Git Product home page Git Product logo

chatgpt-vercel's Issues

Run `npm config delete prefix` or `nvm use --delete-prefix v18.0.0` to unset it.

使用CloudFlare配置Pages项目,刚开始提示Node版本过低,升级Node版本为18.0.0后,出现另外一个错误,如下:

-- | --
20:24:42.689 | Installing dependencies
20:24:42.700 | Python version set to 2.7
20:24:46.058 | Downloading and installing node v18.0.0...
20:24:46.551 | Downloading https://nodejs.org/dist/v18.0.0/node-v18.0.0-linux-x64.tar.xz...
20:24:46.986 | Computing checksum with sha256sum
20:24:47.120 | Checksums matched!
20:24:51.354 | node: /lib/x86_64-linux-gnu/libm.so.6: version GLIBC_2.27' not found (required by node) 20:24:51.354 | node: /lib/x86_64-linux-gnu/libc.so.6: version GLIBC_2.25' not found (required by node)
20:24:51.355 | node: /lib/x86_64-linux-gnu/libc.so.6: version GLIBC_2.28' not found (required by node) 20:24:51.405 | nvm is not compatible with the npm config "prefix" option: currently set to "" 20:24:51.407 | Run npm config delete prefixornvm use --delete-prefix v18.0.0` to unset it.
20:24:51.407 | Failed to install node version '18.0.0'
20:24:51.411 | Failed: build command exited with code: 1
20:24:52.194 | Failed: an internal error occurred

因为在CloudFlare,只能配置npm run build的配置,没办法解决npm和nvm的冲突,有其他人遇到吗

希望增加删除单条问答记录的功能

在需要连续对话的场景,有时一些历史消息是我们不需要提供给api的。目前只有清除整个消息记录的功能,需要携带部分上下文时就满足不了需求了。希望大佬加下

fetch error

我本地部署的, 频繁的 出现下面的错误:

image

手机端复制无效

在手机上使用,点对话右上角复制,提示复制成功,实际没有复制上。

 ERR_PNPM_OUTDATED_LOCKFILE  Cannot install with "frozen-lockfile" because pnpm-lock.yaml is not up-to-date with package.json

加了一个gitalk 评论插件 重新部署后,出现下面错误,框架不熟,求大佬指教

 ERR_PNPM_OUTDATED_LOCKFILE  Cannot install with "frozen-lockfile" because pnpm-lock.yaml is not up-to-date with package.json
Note that in CI environments this setting is true by default. If you still need to run install in such cases, use "pnpm install --no-frozen-lockfile"

image

TypeError An error occurred. --- fetch failed

WeChatba6eb839fe006f7924577891e6d85fe9


输入问题后,一直提示这个问题

env中加入这个:HTTPS_PROXY=http://127.0.0.1:15235
一样也是连接不成功,求解谢谢


import type { APIRoute } from "astro"
import {
createParser,
ParsedEvent,
ReconnectInterval
} from "eventsource-parser"

const apiKeys = (
import.meta.env.OPENAI_API_KEY?.split(/\s*|\s*/) ?? []
).filter(Boolean)

export const post: APIRoute = async context => {
const body = await context.request.json()
const apiKey = apiKeys.length
? apiKeys[Math.floor(Math.random() * apiKeys.length)]
: ""
let { messages, key = apiKey, temperature = 0.6 } = body

const encoder = new TextEncoder()
const decoder = new TextDecoder()
^

if (!key.startsWith("sk-")) key = apiKey
if (!key) {
return new Response("没有填写 OpenAI API key")
}
if (!messages) {
return new Response("没有输入任何文字")
}

const completion = await fetch("https://api.openai.com/v1/chat/completions", {
headers: {
"Content-Type": "application/json",
Authorization: Bearer ${key}
},
method: "POST",
body: JSON.stringify({
model: "gpt-3.5-turbo",
messages,
temperature,
stream: true
})
})

const stream = new ReadableStream({
async start(controller) {
const streamParser = (event: ParsedEvent | ReconnectInterval) => {
if (event.type === "event") {
const data = event.data
if (data === "[DONE]") {
controller.close()
return
}
try {
// response = {
// id: 'chatcmpl-6pULPSegWhFgi0XQ1DtgA3zTa1WR6',
// object: 'chat.completion.chunk',
// created: 1677729391,
// model: 'gpt-3.5-turbo-0301',
// choices: [
// { delta: { content: '你' }, index: 0, finish_reason: null }
// ],
// }
const json = JSON.parse(data)
const text = json.choices[0].delta?.content
const queue = encoder.encode(text)
controller.enqueue(queue)
} catch (e) {
controller.error(e)
}
}
}

  const parser = createParser(streamParser)
  for await (const chunk of completion.body as any) {
    parser.feed(decoder.decode(chunk))
  }
}

})

return new Response(stream)
}

请问prompt在哪里找啊?

如题,还有这个预设可以自己写一个设定,直接在对话开头发给chat吗?还是说需要把写的设定设置到系统角色里?

新版本速度问题

更新到最新版本之后,相应的速度下降了不少,我还是回退到之前部署的版本上面了

模型选择问题

能否就是在下面的设置处,可以添加模型选择,然后根据不同的任务选择不同的模型,然后来执行之后的操作

markdown导出功能

个人部署后无法使用导出markdown功能,导出图片功能可正常使用

添加可用余额展示

希望页面上增加一个可用余额的展示,该接口请求方式如下:

$ curl -s  "https://api.openai.com/dashboard/billing/credit_grants" \
--header 'Content-type: application/json' \
--header 'Authorization: Bearer api_key' | jq    这里替换api_key
{
  "object": "credit_summary",
  "total_granted": 18,
  "total_used": 0.178104,  # 已用
  "total_available": 17.821896,  # 剩余可用余额
  "grants": {
    "object": "list",
    "data": [
      {
        "object": "credit_grant",
        "id": "be32c280-ad4a-4e14-bc1a-077a32275f9e",
        "grant_amount": 18,
        "used_amount": 0.178104,
        "effective_at": 1677628800,
        "expires_at": 1688169600
      }
    ]
  }
}

功能添加

大佬可以加个屏蔽词功能吗
就是设置某个屏蔽词然后转成另外一个词
然后可以设置多个的那种

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.