labring / FastGPT

FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.
https://fastgpt.in
Other
16.78k stars 4.48k forks source link

对话框发送图片报错connect ECONNREFUSED 127.0.0.1:3000 #1438

Closed xiafeng111 closed 2 weeks ago

xiafeng111 commented 4 months ago

例行检查

你的版本

问题描述, 日志截图

复现步骤

预期结果

相关截图

微信截图_20240510161424 微信截图_20240510160033

xiafeng111 commented 4 months ago

用IP地址访问fastgpt并发送图片会报422错误 微信截图_20240510163345 微信截图_20240510163254

c121914yu commented 3 months ago

看着是模型报错了,,你这地址模型访问得到?

xiafeng111 commented 3 months ago

看着是模型报错了,,你这地址模型访问得到?

正常的文字对话没有问题

c121914yu commented 3 months ago

看着是模型报错了,,你这地址模型访问得到?

正常的文字对话没有问题

文字肯定没问题呀,图片是给一个地址过去。对方访问不到你图片地址,那不就报错了

xiafeng111 commented 3 months ago

看着是模型报错了,,你这地址模型访问得到?

正常的文字对话没有问题

文字肯定没问题呀,图片是给一个地址过去。对方访问不到你图片地址,那不就报错了

如果是模型问题,对话框内应该是可以正常发送图片但是收不到返回内容吧。但目前是无法发送图片,对话内容里没有我发送的图片。

c121914yu commented 3 months ago

P地址访问fastgpt并发送图片会报422错误 微信截图_20240510163345 微信截图_20240510163254

你这个不是已经请求模型了么?

jeryfan commented 3 months ago

看着是模型报错了,,你这地址模型访问得到?

正常的文字对话没有问题

文字肯定没问题呀,图片是给一个地址过去。对方访问不到你图片地址,那不就报错了

你好,我目前也遇到了这个问题,之前通过源码部署没问题,现在通过docker-compose部署就出现这种情况,图片可以上传,但是发送就会出现楼主的这个错误,我看了下日志,错误发生在请求模型之前,通过axios请求时将图片转换成base64的过程中,而且进入容器内也是无法请求到3000端口的,请问该如何解决 image

image

image

image

stephenlzc commented 2 months ago

同样的问题,在Mac M1 Pro中,使用OrbStack部署了fastgpt和Open WebUI,使用Open WebUI上传给gpt-4o是可以正常返回的,但是在fastgpt中,出现以下错误:

image

运行日志:

[Error] 2024-06-20 11:21:45 sse error: connect ECONNREFUSED ::1:3000 { message: 'connect ECONNREFUSED ::1:3000', stack: 'Error: connect ECONNREFUSED ::1:3000\n' + ' at AxiosError.from (file:///app/node_modules/.pnpm/axios@1.5.1/node_modules/axios/lib/core/AxiosError.js:89:14)\n' + ' at RedirectableRequest.handleRequestError (file:///app/node_modules/.pnpm/axios@1.5.1/node_modules/axios/lib/adapters/http.js:593:25)\n' + ' at RedirectableRequest.emit (node:events:514:28)\n' + ' at eventHandlers. (/app/node_modules/.pnpm/follow-redirects@1.15.6/node_modules/follow-redirects/index.js:38:24)\n' + ' at ClientRequest.emit (node:events:514:28)\n' + ' at Socket.socketErrorListener (node:_http_client:501:9)\n' + ' at Socket.emit (node:events:514:28)\n' + ' at emitErrorNT (node:internal/streams/destroy:151:8)\n' + ' at emitErrorCloseNT (node:internal/streams/destroy:116:3)\n' + ' at process.processTicksAndRejections (node:internal/process/task_queues:82:21)', config: { headers: Object [AxiosHeaders] { Accept: 'application/json, text/plain, /', 'Content-Type': undefined, 'User-Agent': 'axios/1.5.1', 'Accept-Encoding': 'gzip, compress, deflate, br' }, url: 'http://localhost:3000/api/system/img/66740ed30798ad1e1b630a96', data: undefined } } [Info] 2024-06-20 11:22:00 [QA Queue] Done [Info] 2024-06-20 11:22:00 [Vector Queue] Done { message: 'connect ECONNREFUSED ::1:3000', stack: 'Error: connect ECONNREFUSED ::1:3000\n' + ' at AxiosError.from (file:///app/node_modules/.pnpm/axios@1.5.1/node_modules/axios/lib/core/AxiosError.js:89:14)\n' + ' at RedirectableRequest.handleRequestError (file:///app/node_modules/.pnpm/axios@1.5.1/node_modules/axios/lib/adapters/http.js:593:25)\n' + ' at RedirectableRequest.emit (node:events:514:28)\n' + ' at eventHandlers. (/app/node_modules/.pnpm/follow-redirects@1.15.6/node_modules/follow-redirects/index.js:38:24)\n' + ' at ClientRequest.emit (node:events:514:28)\n' + ' at Socket.socketErrorListener (node:_http_client:501:9)\n' + ' at Socket.emit (node:events:514:28)\n' + ' at emitErrorNT (node:internal/streams/destroy:151:8)\n' + ' at emitErrorCloseNT (node:internal/streams/destroy:116:3)\n' + ' at process.processTicksAndRejections (node:internal/process/task_queues:82:21)', config: { headers: Object [AxiosHeaders] { Accept: 'application/json, text/plain, /', 'Content-Type': undefined, 'User-Agent': 'axios/1.5.1', 'Accept-Encoding': 'gzip, compress, deflate, br' }, url: 'http://localhost:3000/api/system/img/66740ed30798ad1e1b630a96', data: undefined } } [Error] 2024-06-20 11:22:02 sse error: connect ECONNREFUSED ::1:3000 [Info] 2024-06-20 11:23:00 [QA Queue] Done [Info] 2024-06-20 11:23:00 [Vector Queue] Done [Info] 2024-06-20 11:24:00 [Vector Queue] Done [Info] 2024-06-20 11:24:00 [QA Queue] Done

这是在open webui中的返回结果

image

运行日志:

INFO:apps.ollama.main:get_all_models() INFO: 192.168.215.1:52744 - "GET /api/models HTTP/1.1" 200 OK INFO: 192.168.215.1:52744 - "GET /ollama/api/version HTTP/1.1" 200 OK INFO: 192.168.215.1:52752 - "GET /api/v1/users/user/settings HTTP/1.1" 200 OK INFO: 192.168.215.1:52744 - "GET /api/v1/users/user/settings HTTP/1.1" 200 OK INFO: 127.0.0.1:46606 - "GET /health HTTP/1.1" 200 OK INFO: 192.168.215.1:57834 - "POST /api/v1/chats/new HTTP/1.1" 200 OK INFO: 192.168.215.1:57834 - "GET /api/v1/chats/ HTTP/1.1" 200 OK INFO: 192.168.215.1:57834 - "POST /openai/chat/completions HTTP/1.1" 200 OK gpt-4o INFO: 192.168.215.1:57834 - "POST /api/chat/completed HTTP/1.1" 200 OK INFO: 192.168.215.1:57834 - "POST /api/v1/chats/a6bdb19d-cc7d-4228-9885-927f419ef5b5 HTTP/1.1" 200 OK INFO: 192.168.215.1:57834 - "GET /api/v1/chats/ HTTP/1.1" 200 OK generate_title gpt-4o INFO: 192.168.215.1:57834 - "POST /api/task/title/completions HTTP/1.1" 200 OK INFO: 192.168.215.1:57834 - "POST /api/v1/chats/a6bdb19d-cc7d-4228-9885-927f419ef5b5 HTTP/1.1" 200 OK INFO: 192.168.215.1:57834 - "GET /api/v1/chats/ HTTP/1.1" 200 OK INFO: 192.168.215.1:57834 - "GET /api/v1/chats/ HTTP/1.1" 200 OK ['HAh6m316YvvqAE9AAAAD'] INFO: 127.0.0.1:48030 - "GET /health HTTP/1.1" 200 OK INFO: 127.0.0.1:46064 - "GET /health HTTP/1.1" 200 OK INFO: 127.0.0.1:33206 - "GET /health HTTP/1.1" 200 OK INFO: 127.0.0.1:41288 - "GET /health HTTP/1.1" 200 OK INFO: 127.0.0.1:46538 - "GET /health HTTP/1.1" 200 OK

请确认,谢谢!

yw-2020 commented 2 months ago

同样的错误,docker部署的,4o和claude-3.5-sonnet都报错

c121914yu commented 2 weeks ago

CLose 未关联 Issue. 可升级新版,旧版的如果用 localhost docker部署无法使用,需IP 或域名模式,新版已兼容。