Coder Social home page Coder Social logo

labring / fastgpt Goto Github PK

View Code? Open in Web Editor NEW
13.0K 92.0 3.3K 167.11 MB

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.

Home Page: https://fastgpt.in

License: Other

JavaScript 1.09% TypeScript 93.70% SCSS 0.97% Shell 0.04% Dockerfile 0.19% Python 1.64% HTML 2.30% Smarty 0.08%
gpt35 nextjs react openai gpt gpt-35-turbo gpt-4 llm rag

fastgpt's People

Contributors

a327958099 avatar c121914yu avatar cuisongliu avatar daxiaraoming avatar dimsky avatar entorick avatar fanux avatar fengrui-liu avatar gaord avatar hehan-wang avatar imgbot[bot] avatar kaqijiang avatar kense-lab avatar knightgao avatar kssdxw avatar leoterry-ulrica avatar linuxsuren avatar liujianglc avatar lizhuang avatar moonrailgun avatar mrxyy avatar newfish-cmyk avatar nilsjacobsen avatar stakeswky avatar textcat avatar xiao-jay avatar yangchuansheng avatar yaoyaoio avatar zjy365 avatar zuofeng59556 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

fastgpt's Issues

分享一下像我这种小白的宝塔搭建视频,录的不好,大佬们轻喷

b站跪求大佬们三连

关于为什么我录制的版本跟作者的版本不一致,不多说了。。。看作者的更新记录,hhh,我是卷不过他,我录制的时候才更新到2.8,录制完以后都要更新到4了,没办法,本人拖延症晚期~~

关于为什么要分几个小节,主要是多平台发布,每个平台对视频的时长要求不同,也顺便想坑多点流量^_^

关于为什么宝塔不用docker更方便,测试过宝塔上docker会有些乱七八糟的问题,所以就弃用宝塔docker的方式,要是想用docker的,可以看作者录制的部署,这种渣渣类视频只适合像我这种没有什么基础的小白们,逃~~~

无法登录

采用的是docker-compose部署。部署完了访问域名。直接跳转到login页面了。默认账号密码应该在哪里配置?

导入知识库数据出错

硬件环境:Mac M2芯片
软件环境:pg, mongo用的docker部署,fastgpt使用pnpm。

在知识库--知识库数据--导入--手动/文件拆分都报一样的错误:
wait - compiling /api/openapi/kb/pushData (client and server)... event - compiled successfully in 156 ms (198 modules) error: null value in column "model_id" of relation "modeldata" violates not-null constraint at Parser.parseErrorMessage (~/Work/ai/FastGPT/node_modules/.pnpm/[email protected]/node_modules/pg-protocol/dist/parser.js:287:98) at Parser.handlePacket (~/Work/ai/FastGPT/node_modules/.pnpm/[email protected]/node_modules/pg-protocol/dist/parser.js:126:29) at Parser.parse (~/Work/ai/FastGPT/node_modules/.pnpm/[email protected]/node_modules/pg-protocol/dist/parser.js:39:38) at Socket.<anonymous> (~/Work/ai/FastGPT/node_modules/.pnpm/[email protected]/node_modules/pg-protocol/dist/index.js:11:42) at Socket.emit (node:events:527:28) at addChunk (node:internal/streams/readable:324:12) at readableAddChunk (node:internal/streams/readable:297:9) at Readable.push (node:internal/streams/readable:234:10) at TCP.onStreamRead (node:internal/stream_base_commons:190:23) { length: 414, severity: 'ERROR', code: '23502', detail: 'Failing row contains (3, null, waiting, 64741167079cb0c39ba3e8d4, null, JDK 17已经于2021年3月16日如期发布。本文介绍JDK 17..., 发布版本说明\n' + '根据发布的规划,这次发布的 JDK 1..., 6474118c079cb0c39ba3e8e3).', hint: undefined, position: undefined, internalPosition: undefined, internalQuery: undefined, where: undefined, schema: 'public', table: 'modeldata', column: 'model_id', dataType: undefined, constraint: undefined, file: 'execMain.c', line: '1968', routine: 'ExecConstraints' }

麻烦帮忙看看是什么情况,谢谢!

issue

请问有考虑加入文生图功能嘛

国外服务器拉取 FastGPT镜像总是失败

Error response from daemon: Get "https://registry.cn-hangzhou.aliyuncs.com/v2/": net/http: request canceled while waiting for connection (Client.Timeout exceeded while awaiting headers)

已经配置了 dns 等。但是仍然失败。太难受了,能把镜像发布到 docker官方上吗?
https://blog.csdn.net/qq_35314762/article/details/82085864
这个方法试了
https://www.cnblogs.com/wangzy-Zj/p/16873237.html
这个也试了
死活不通。ping registry.cn-hangzhou.aliyuncs.com通
curl https://registry.cn-hangzhou.aliyuncs.com/v2/ 不通

本地部署短信为啥还要注册?而且报错

Fast GPT
InvalidAccessKeyId.NotFound: code: 404, Specified access key is not found. request id: E0C973B6-6B50-5705-83C8-08E647661E92

mac本地部署。按照提示用pnpm可以打开,但是无法完成手机号注册。

提示3000端口被占用

一台全新配置的vps,系统为ubuntu 22.04,请问如何排查?谢谢

sudo lsof -i :3000
COMMAND PID USER FD TYPE DEVICE SIZE/OFF NODE NAME
nginx 6010 root 6u IPv4 44047 0t0 TCP *:3000 (LISTEN)
nginx 6038 systemd-resolve 6u IPv4 44047 0t0 TCP *:3000 (LISTEN)
nginx 6039 systemd-resolve 6u IPv4 44047 0t0 TCP *:3000 (LISTEN)

代理的方式相对受限,能否支持修改OpenAI API Base URL呢

OpenAI API Base URL默认是https://api.openai.com,但是如果找一台能访问外网的服务器A,代理该网址。然后让本地项目的OpenAI API Base URL设置为服务器A中的网址,即可实现本地服务器无缝访问。目前这种部署方式在国内较为流行,github上也有很成熟的无脑式部署教程,如下:
https://github.com/Ice-Hazymoon/openai-scf-proxy。

故,建议支持修改OpenAI API Base URL

有考虑使用vercel一键部署吗?

看到整体技术栈是基于next.js开发的,vercel对这块儿的支持力度比较大。唯一需要考虑的是数据存储。现阶段使用的似乎是mongodb,有两个选择

  1. 使用第三方的mongodb(可能需要收费)
  2. 迁移到postgresql。vercel和neon都提供了免费的postgresql服务,可以白嫖。同时看到知识库数据也是使用postgresql,可以考虑合并,统一使用一个数据库?

增加提示词的来源信息显示。

知识库的训练数据来源,通常都会是来自外部的文档。
可能是notion、飞书、或者本地的word文件。
这样,如果给出的回答不够准确或者全面,就可以跳转到源文档去查看更完整的信息。
因为目前的知识库,已经给出了响应的提示词,但提示词目前并没有跟信息源做关联。所以是否会考虑增加这个关联。
如果愿意考虑的话,那我可以提一个PR来实现这个功能。
目前的思路,就是导入知识库的时候,临时记录一个来源,等到拆分完成后,将来源以一个特殊的字符串格式,保存到知识库中。
这样,每次响应的时候,就可以从提示词中解析出来源来渲染到页面上。

大家觉得如何呢?

管理后台

请问该项目有管理后台吗?该如何进入?

请问对vps的配置,最近要求是多少?

1c1g的低配服务器一直运行不起来:

[root@fastgpt-445487 FastGPT]# pnpm build

> [email protected] build /www/wwwroot/FastGPT
> next build

info  - Loaded env from /www/wwwroot/FastGPT/.env.local

./src/hooks/usePagination.tsx
98:6  Warning: React Hook useEffect has missing dependencies: 'defaultRequest' and 'mutate'. Either include them or remove the dependency array.  react-hooks/exhaustive-deps

./src/hooks/usePaging.ts
68:6  Warning: React Hook useEffect has a missing dependency: 'getData'. Either include it or remove the dependency array.  react-hooks/exhaustive-deps

info  - Need to disable some ESLint rules? Learn more here: https://nextjs.org/docs/basic-features/eslint#disabling-rules
info  - Linting and checking validity of types .
<--- Last few GCs --->

[4667:0x6c50340]   133280 ms: Scavenge (reduce) 471.5 (482.0) -> 470.5 (482.0) MB, 2.8 / 0.0 ms  (average mu = 0.216, current mu = 0.261) allocation failure; 
[4667:0x6c50340]   133374 ms: Scavenge (reduce) 471.5 (482.0) -> 470.6 (482.0) MB, 3.8 / 0.0 ms  (average mu = 0.216, current mu = 0.261) allocation failure; 
[4667:0x6c50340]   135086 ms: Mark-sweep (reduce) 472.0 (482.2) -> 470.6 (482.2) MB, 1612.6 / 0.0 ms  (average mu = 0.210, current mu = 0.199) allocation failure; scavenge might not succeed


<--- JS stacktrace --->

FATAL ERROR: Ineffective mark-compacts near heap limit Allocation failed - JavaScript heap out of memory
 1: 0xb7a940 node::Abort() [/www/server/nvm/versions/node/v18.16.0/bin/node]
 2: 0xa8e823  [/www/server/nvm/versions/node/v18.16.0/bin/node]
 3: 0xd5c940 v8::Utils::ReportOOMFailure(v8::internal::Isolate*, char const*, bool) [/www/server/nvm/versions/node/v18.16.0/bin/node]
 4: 0xd5cce7 v8::internal::V8::FatalProcessOutOfMemory(v8::internal::Isolate*, char const*, bool) [/www/server/nvm/versions/node/v18.16.0/bin/node]
 5: 0xf3a3e5  [/www/server/nvm/versions/node/v18.16.0/bin/node]
 6: 0xf3b2e8 v8::internal::Heap::RecomputeLimits(v8::internal::GarbageCollector) [/www/server/nvm/versions/node/v18.16.0/bin/node]
info  - Linting and checking validity of types .. 7: 0xf4b7f3  [/www/server/nvm/versions/node/v18.16.0/bin/node]
 8: 0xf4c668 v8::internal::Heap::CollectGarbage(v8::internal::AllocationSpace, v8::internal::GarbageCollectionReason, v8::GCCallbackFlags) [/www/server/nvm/versions/node/v18.16.0/bin/node]
 9: 0xf26fce v8::internal::HeapAllocator::AllocateRawWithLightRetrySlowPath(int, v8::internal::AllocationType, v8::internal::AllocationOrigin, v8::internal::AllocationAlignment) [/www/server/nvm/versions/node/v18.16.0/bin/node]
10: 0xf28397 v8::internal::HeapAllocator::AllocateRawWithRetryOrFailSlowPath(int, v8::internal::AllocationType, v8::internal::AllocationOrigin, v8::internal::AllocationAlignment) [/www/server/nvm/versions/node/v18.16.0/bin/node]
11: 0xf0956a v8::internal::Factory::NewFillerObject(int, v8::internal::AllocationAlignment, v8::internal::AllocationType, v8::internal::AllocationOrigin) [/www/server/nvm/versions/node/v18.16.0/bin/node]
12: 0x12ce7af v8::internal::Runtime_AllocateInYoungGeneration(int, unsigned long*, v8::internal::Isolate*) [/www/server/nvm/versions/node/v18.16.0/bin/node]
13: 0x16fb6b9  [/www/server/nvm/versions/node/v18.16.0/bin/node]
info  - Linting and checking validity of types .

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.