主题总结不起作用 : -(

支持
,
1

大家好，

这是关于一个自托管实例

我启用了 Discourse AI 插件，并在那里遇到了一些问题。
在企业环境中工作，AI 访问是通过一个带有额外身份验证的内部端点。
我实现了一个 AWS API Gateway 端点和一个 Lambda，它负责用所需的身份验证信息丰富标头，并将请求传递给兼容 OPENAI 的内部端点。

该图像描绘了一个软件应用程序中大型语言模型 (LLM) 的设置页面，详细说明了它们的使用方式，并列出了一个名为 GPT-4o 的已配置 LLM，该 LLM 与 vLLM 提供商相关联。（由 AI 题注）
该图像描绘了一个软件应用程序中大型语言模型 (LLM) 的设置页面，详细说明了它们的使用方式，并列出了一个名为 GPT-4o 的已配置 LLM，该 LLM 与 vLLM 提供商相关联。（由 AI 题注）1457×433 27 KB

LLM 测试给了我一个

image
image536×127 5.39 KB

然后我认为我准备好了。

我还在 CloudWatch 日志中看到了与 API Gateway 调用相关的调用。

然后，我将摘要 Persona（Smmmarization 和…（简短形式））与此 LLM 相关联，并启用了主题摘要。

但我现在看到的结果并不是我想要的 :smiley:

该图像显示了一个写作应用程序中的摘要建议工具，突出显示了一个模板以及按投票或活动排序的选项。（由 AI 题注）
该图像显示了一个写作应用程序中的摘要建议工具，突出显示了一个模板以及按投票或活动排序的选项。（由 AI 题注）1394×664 13 KB

而且这也没有改变 :frowning:

最奇怪的是，我在 CloudWatch 日志中没有看到尝试摘要的请求。

好的，我再次总结一下我所做的：

  • 启用了 AI
  • 使用我的 API Gateway 端点创建了 vLLM
  • 创建了 2 个 Persona（见上文）并将它们与我的 LLM 配置相关联
  • 启用了摘要，并在那里关联了 Persona（尝试了两者）

不确定接下来可以尝试什么 :frowning:

谢谢大家，祝好，

JP

2

我们的测试终结点有点误导，我想修复这个问题。

我们目前只测试“非流式传输”终结点。“流式传输”未被测试。

如果禁用 LLM 上的流式传输，所有功能是否都能正常工作？也许您的代理尚未实现流式传输。

3

嘿 @sam，

我在 LAMBDA 中禁用了流式传输（硬编码），同时将请求传递了过去。

问题是，LAMBDA 根本没有被摘要 API 触发（我看不到任何请求）。

LLM 测试会发出一个调用，但主题中的摘要按钮不会。

没有任何错误（我已通过 DISCOURSE_LOG_LEVEL=debug 开启了调试级别），在 discourse 日志中没有，在我的 LAMBDA（CloudWatch）日志中也没有。

就好像我什么都没按一样 :frowning:

谢谢，祝好，

Julian

4

如果它是一个与 OpenAI 兼容的端点，为什么提供商设置为 vLLM？

1 个赞
5

Hi,

I´ve tried many different engines. Sorry, the screenshot was misleading. I´ve tried OpenAI also …

This is the answer from the endpoint which I send 1:1 back to discourse instance.
With this I´m getting an “Internal Server Error” @ discourse (not sure why, because the test worked until this morning :smiley: )

{
  "statusCode": 200,
  "headers": {
    "date": "Mon, 02 Jun 2025 05:57:44 GMT",
    "content-type": "application/json",
    "content-length": "1315",
    "x-content-type-options": "nosniff",
    "x-frame-options": "DENY",
    "strict-transport-security": "max-age=63072000; includeSubdomains; preload",
    "content-security-policy": "default-src 'none'; img-src 'self'; script-src 'self'; style-src 'self'; object-src 'none'",
    "referrer-policy": "no-referrer",
    "x-xss-protection": "0",
    "x-request-id": "02d33931-1e29-418e-b9a7-4eba07710e8e",
    "x-accel-buffering": "no",
    "via": "1.1 google"
  },
  "body": {
    "id": "24c1474f-bd51-4542-b87a-8608fd90b5fb",
    "choices": [
      {
        "finish_reason": "stop",
        "index": 0,
        "logprobs": null,
        "message": {
          "content": "1 + 1 equals 2.",
          "refusal": null,
          "role": "assistant",
          "annotations": [],
          "audio": null,
          "function_call": null,
          "tool_calls": null,
          "reasoning_content": null
        },
        "content_filter_results": {
          "hate": {
            "filtered": false,
            "severity": "safe"
          },
          "profanity": {
            "filtered": false,
            "detected": false
          },
          "protected_material_code": {
            "filtered": false,
            "detected": false
          },
          "protected_material_text": {
            "filtered": false,
            "detected": false
          },
          "self_harm": {
            "filtered": false,
            "severity": "safe"
          },
          "sexual": {
            "filtered": false,
            "severity": "safe"
          },
          "violence": {
            "filtered": false,
            "severity": "safe"
          }
        }
      }
    ],
    "created": 1748843864,
    "model": "openai/gpt-4o",
    "object": "chat.completion",
    "usage": {
      "prompt_tokens": 25,
      "completion_tokens": 9,
      "total_tokens": 34,
      "prompt_tokens_details": {
        "audio_tokens": 0,
        "cached_tokens": 0
      },
      "completion_tokens_details": {
        "accepted_prediction_tokens": 0,
        "audio_tokens": 0,
        "reasoning_tokens": 0,
        "rejected_prediction_tokens": 0,
        "cached_tokens": 0
      }
    },
    "cost": {
      "interaction": {
        "prompt_tokens": 0.0000688,
        "prompt_tokens_details": {
          "standard": 0.0000688,
          "cached": 0
        },
        "completion_tokens": 0.000099,
        "completion_tokens_details": {
          "standard": 0.000099,
          "reasoning": 0,
          "cached": 0
        },
        "total": 0.0001678,
        "currency": "USD"
      },
      "integrations": {},
      "total": 0.0001678,
      "currency": "USD"
    }
  }
}

@ discourse logs:

 Back to site
DiscourseAi::Completions::Endpoints::Vllm: status: 502 - body: {"message": "Internal server error"}
8:07 am
activesupport-7.2.2.1/lib/active_support/broadcast_logger.rb:134:in `block in error' 
activesupport-7.2.2.1/lib/active_support/broadcast_logger.rb:231:in `block in dispatch' 
activesupport-7.2.2.1/lib/active_support/broadcast_logger.rb:231:in `each' 
activesupport-7.2.2.1/lib/active_support/broadcast_logger.rb:231:in `dispatch' 
activesupport-7.2.2.1/lib/active_support/broadcast_logger.rb:134:in `error' 
/var/www/discourse/plugins/discourse-ai/lib/completions/endpoints/base.rb:160:in `block (2 levels) in perform_completion!' 
net-http-0.6.0/lib/net/http.rb:2433:in `block in transport_request' 
net-http-0.6.0/lib/net/http/response.rb:320:in `reading_body' 
net-http-0.6.0/lib/net/http.rb:2430:in `transport_request' 
net-http-0.6.0/lib/net/http.rb:2384:in `request' 
rack-mini-profiler-3.3.1/lib/patches/net_patches.rb:19:in `block in request_with_mini_profiler' 
rack-mini-profiler-3.3.1/lib/mini_profiler/profiling_methods.rb:50:in `step' 
rack-mini-profiler-3.3.1/lib/patches/net_patches.rb:18:in `request_with_mini_profiler' 
/var/www/discourse/plugins/discourse-ai/lib/completions/endpoints/base.rb:158:in `block in perform_completion!' 
net-http-0.6.0/lib/net/http.rb:1632:in `start' 
net-http-0.6.0/lib/net/http.rb:1070:in `start' 
/var/www/discourse/plugins/discourse-ai/lib/completions/endpoints/base.rb:129:in `perform_completion!' 
/var/www/discourse/plugins/discourse-ai/lib/completions/llm.rb:374:in `generate' 
/var/www/discourse/plugins/discourse-ai/lib/configuration/llm_validator.rb:36:in `run_test' 
/var/www/discourse/plugins/discourse-ai/app/controllers/discourse_ai/admin/ai_llms_controller.rb:128:in `test' 
actionpack-7.2.2.1/lib/action_controller/metal/basic_implicit_render.rb:8:in `send_action' 
actionpack-7.2.2.1/lib/abstract_controller/base.rb:226:in `process_action' 
actionpack-7.2.2.1/lib/action_controller/metal/rendering.rb:193:in `process_action' 
actionpack-7.2.2.1/lib/abstract_controller/callbacks.rb:261:in `block in process_action' 
activesupport-7.2.2.1/lib/active_support/callbacks.rb:121:in `block in run_callbacks' 
/var/www/discourse/app/controllers/application_controller.rb:428:in `block in with_resolved_locale' 
i18n-1.14.7/lib/i18n.rb:353:in `with_locale' 
/var/www/discourse/app/controllers/application_controller.rb:428:in `with_resolved_locale' 
activesupport-7.2.2.1/lib/active_support/callbacks.rb:130:in `block in run_callbacks' 
activesupport-7.2.2.1/lib/active_support/callbacks.rb:141:in `run_callbacks' 
actionpack-7.2.2.1/lib/abstract_controller/callbacks.rb:260:in `process_action' 
actionpack-7.2.2.1/lib/action_controller/metal/rescue.rb:27:in `process_action' 
actionpack-7.2.2.1/lib/action_controller/metal/instrumentation.rb:77:in `block in process_action' 
activesupport-7.2.2.1/lib/active_support/notifications.rb:210:in `block in instrument' 
activesupport-7.2.2.1/lib/active_support/notifications/instrumenter.rb:58:in `instrument' 
activesupport-7.2.2.1/lib/active_support/notifications.rb:210:in `instrument' 
actionpack-7.2.2.1/lib/action_controller/metal/instrumentation.rb:76:in `process_action' 
actionpack-7.2.2.1/lib/action_controller/metal/params_wrapper.rb:259:in `process_action' 
activerecord-7.2.2.1/lib/active_record/railties/controller_runtime.rb:39:in `process_action' 
actionpack-7.2.2.1/lib/abstract_controller/base.rb:163:in `process' 
actionview-7.2.2.1/lib/action_view/rendering.rb:40:in `process' 
rack-mini-profiler-3.3.1/lib/mini_profiler/profiling_methods.rb:89:in `block in profile_method' 
actionpack-7.2.2.1/lib/action_controller/metal.rb:252:in `dispatch' 
actionpack-7.2.2.1/lib/action_controller/metal.rb:335:in `dispatch' 
actionpack-7.2.2.1/lib/action_dispatch/routing/route_set.rb:67:in `dispatch' 
actionpack-7.2.2.1/lib/action_dispatch/routing/route_set.rb:50:in `serve' 
actionpack-7.2.2.1/lib/action_dispatch/routing/mapper.rb:32:in `block in <class:Constraints>' 
actionpack-7.2.2.1/lib/action_dispatch/routing/mapper.rb:62:in `serve' 
actionpack-7.2.2.1/lib/action_dispatch/journey/router.rb:53:in `block in serve' 
actionpack-7.2.2.1/lib/action_dispatch/journey/router.rb:133:in `block in find_routes' 
actionpack-7.2.2.1/lib/action_dispatch/journey/router.rb:126:in `each' 
actionpack-7.2.2.1/lib/action_dispatch/journey/router.rb:126:in `find_routes' 
actionpack-7.2.2.1/lib/action_dispatch/journey/router.rb:34:in `serve' 
actionpack-7.2.2.1/lib/action_dispatch/routing/route_set.rb:896:in `call' 
/var/www/discourse/lib/middleware/omniauth_bypass_middleware.rb:35:in `call' 
rack-2.2.13/lib/rack/tempfile_reaper.rb:15:in `call' 
rack-2.2.13/lib/rack/conditional_get.rb:27:in `call' 
rack-2.2.13/lib/rack/head.rb:12:in `call' 
actionpack-7.2.2.1/lib/action_dispatch/http/permissions_policy.rb:38:in `call' 
/var/www/discourse/lib/content_security_policy/middleware.rb:12:in `call' 
/var/www/discourse/lib/middleware/anonymous_cache.rb:415:in `call' 
/var/www/discourse/lib/middleware/csp_script_nonce_injector.rb:12:in `call' 
/var/www/discourse/config/initializers/008-rack-cors.rb:14:in `call' 
rack-2.2.13/lib/rack/session/abstract/id.rb:266:in `context' 
rack-2.2.13/lib/rack/session/abstract/id.rb:260:in `call' 
actionpack-7.2.2.1/lib/action_dispatch/middleware/cookies.rb:704:in `call' 
actionpack-7.2.2.1/lib/action_dispatch/middleware/callbacks.rb:31:in `block in call' 
activesupport-7.2.2.1/lib/active_support/callbacks.rb:101:in `run_callbacks' 
actionpack-7.2.2.1/lib/action_dispatch/middleware/callbacks.rb:30:in `call' 
actionpack-7.2.2.1/lib/action_dispatch/middleware/debug_exceptions.rb:31:in `call' 
actionpack-7.2.2.1/lib/action_dispatch/middleware/show_exceptions.rb:32:in `call' 
logster-2.20.1/lib/logster/middleware/reporter.rb:40:in `call' 
/var/www/discourse/lib/middleware/default_headers.rb:13:in `call' 
railties-7.2.2.1/lib/rails/rack/logger.rb:41:in `call_app' 
railties-7.2.2.1/lib/rails/rack/logger.rb:29:in `call' 
/var/www/discourse/config/initializers/100-quiet_logger.rb:20:in `call' 
/var/www/discourse/config/initializers/100-silence_logger.rb:29:in `call' 
actionpack-7.2.2.1/lib/action_dispatch/middleware/request_id.rb:33:in `call' 
/var/www/discourse/lib/middleware/enforce_hostname.rb:24:in `call' 
rack-2.2.13/lib/rack/method_override.rb:24:in `call' 
actionpack-7.2.2.1/lib/action_dispatch/middleware/executor.rb:16:in `call' 
rack-2.2.13/lib/rack/sendfile.rb:110:in `call' 
rack-mini-profiler-3.3.1/lib/mini_profiler.rb:191:in `call' 
/var/www/discourse/lib/middleware/processing_request.rb:12:in `call' 
message_bus-4.4.1/lib/message_bus/rack/middleware.rb:60:in `call' 
/var/www/discourse/lib/middleware/request_tracker.rb:385:in `call' 
actionpack-7.2.2.1/lib/action_dispatch/middleware/remote_ip.rb:96:in `call' 
railties-7.2.2.1/lib/rails/engine.rb:535:in `call' 
railties-7.2.2.1/lib/rails/railtie.rb:226:in `public_send' 
railties-7.2.2.1/lib/rails/railtie.rb:226:in `method_missing' 
rack-2.2.13/lib/rack/urlmap.rb:74:in `block in call' 
rack-2.2.13/lib/rack/urlmap.rb:58:in `each' 
rack-2.2.13/lib/rack/urlmap.rb:58:in `call' 
unicorn-6.1.0/lib/unicorn/http_server.rb:634:in `process_client'
unicorn-6.1.0/lib/unicorn/http_server.rb:739:in `worker_loop'
unicorn-6.1.0/lib/unicorn/http_server.rb:547:in `spawn_missing_workers'
unicorn-6.1.0/lib/unicorn/http_server.rb:143:in `start'
unicorn-6.1.0/bin/unicorn:128:in `<top (required)>'
/var/www/discourse/vendor/bundle/ruby/3.3.0/bin/unicorn:25:in `load' 
/var/www/discourse/vendor/bundle/ruby/3.3.0/bin/unicorn:25:in `<main>' 
infobacktraceenv
 Solve  Remove  Protect  Copy  Share
 Debug
 Info
  Warning
  Error
  Fatal
Search

 Clear logs
6

大家好，

翻译器和论坛助手现在可以工作了，但“总结”按钮没有任何反应。

我在 CloudWatch 日志中没有看到任何来自 Discourse 的请求触发。

总结器配置了总结角色（Summarize Persona），并且该角色正在使用我之前在讨论中提到的 LLM 端点……

有什么提示吗？

非常感谢，祝好！

WS

7

新见解：

有些主题可以总结，有些则不行……

似乎新的主题可以总结。
另外一个问题：当我的主题包含图片，且没有图像识别 AI 时，这会是一个问题吗？

8

那是来自您自己端点的 502 :stuck_out_tongue:

主题长度可能？

这对于图像相关任务来说是个问题，例如图像字幕或帖子分类自动化。

1 个赞
9

嘿 @Falco

但是 discourse 甚至没有开始请求，也没有给出任何理由（日志，…），说明为什么它没有这样做 :frowning:
很难缩小我的选择范围

不，不是。我找到了问题（没有对来自 llm 端体的正文进行 JSON.stringify，但 discourse 可以更详细地说明 502 的原因 :-)）

谢谢，祝好，

WS

1 个赞