From fa3ad007b3f582c403178dbbda18a6f3735a0470 Mon Sep 17 00:00:00 2001 From: janiussyafiq Date: Thu, 9 Apr 2026 14:48:54 +0800 Subject: [PATCH 1/4] docs(ai-proxy): clarify logging options apply to structured access logs, not error.log --- docs/en/latest/plugins/ai-proxy-multi.md | 6 +++--- docs/en/latest/plugins/ai-proxy.md | 6 +++--- docs/zh/latest/plugins/ai-proxy-multi.md | 6 +++--- docs/zh/latest/plugins/ai-proxy.md | 6 +++--- 4 files changed, 12 insertions(+), 12 deletions(-) diff --git a/docs/en/latest/plugins/ai-proxy-multi.md b/docs/en/latest/plugins/ai-proxy-multi.md index 0c59fcb34fa2..f6cb0021c9c2 100644 --- a/docs/en/latest/plugins/ai-proxy-multi.md +++ b/docs/en/latest/plugins/ai-proxy-multi.md @@ -37,7 +37,7 @@ description: The ai-proxy-multi Plugin extends the capabilities of ai-proxy with The `ai-proxy-multi` Plugin simplifies access to LLM and embedding models by transforming Plugin configurations into the designated request format for OpenAI, DeepSeek, Azure, AIMLAPI, Anthropic, OpenRouter, Gemini, Vertex AI, and other OpenAI-compatible APIs. It extends the capabilities of [`ai-proxy`](./ai-proxy.md) with load balancing, retries, fallbacks, and health checks. -In addition, the Plugin also supports logging LLM request information in the access log, such as token usage, model, time to the first response, and more. +In addition, the Plugin also supports appending LLM request information to structured access log entries, such as token usage, model, time to the first response, and more. These structured entries are consumed by logging plugins such as `http-logger` and `kafka-logger`, and are separate from the debug messages written to `error.log`. ## Request Format @@ -74,8 +74,8 @@ In addition, the Plugin also supports logging LLM request information in the acc | instances.options | object | False | | | Model configurations. In addition to `model`, you can configure additional parameters and they will be forwarded to the upstream LLM service in the request body. For instance, if you are working with OpenAI, DeepSeek, or AIMLAPI, you can configure additional parameters such as `max_tokens`, `temperature`, `top_p`, and `stream`. See your LLM provider's API documentation for more available options. | | instances.options.model | string | False | | | Name of the LLM model, such as `gpt-4` or `gpt-3.5`. See your LLM provider's API documentation for more available models. | | logging | object | False | | | Logging configurations. | -| logging.summaries | boolean | False | false | | If true, log request LLM model, duration, request, and response tokens. | -| logging.payloads | boolean | False | false | | If true, log request and response payload. | +| logging.summaries | boolean | False | false | | If true, appends LLM model, duration, request tokens, and response tokens to the structured access log entry for use by logging plugins (e.g. `http-logger`, `kafka-logger`). Does not affect `error.log`. | +| logging.payloads | boolean | False | false | | If true, appends the request and response payload to the structured access log entry for use by logging plugins (e.g. `http-logger`, `kafka-logger`). Does not affect `error.log`. | | logging.override | object | False | | | Override setting. | | logging.override.endpoint | string | False | | | LLM provider endpoint to replace the default endpoint with. If not configured, the Plugin uses the default OpenAI endpoint `https://api.openai.com/v1/chat/completions`. | | checks | object | False | | | Health check configurations. Note that at the moment, OpenAI, DeepSeek, and AIMLAPI do not provide an official health check endpoint. Other LLM services that you can configure under `openai-compatible` provider may have available health check endpoints. | diff --git a/docs/en/latest/plugins/ai-proxy.md b/docs/en/latest/plugins/ai-proxy.md index 56bc7e1f081d..4f5dfa9b8cb8 100644 --- a/docs/en/latest/plugins/ai-proxy.md +++ b/docs/en/latest/plugins/ai-proxy.md @@ -37,7 +37,7 @@ description: The ai-proxy Plugin simplifies access to LLM and embedding models p The `ai-proxy` Plugin simplifies access to LLM and embedding models by transforming Plugin configurations into the designated request format. It supports the integration with OpenAI, DeepSeek, Azure, AIMLAPI, Anthropic, OpenRouter, Gemini, Vertex AI, and other OpenAI-compatible APIs. -In addition, the Plugin also supports logging LLM request information in the access log, such as token usage, model, time to the first response, and more. +In addition, the Plugin also supports appending LLM request information to structured access log entries, such as token usage, model, time to the first response, and more. These structured entries are consumed by logging plugins such as `http-logger` and `kafka-logger`, and are separate from the debug messages written to `error.log` ## Request Format @@ -67,8 +67,8 @@ In addition, the Plugin also supports logging LLM request information in the acc | override | object | False | | | Override setting. | | override.endpoint | string | False | | | Custom LLM provider endpoint, required when `provider` is `openai-compatible`. | | logging | object | False | | | Logging configurations. | -| logging.summaries | boolean | False | false | | If true, logs request LLM model, duration, request, and response tokens. | -| logging.payloads | boolean | False | false | | If true, logs request and response payload. | +| logging.summaries | boolean | False | false | | If true, appends LLM model, duration, request tokens, and response tokens to structured access log entry for use by logging plugins (e.g. `http-logger`, `kafka-logger`). Does not affect `error.log`. | +| logging.payloads | boolean | False | false | | If true, appends the request and response payload to the structured access log entry for use by logging plugins (e.g. `http-logger`, `kafka-logger`). Does not affect `error.log`. | | timeout | integer | False | 30000 | ≥ 1 | Request timeout in milliseconds when requesting the LLM service. | | keepalive | boolean | False | true | | If true, keeps the connection alive when requesting the LLM service. | | keepalive_timeout | integer | False | 60000 | ≥ 1000 | Keepalive timeout in milliseconds when connecting to the LLM service. | diff --git a/docs/zh/latest/plugins/ai-proxy-multi.md b/docs/zh/latest/plugins/ai-proxy-multi.md index 3f108cace7f0..4f534010468b 100644 --- a/docs/zh/latest/plugins/ai-proxy-multi.md +++ b/docs/zh/latest/plugins/ai-proxy-multi.md @@ -37,7 +37,7 @@ description: ai-proxy-multi 插件通过负载均衡、重试、故障转移和 `ai-proxy-multi` 插件通过将插件配置转换为 OpenAI、DeepSeek、Azure、AIMLAPI、Anthropic、OpenRouter、Gemini、Vertex AI 和其他 OpenAI 兼容 API 的指定请求格式，简化了对 LLM 和嵌入模型的访问。它通过负载均衡、重试、故障转移和健康检查扩展了 [`ai-proxy`](./ai-proxy.md) 的功能。 -此外，该插件还支持在访问日志中记录 LLM 请求信息，如令牌使用量、模型、首次响应时间等。 +此外，该插件还支持将 LLM 请求信息追加到结构化访问日志条目中，如令牌使用量、模型、首次响应时间等。这些结构化条目由 `http-logger`、`kafka-logger` 等日志插件消费，与写入 `error.log` 的调试消息相互独立。 ## 请求格式 @@ -74,8 +74,8 @@ description: ai-proxy-multi 插件通过负载均衡、重试、故障转移和 | instances.options | object | 否 | | | 模型配置。除了 `model` 之外，您还可以配置其他参数，它们将在请求体中转发到上游 LLM 服务。例如，如果您使用 OpenAI、DeepSeek 或 AIMLAPI，可以配置其他参数，如 `max_tokens`、`temperature`、`top_p` 和 `stream`。有关更多可用选项，请参阅您的 LLM 提供商的 API 文档。 | | instances.options.model | string | 否 | | | LLM 模型的名称，如 `gpt-4` 或 `gpt-3.5`。有关更多可用模型，请参阅您的 LLM 提供商的 API 文档。 | | logging | object | 否 | | | 日志配置。 | -| logging.summaries | boolean | 否 | false | | 如果为 true，记录请求 LLM 模型、持续时间、请求和响应令牌。 | -| logging.payloads | boolean | 否 | false | | 如果为 true，记录请求和响应负载。 | +| logging.summaries | boolean | 否 | false | | 如果为 true，将 LLM 模型、持续时间、请求令牌和响应令牌追加到结构化访问日志条目中，供 `http-logger`、`kafka-logger` 等日志插件使用。不影响 `error.log`。 | +| logging.payloads | boolean | 否 | false | | 如果为 true，将请求和响应负载追加到结构化访问日志条目中，供 `http-logger`、`kafka-logger` 等日志插件使用。不影响 `error.log`。 | | logging.override | object | 否 | | | 覆盖设置。 | | logging.override.endpoint | string | 否 | | | 用于替换默认端点的 LLM 提供商端点。如果未配置，插件使用默认的 OpenAI 端点 `https://api.openai.com/v1/chat/completions`。 | | checks | object | 否 | | | 健康检查配置。请注意，目前 OpenAI、DeepSeek 和 AIMLAPI 不提供官方健康检查端点。您可以在 `openai-compatible` 提供商下配置的其他 LLM 服务可能有可用的健康检查端点。 | diff --git a/docs/zh/latest/plugins/ai-proxy.md b/docs/zh/latest/plugins/ai-proxy.md index f59e2f76bfb3..500357ae448c 100644 --- a/docs/zh/latest/plugins/ai-proxy.md +++ b/docs/zh/latest/plugins/ai-proxy.md @@ -37,7 +37,7 @@ description: ai-proxy 插件通过将插件配置转换为所需的请求格式 `ai-proxy` 插件通过将插件配置转换为指定的请求格式，简化了对 LLM 和嵌入模型的访问。它支持与 OpenAI、DeepSeek、Azure、AIMLAPI、Anthropic、OpenRouter、Gemini、Vertex AI 和其他 OpenAI 兼容的 API 集成。 -此外，该插件还支持在访问日志中记录 LLM 请求信息，如令牌使用量、模型、首次响应时间等。 +此外，该插件还支持将 LLM 请求信息追加到结构化访问日志条目中，如令牌使用量、模型、首次响应时间等。这些结构化条目由 `http-logger`、`kafka-logger` 等日志插件消费，与写入 `error.log` 的调试消息相互独立。 ## 请求格式 @@ -67,8 +67,8 @@ description: ai-proxy 插件通过将插件配置转换为所需的请求格式 | override | object | 否 | | | 覆盖设置。 | | override.endpoint | string | 否 | | | 自定义 LLM 提供商端点，当 `provider` 为 `openai-compatible` 时必需。 | | logging | object | 否 | | | 日志配置。 | -| logging.summaries | boolean | 否 | false | | 如果为 true，记录请求 LLM 模型、持续时间、请求和响应令牌。 | -| logging.payloads | boolean | 否 | false | | 如果为 true，记录请求和响应负载。 | +| logging.summaries | boolean | 否 | false | | 如果为 true，将 LLM 模型、持续时间、请求令牌和响应令牌追加到结构化访问日志条目中，供 `http-logger`、`kafka-logger` 等日志插件使用。不影响 `error.log`。 | +| logging.payloads | boolean | 否 | false | | 如果为 true，将请求和响应负载追加到结构化访问日志条目中，供 `http-logger`、`kafka-logger` 等日志插件使用。不影响 `error.log`。 | | timeout | integer | 否 | 30000 | ≥ 1 | 请求 LLM 服务时的请求超时时间（毫秒）。 | | keepalive | boolean | 否 | true | | 如果为 true，在请求 LLM 服务时保持连接活跃。 | | keepalive_timeout | integer | 否 | 60000 | ≥ 1000 | 连接到 LLM 服务时的保活超时时间（毫秒）。 | From 0e77cd6f8ac9a97b9ed862041a9bda70bf9546d6 Mon Sep 17 00:00:00 2001 From: janiussyafiq Date: Fri, 10 Apr 2026 11:49:13 +0800 Subject: [PATCH 2/4] refine wording --- docs/en/latest/plugins/ai-proxy-multi.md | 6 +++--- docs/en/latest/plugins/ai-proxy.md | 6 +++--- docs/zh/latest/plugins/ai-proxy-multi.md | 6 +++--- docs/zh/latest/plugins/ai-proxy.md | 6 +++--- 4 files changed, 12 insertions(+), 12 deletions(-) diff --git a/docs/en/latest/plugins/ai-proxy-multi.md b/docs/en/latest/plugins/ai-proxy-multi.md index f6cb0021c9c2..956078b612d9 100644 --- a/docs/en/latest/plugins/ai-proxy-multi.md +++ b/docs/en/latest/plugins/ai-proxy-multi.md @@ -37,7 +37,7 @@ description: The ai-proxy-multi Plugin extends the capabilities of ai-proxy with The `ai-proxy-multi` Plugin simplifies access to LLM and embedding models by transforming Plugin configurations into the designated request format for OpenAI, DeepSeek, Azure, AIMLAPI, Anthropic, OpenRouter, Gemini, Vertex AI, and other OpenAI-compatible APIs. It extends the capabilities of [`ai-proxy`](./ai-proxy.md) with load balancing, retries, fallbacks, and health checks. -In addition, the Plugin also supports appending LLM request information to structured access log entries, such as token usage, model, time to the first response, and more. These structured entries are consumed by logging plugins such as `http-logger` and `kafka-logger`, and are separate from the debug messages written to `error.log`. +In addition, the Plugin also supports logging LLM request information in the access log, such as token usage, model, time to the first response, and more. These log entries are also consumed by logging plugins such as `http-logger` and `kafka-logger`. These options do not affect `error.log`. ## Request Format @@ -74,8 +74,8 @@ In addition, the Plugin also supports appending LLM request information to struc | instances.options | object | False | | | Model configurations. In addition to `model`, you can configure additional parameters and they will be forwarded to the upstream LLM service in the request body. For instance, if you are working with OpenAI, DeepSeek, or AIMLAPI, you can configure additional parameters such as `max_tokens`, `temperature`, `top_p`, and `stream`. See your LLM provider's API documentation for more available options. | | instances.options.model | string | False | | | Name of the LLM model, such as `gpt-4` or `gpt-3.5`. See your LLM provider's API documentation for more available models. | | logging | object | False | | | Logging configurations. | -| logging.summaries | boolean | False | false | | If true, appends LLM model, duration, request tokens, and response tokens to the structured access log entry for use by logging plugins (e.g. `http-logger`, `kafka-logger`). Does not affect `error.log`. | -| logging.payloads | boolean | False | false | | If true, appends the request and response payload to the structured access log entry for use by logging plugins (e.g. `http-logger`, `kafka-logger`). Does not affect `error.log`. | +| logging.summaries | boolean | False | false | | If true, logs request LLM model, duration, request, and response tokens. Does not affect `error.log`. | +| logging.payloads | boolean | False | false | | If true, logs request and response payload. Does not affect `error.log`. | | logging.override | object | False | | | Override setting. | | logging.override.endpoint | string | False | | | LLM provider endpoint to replace the default endpoint with. If not configured, the Plugin uses the default OpenAI endpoint `https://api.openai.com/v1/chat/completions`. | | checks | object | False | | | Health check configurations. Note that at the moment, OpenAI, DeepSeek, and AIMLAPI do not provide an official health check endpoint. Other LLM services that you can configure under `openai-compatible` provider may have available health check endpoints. | diff --git a/docs/en/latest/plugins/ai-proxy.md b/docs/en/latest/plugins/ai-proxy.md index 4f5dfa9b8cb8..4b54d1c0d0c5 100644 --- a/docs/en/latest/plugins/ai-proxy.md +++ b/docs/en/latest/plugins/ai-proxy.md @@ -37,7 +37,7 @@ description: The ai-proxy Plugin simplifies access to LLM and embedding models p The `ai-proxy` Plugin simplifies access to LLM and embedding models by transforming Plugin configurations into the designated request format. It supports the integration with OpenAI, DeepSeek, Azure, AIMLAPI, Anthropic, OpenRouter, Gemini, Vertex AI, and other OpenAI-compatible APIs. -In addition, the Plugin also supports appending LLM request information to structured access log entries, such as token usage, model, time to the first response, and more. These structured entries are consumed by logging plugins such as `http-logger` and `kafka-logger`, and are separate from the debug messages written to `error.log` +In addition, the Plugin also supports logging LLM request information in the access log, such as token usage, model, time to the first response, and more. These log entries are also consumed by logging plugins such as `http-logger` and `kafka-logger`. These options do not affect `error.log`. ## Request Format @@ -67,8 +67,8 @@ In addition, the Plugin also supports appending LLM request information to struc | override | object | False | | | Override setting. | | override.endpoint | string | False | | | Custom LLM provider endpoint, required when `provider` is `openai-compatible`. | | logging | object | False | | | Logging configurations. | -| logging.summaries | boolean | False | false | | If true, appends LLM model, duration, request tokens, and response tokens to structured access log entry for use by logging plugins (e.g. `http-logger`, `kafka-logger`). Does not affect `error.log`. | -| logging.payloads | boolean | False | false | | If true, appends the request and response payload to the structured access log entry for use by logging plugins (e.g. `http-logger`, `kafka-logger`). Does not affect `error.log`. | +| logging.summaries | boolean | False | false | | If true, logs request LLM model, duration, request, and response tokens. Does not affect `error.log`. | +| logging.payloads | boolean | False | false | | If true, logs request and response payload. Does not affect `error.log`. | | timeout | integer | False | 30000 | ≥ 1 | Request timeout in milliseconds when requesting the LLM service. | | keepalive | boolean | False | true | | If true, keeps the connection alive when requesting the LLM service. | | keepalive_timeout | integer | False | 60000 | ≥ 1000 | Keepalive timeout in milliseconds when connecting to the LLM service. | diff --git a/docs/zh/latest/plugins/ai-proxy-multi.md b/docs/zh/latest/plugins/ai-proxy-multi.md index 4f534010468b..2d0b2de0d99c 100644 --- a/docs/zh/latest/plugins/ai-proxy-multi.md +++ b/docs/zh/latest/plugins/ai-proxy-multi.md @@ -37,7 +37,7 @@ description: ai-proxy-multi 插件通过负载均衡、重试、故障转移和 `ai-proxy-multi` 插件通过将插件配置转换为 OpenAI、DeepSeek、Azure、AIMLAPI、Anthropic、OpenRouter、Gemini、Vertex AI 和其他 OpenAI 兼容 API 的指定请求格式，简化了对 LLM 和嵌入模型的访问。它通过负载均衡、重试、故障转移和健康检查扩展了 [`ai-proxy`](./ai-proxy.md) 的功能。 -此外，该插件还支持将 LLM 请求信息追加到结构化访问日志条目中，如令牌使用量、模型、首次响应时间等。这些结构化条目由 `http-logger`、`kafka-logger` 等日志插件消费，与写入 `error.log` 的调试消息相互独立。 +此外，该插件还支持在访问日志中记录 LLM 请求信息，如令牌使用量、模型、首次响应时间等。这些日志条目也会被 `http-logger`、`kafka-logger` 等日志插件消费。这些选项不影响 `error.log`。 ## 请求格式 @@ -74,8 +74,8 @@ description: ai-proxy-multi 插件通过负载均衡、重试、故障转移和 | instances.options | object | 否 | | | 模型配置。除了 `model` 之外，您还可以配置其他参数，它们将在请求体中转发到上游 LLM 服务。例如，如果您使用 OpenAI、DeepSeek 或 AIMLAPI，可以配置其他参数，如 `max_tokens`、`temperature`、`top_p` 和 `stream`。有关更多可用选项，请参阅您的 LLM 提供商的 API 文档。 | | instances.options.model | string | 否 | | | LLM 模型的名称，如 `gpt-4` 或 `gpt-3.5`。有关更多可用模型，请参阅您的 LLM 提供商的 API 文档。 | | logging | object | 否 | | | 日志配置。 | -| logging.summaries | boolean | 否 | false | | 如果为 true，将 LLM 模型、持续时间、请求令牌和响应令牌追加到结构化访问日志条目中，供 `http-logger`、`kafka-logger` 等日志插件使用。不影响 `error.log`。 | -| logging.payloads | boolean | 否 | false | | 如果为 true，将请求和响应负载追加到结构化访问日志条目中，供 `http-logger`、`kafka-logger` 等日志插件使用。不影响 `error.log`。 | +| logging.summaries | boolean | 否 | false | | 如果为 true，记录请求 LLM 模型、持续时间、请求和响应令牌。不影响 `error.log`。 | +| logging.payloads | boolean | 否 | false | | 如果为 true，记录请求和响应负载。不影响 `error.log`。 | | logging.override | object | 否 | | | 覆盖设置。 | | logging.override.endpoint | string | 否 | | | 用于替换默认端点的 LLM 提供商端点。如果未配置，插件使用默认的 OpenAI 端点 `https://api.openai.com/v1/chat/completions`。 | | checks | object | 否 | | | 健康检查配置。请注意，目前 OpenAI、DeepSeek 和 AIMLAPI 不提供官方健康检查端点。您可以在 `openai-compatible` 提供商下配置的其他 LLM 服务可能有可用的健康检查端点。 | diff --git a/docs/zh/latest/plugins/ai-proxy.md b/docs/zh/latest/plugins/ai-proxy.md index 500357ae448c..bc1ec03a8372 100644 --- a/docs/zh/latest/plugins/ai-proxy.md +++ b/docs/zh/latest/plugins/ai-proxy.md @@ -37,7 +37,7 @@ description: ai-proxy 插件通过将插件配置转换为所需的请求格式 `ai-proxy` 插件通过将插件配置转换为指定的请求格式，简化了对 LLM 和嵌入模型的访问。它支持与 OpenAI、DeepSeek、Azure、AIMLAPI、Anthropic、OpenRouter、Gemini、Vertex AI 和其他 OpenAI 兼容的 API 集成。 -此外，该插件还支持将 LLM 请求信息追加到结构化访问日志条目中，如令牌使用量、模型、首次响应时间等。这些结构化条目由 `http-logger`、`kafka-logger` 等日志插件消费，与写入 `error.log` 的调试消息相互独立。 +此外，该插件还支持在访问日志中记录 LLM 请求信息，如令牌使用量、模型、首次响应时间等。这些日志条目也会被 `http-logger`、`kafka-logger` 等日志插件消费。这些选项不影响 `error.log`。 ## 请求格式 @@ -67,8 +67,8 @@ description: ai-proxy 插件通过将插件配置转换为所需的请求格式 | override | object | 否 | | | 覆盖设置。 | | override.endpoint | string | 否 | | | 自定义 LLM 提供商端点，当 `provider` 为 `openai-compatible` 时必需。 | | logging | object | 否 | | | 日志配置。 | -| logging.summaries | boolean | 否 | false | | 如果为 true，将 LLM 模型、持续时间、请求令牌和响应令牌追加到结构化访问日志条目中，供 `http-logger`、`kafka-logger` 等日志插件使用。不影响 `error.log`。 | -| logging.payloads | boolean | 否 | false | | 如果为 true，将请求和响应负载追加到结构化访问日志条目中，供 `http-logger`、`kafka-logger` 等日志插件使用。不影响 `error.log`。 | +| logging.summaries | boolean | 否 | false | | 如果为 true，记录请求 LLM 模型、持续时间、请求和响应令牌。不影响 `error.log`。 | +| logging.payloads | boolean | 否 | false | | 如果为 true，记录请求和响应负载。不影响 `error.log`。 | | timeout | integer | 否 | 30000 | ≥ 1 | 请求 LLM 服务时的请求超时时间（毫秒）。 | | keepalive | boolean | 否 | true | | 如果为 true，在请求 LLM 服务时保持连接活跃。 | | keepalive_timeout | integer | 否 | 60000 | ≥ 1000 | 连接到 LLM 服务时的保活超时时间（毫秒）。 | From a5eb138bc52f0140d94f2a7e81e9c1d3af243a66 Mon Sep 17 00:00:00 2001 From: janiussyafiq Date: Fri, 10 Apr 2026 12:09:58 +0800 Subject: [PATCH 3/4] put info in parent --- docs/en/latest/plugins/ai-proxy-multi.md | 6 +++--- docs/en/latest/plugins/ai-proxy.md | 6 +++--- docs/zh/latest/plugins/ai-proxy-multi.md | 6 +++--- docs/zh/latest/plugins/ai-proxy.md | 6 +++--- 4 files changed, 12 insertions(+), 12 deletions(-) diff --git a/docs/en/latest/plugins/ai-proxy-multi.md b/docs/en/latest/plugins/ai-proxy-multi.md index 956078b612d9..00d2786f14f0 100644 --- a/docs/en/latest/plugins/ai-proxy-multi.md +++ b/docs/en/latest/plugins/ai-proxy-multi.md @@ -73,9 +73,9 @@ In addition, the Plugin also supports logging LLM request information in the acc | instances.auth.gcp.expire_early_secs| integer | False | 60 | minimum = 0 | Seconds to expire the access token before its actual expiration time to avoid edge cases. | | instances.options | object | False | | | Model configurations. In addition to `model`, you can configure additional parameters and they will be forwarded to the upstream LLM service in the request body. For instance, if you are working with OpenAI, DeepSeek, or AIMLAPI, you can configure additional parameters such as `max_tokens`, `temperature`, `top_p`, and `stream`. See your LLM provider's API documentation for more available options. | | instances.options.model | string | False | | | Name of the LLM model, such as `gpt-4` or `gpt-3.5`. See your LLM provider's API documentation for more available models. | -| logging | object | False | | | Logging configurations. | -| logging.summaries | boolean | False | false | | If true, logs request LLM model, duration, request, and response tokens. Does not affect `error.log`. | -| logging.payloads | boolean | False | false | | If true, logs request and response payload. Does not affect `error.log`. | +| logging | object | False | | | Logging configurations. Does not affect `error.log`. | +| logging.summaries | boolean | False | false | | If true, logs request LLM model, duration, request, and response tokens. | +| logging.payloads | boolean | False | false | | If true, logs request and response payload. | | logging.override | object | False | | | Override setting. | | logging.override.endpoint | string | False | | | LLM provider endpoint to replace the default endpoint with. If not configured, the Plugin uses the default OpenAI endpoint `https://api.openai.com/v1/chat/completions`. | | checks | object | False | | | Health check configurations. Note that at the moment, OpenAI, DeepSeek, and AIMLAPI do not provide an official health check endpoint. Other LLM services that you can configure under `openai-compatible` provider may have available health check endpoints. | diff --git a/docs/en/latest/plugins/ai-proxy.md b/docs/en/latest/plugins/ai-proxy.md index 4b54d1c0d0c5..dab9f784e2c5 100644 --- a/docs/en/latest/plugins/ai-proxy.md +++ b/docs/en/latest/plugins/ai-proxy.md @@ -66,9 +66,9 @@ In addition, the Plugin also supports logging LLM request information in the acc | options.model | string | False | | | Name of the LLM model, such as `gpt-4` or `gpt-3.5`. Refer to the LLM provider's API documentation for available models. | | override | object | False | | | Override setting. | | override.endpoint | string | False | | | Custom LLM provider endpoint, required when `provider` is `openai-compatible`. | -| logging | object | False | | | Logging configurations. | -| logging.summaries | boolean | False | false | | If true, logs request LLM model, duration, request, and response tokens. Does not affect `error.log`. | -| logging.payloads | boolean | False | false | | If true, logs request and response payload. Does not affect `error.log`. | +| logging | object | False | | | Logging configurations. Does not affect `error.log`. | +| logging.summaries | boolean | False | false | | If true, logs request LLM model, duration, request, and response tokens. | +| logging.payloads | boolean | False | false | | If true, logs request and response payload. | | timeout | integer | False | 30000 | ≥ 1 | Request timeout in milliseconds when requesting the LLM service. | | keepalive | boolean | False | true | | If true, keeps the connection alive when requesting the LLM service. | | keepalive_timeout | integer | False | 60000 | ≥ 1000 | Keepalive timeout in milliseconds when connecting to the LLM service. | diff --git a/docs/zh/latest/plugins/ai-proxy-multi.md b/docs/zh/latest/plugins/ai-proxy-multi.md index 2d0b2de0d99c..37602241a6fb 100644 --- a/docs/zh/latest/plugins/ai-proxy-multi.md +++ b/docs/zh/latest/plugins/ai-proxy-multi.md @@ -73,9 +73,9 @@ description: ai-proxy-multi 插件通过负载均衡、重试、故障转移和 | instances.auth.gcp.expire_early_secs| integer | 否 | 60 | minimum = 0 | 在访问令牌实际过期时间之前使其过期的秒数，以避免边缘情况。 | | instances.options | object | 否 | | | 模型配置。除了 `model` 之外，您还可以配置其他参数，它们将在请求体中转发到上游 LLM 服务。例如，如果您使用 OpenAI、DeepSeek 或 AIMLAPI，可以配置其他参数，如 `max_tokens`、`temperature`、`top_p` 和 `stream`。有关更多可用选项，请参阅您的 LLM 提供商的 API 文档。 | | instances.options.model | string | 否 | | | LLM 模型的名称，如 `gpt-4` 或 `gpt-3.5`。有关更多可用模型，请参阅您的 LLM 提供商的 API 文档。 | -| logging | object | 否 | | | 日志配置。 | -| logging.summaries | boolean | 否 | false | | 如果为 true，记录请求 LLM 模型、持续时间、请求和响应令牌。不影响 `error.log`。 | -| logging.payloads | boolean | 否 | false | | 如果为 true，记录请求和响应负载。不影响 `error.log`。 | +| logging | object | 否 | | | 日志配置。不影响 `error.log`。 | +| logging.summaries | boolean | 否 | false | | 如果为 true，记录请求 LLM 模型、持续时间、请求和响应令牌。 | +| logging.payloads | boolean | 否 | false | | 如果为 true，记录请求和响应负载。 | | logging.override | object | 否 | | | 覆盖设置。 | | logging.override.endpoint | string | 否 | | | 用于替换默认端点的 LLM 提供商端点。如果未配置，插件使用默认的 OpenAI 端点 `https://api.openai.com/v1/chat/completions`。 | | checks | object | 否 | | | 健康检查配置。请注意，目前 OpenAI、DeepSeek 和 AIMLAPI 不提供官方健康检查端点。您可以在 `openai-compatible` 提供商下配置的其他 LLM 服务可能有可用的健康检查端点。 | diff --git a/docs/zh/latest/plugins/ai-proxy.md b/docs/zh/latest/plugins/ai-proxy.md index bc1ec03a8372..ebf27332bc9a 100644 --- a/docs/zh/latest/plugins/ai-proxy.md +++ b/docs/zh/latest/plugins/ai-proxy.md @@ -66,9 +66,9 @@ description: ai-proxy 插件通过将插件配置转换为所需的请求格式 | options.model | string | 否 | | | LLM 模型的名称，如 `gpt-4` 或 `gpt-3.5`。请参阅 LLM 提供商的 API 文档以了解可用模型。 | | override | object | 否 | | | 覆盖设置。 | | override.endpoint | string | 否 | | | 自定义 LLM 提供商端点，当 `provider` 为 `openai-compatible` 时必需。 | -| logging | object | 否 | | | 日志配置。 | -| logging.summaries | boolean | 否 | false | | 如果为 true，记录请求 LLM 模型、持续时间、请求和响应令牌。不影响 `error.log`。 | -| logging.payloads | boolean | 否 | false | | 如果为 true，记录请求和响应负载。不影响 `error.log`。 | +| logging | object | 否 | | | 日志配置。不影响 `error.log`。 | +| logging.summaries | boolean | 否 | false | | 如果为 true，记录请求 LLM 模型、持续时间、请求和响应令牌。 | +| logging.payloads | boolean | 否 | false | | 如果为 true，记录请求和响应负载。 | | timeout | integer | 否 | 30000 | ≥ 1 | 请求 LLM 服务时的请求超时时间（毫秒）。 | | keepalive | boolean | 否 | true | | 如果为 true，在请求 LLM 服务时保持连接活跃。 | | keepalive_timeout | integer | 否 | 60000 | ≥ 1000 | 连接到 LLM 服务时的保活超时时间（毫秒）。 | From c43ecbea9c9201a9626dff52d82b1a66f1a79546 Mon Sep 17 00:00:00 2001 From: Traky Deng Date: Fri, 10 Apr 2026 12:22:31 +0800 Subject: [PATCH 4/4] Apply suggestions from review Co-authored-by: Traky Deng --- docs/en/latest/plugins/ai-proxy-multi.md | 2 +- docs/zh/latest/plugins/ai-proxy-multi.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/en/latest/plugins/ai-proxy-multi.md b/docs/en/latest/plugins/ai-proxy-multi.md index 00d2786f14f0..295acca84c71 100644 --- a/docs/en/latest/plugins/ai-proxy-multi.md +++ b/docs/en/latest/plugins/ai-proxy-multi.md @@ -37,7 +37,7 @@ description: The ai-proxy-multi Plugin extends the capabilities of ai-proxy with The `ai-proxy-multi` Plugin simplifies access to LLM and embedding models by transforming Plugin configurations into the designated request format for OpenAI, DeepSeek, Azure, AIMLAPI, Anthropic, OpenRouter, Gemini, Vertex AI, and other OpenAI-compatible APIs. It extends the capabilities of [`ai-proxy`](./ai-proxy.md) with load balancing, retries, fallbacks, and health checks. -In addition, the Plugin also supports logging LLM request information in the access log, such as token usage, model, time to the first response, and more. These log entries are also consumed by logging plugins such as `http-logger` and `kafka-logger`. These options do not affect `error.log`. +In addition, the Plugin also supports logging LLM request information in the access log, such as token usage, model, time to the first response, and more. These log entries are also consumed by logging plugins such as `http-logger` and `kafka-logger`, and do not affect error log. ## Request Format diff --git a/docs/zh/latest/plugins/ai-proxy-multi.md b/docs/zh/latest/plugins/ai-proxy-multi.md index 37602241a6fb..c1ca7f8c7c65 100644 --- a/docs/zh/latest/plugins/ai-proxy-multi.md +++ b/docs/zh/latest/plugins/ai-proxy-multi.md @@ -37,7 +37,7 @@ description: ai-proxy-multi 插件通过负载均衡、重试、故障转移和 `ai-proxy-multi` 插件通过将插件配置转换为 OpenAI、DeepSeek、Azure、AIMLAPI、Anthropic、OpenRouter、Gemini、Vertex AI 和其他 OpenAI 兼容 API 的指定请求格式，简化了对 LLM 和嵌入模型的访问。它通过负载均衡、重试、故障转移和健康检查扩展了 [`ai-proxy`](./ai-proxy.md) 的功能。 -此外，该插件还支持在访问日志中记录 LLM 请求信息，如令牌使用量、模型、首次响应时间等。这些日志条目也会被 `http-logger`、`kafka-logger` 等日志插件消费。这些选项不影响 `error.log`。 +此外，该插件还支持在访问日志中记录 LLM 请求信息，如令牌使用量、模型、首次响应时间等。这些日志条目也会被 `http-logger`、`kafka-logger` 等日志插件消费，但不影响 `error.log`。 ## 请求格式