`HeadersTimeoutError` occurs in timeout of more than 5 mins in `fetchAdapter`

[Arthur19312]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain.js documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain.js rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

const result = await fetchAdapter(
      {
        url: this.url,
        method: "POST",
        data: JSON.stringify(request),
        headers: {
          "Content-Type":
            this.responseType === "stream"
              ? "text/event-stream"
              : "application/json",
        },
        responseType: this.responseType || "json",
        timeout: this.timeout,
      }
    ).then((res) => (this.responseType === "stream" ? res : res.data));

Error Message and Stack Trace (if applicable)

{
    "name": "HeadersTimeoutError",
    "code": "UND_ERR_HEADERS_TIMEOUT",
    "message": "Headers Timeout Error"
}

Description

HeadersTimeoutError occurs when I use timeout over 5 mins in fetchAdapter

My azure GPT api sometimes goes to 10 mins while the HeadersTimeoutError breaks the request at the 5th minute every time when I use the inner fetchAdapter

A related report is https://github.com/nodejs/node/issues/46375

System Info

Mac, Linux
node v18.17.1
yarn 3.4.1

[dosubot]

To resolve the HeadersTimeoutError when using fetchAdapter with a timeout of more than 5 minutes, you'll need to adjust the timeout parameter in your request configuration to accommodate longer response times from the Azure GPT API. Specifically, for a 10-minute timeout, set the timeout value to 600000 milliseconds in your request configuration. Here's how you can modify your existing code:

const result = await fetchAdapter(
  {
    url: this.url,
    method: "POST",
    data: JSON.stringify(request),
    headers: {
      "Content-Type": this.responseType === "stream" ? "text/event-stream" : "application/json",
    },
    responseType: this.responseType || "json",
    timeout: 600000, // Set timeout to 10 minutes in milliseconds
  }
).then((res) => (this.responseType === "stream" ? res : res.data));

This adjustment ensures that the request will not be aborted until the specified 10-minute duration has passed, allowing the Azure GPT API sufficient time to respond without triggering a HeadersTimeoutError.

Details

Sources

• langchain/src/util/axios-fetch-adapter.js
• langchain/src/util/hub.ts

About Dosu
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosu.

[Arthur19312]

要解决HeadersTimeoutError超时fetchAdapter超过 5 分钟的问题，您需要调整timeout请求配置中的参数，以适应 Azure GPT API 更长的响应时间。具体来说，对于 10 分钟的超时，请在请求配置中将该timeout值设置为毫秒。600000以下是修改现有代码的方法：

const result = await fetchAdapter(
  {
    url: this.url,
    method: "POST",
    data: JSON.stringify(request),
    headers: {
      "Content-Type": this.responseType === "stream" ? "text/event-stream" : "application/json",
    },
    responseType: this.responseType || "json",
    timeout: 600000, // Set timeout to 10 minutes in milliseconds
  }
).then((res) => (this.responseType === "stream" ? res : res.data));

此调整可确保请求在指定的 10 分钟持续时间过去之前不会中止，从而使 Azure GPT API 有足够的时间进行响应，而不会触发HeadersTimeoutError.

细节

要继续对话，请提及@dosu。

It didn't work by this @dosu

[dosubot]

If adjusting the timeout parameter to 600000 milliseconds in your fetchAdapter configuration did not resolve the HeadersTimeoutError, it suggests that the issue might not be solely related to the client-side timeout setting. Here are some steps and considerations to further troubleshoot and potentially resolve the issue:

1. Verify the Timeout Configuration: Double-check that the timeout value is correctly applied in the fetchAdapter call. The value should be in milliseconds, and for a 10-minute timeout, 600000 is correct.

2. Network and Server-Side Considerations: Network latency or server-side timeout settings could be affecting your requests. Ensure there are no network issues on your end and verify if the Azure GPT API has its own timeout settings that might be causing the connection to close prematurely.

3. Update or Patch fetchAdapter: Look for any updates to the langchainjs library or consider patching the fetchAdapter function if there's a known issue with how timeouts are handled.

4. Alternative Fetch Methods: If the problem persists, using a different method for making HTTP requests might offer more robust handling of long timeouts.

Regarding compatibility with Node v18.17.1 and Yarn 3.4.1, there are no known issues that should affect the fetchAdapter function. The fetchAdapter is designed to work within the Node environment specified and does not have known limitations on Mac systems.

If these steps do not resolve the issue, providing more details about when the error occurs could help in further diagnosing the problem.

Details

Sources

• langchain/src/util/axios-fetch-adapter.js
• langchain/src/util/hub.ts
• package.json

About Dosu
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosu.

[Arthur19312]

Finally I resolved it by adding undici fetch agent : #5245