback_on_resolution'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/concurrent-ruby-1.3.5/lib/concurrent-ruby/concurrent/promises.rb:797:in `call_callback'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/concurrent-ruby-1.3.5/lib/concurrent-ruby/concurrent/promises.rb:803:in `call_callbacks'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/concurrent-ruby-1.3.5/lib/concurrent-ruby/concurrent/promises.rb:692:in `resolve_with'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/concurrent-ruby-1.3.5/lib/concurrent-ruby/concurrent/promises.rb:1325:in `resolve'
/var/www/discourse/lib/scheduler/defer.rb:125:in `block in do_work'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/rails_multisite-7.0.0/lib/rails_multisite/connection_management/null_instance.rb:49:in `with_connection'
/var/www/discourse/vendor/bundle/ruby/3.3.0/gems/rails_multisite-7.0.0/lib/rails_multisite/connection_management.rb:17:in `with_connection'
/var/www/discourse/lib/scheduler/defer.rb:119:in `do_work'
/var/www/discourse/lib/scheduler/defer.rb:105:in `block (2 levels) in start_thread'

…而似乎可行的是创建一个新模型并将 Embedding dimensions 从默认的 768 改为 3072。

可能 discourse gemini 嵌入需要对其默认设置进行检修，并且在第一个帖子中添加一个简短的“如何配置 gemini 嵌入”可能也是个好主意。

1 个赞
4

Gemini 嵌入设置未传递 output_dimensionality？ 的重复内容