Fix CLI streaming bug

• fix: cli streaming issue 6e256e9
• 🍚 26a16fb
• Merge pull request #407 from youngle316/add-nextjschatgpt ffb31ac
• Merge branch 'main' into add-nextjschatgpt 6f08ece
• Update readme.md 2842a55
• Merge pull request #406 from insulineru/add-aicommits 62f267c
• 👄 bdda9a4
• docs: add NextJS chatgpt to README.md 0aa6f37
• chore: add ai-commit library to projects 5d62fe2

v5.0.0...v5.0.1

Switch to official chat completions API 🔥

The official OpenAI chat completions API has been released, and it is now the default for this package! 🔥

Method	Free?	Robust?	Quality?
ChatGPTAPI	❌ No	✅ Yes	✅️ Real ChatGPT models
ChatGPTUnofficialProxyAPI	✅ Yes	☑️ Maybe	✅ Real ChatGPT

Note: We strongly recommend using ChatGPTAPI since it uses the officially supported API from OpenAI. We may remove support for ChatGPTUnofficialProxyAPI in a future release.

1. ChatGPTAPI - Uses the gpt-3.5-turbo-0301 model with the official OpenAI chat completions API (official, robust approach, but it's not free)
2. ChatGPTUnofficialProxyAPI - Uses an unofficial proxy server to access ChatGPT's backend API in a way that circumvents Cloudflare (uses the real ChatGPT and is pretty lightweight, but relies on a third-party server and is rate-limited)

• 🐟 5c6a027
• 🚈 6577209
• 🔫 1b326db
• Merge pull request #412 from transitive-bullshit/feature/official-chat-completions-api 47b615d
• 🦋 067a758
• 🐛 fc429ec
• fix: bugfix 8ea449f
• feat: add support for official OpenAI chat completions API 271ed9d

v4.8.3...v5.0.0

Fix ChatGPTAPI tokenizer bug

• 🌑 8e26eb4
• fix: tokenizer special tokens e3ee727

v4.8.2...v4.8.3

Update tiktoken dep

• 😳 a6d3c1c
• Merge pull request #403 from NoodleOfDeath/main 942f414
• fix: update tiktoken dep 1bc24d2

v4.8.1...v4.8.2

Add conversationId / parentMessageId validity checking

• feat: check for invalid conversationId and parentMessageId 539aa6d

v4.8.0...v4.8.1

Switch tokenizers; Add Node.js access token generation; Minor fixes

• ⚒ f2a66f8
• Merge pull request #387 from gencay/patch-1 16b29b6
• Merge pull request #397 from dannysantino/whatsapp-bot 7212916
• Merge pull request #391 from tehfonsi/main 202b041
• Update readme.md be8a89d
• 🤛 d706918
• 🐝 e6784d6
• Merge pull request #393 from AllanOricil/update-readme 920344f
• Merge pull request #390 from transitive-bullshit/feature/rust-wasm-tokenizer aaa482b
• Merge pull request #398 from acheong08/patch-1 a5d891a
• Rate limit increased 0409ecd
• docs: add new whatsapp chatbot to README.md 77484e0
• Merge pull request #396 from IsiteYves/fixing-typos edd364e
• Update readme.md 5be8159
• Fix typo in README.md 0d8dea1
• add node js lib in the Access Token section 4f33703
• docs: add ai poem generator to projects 0eeab41
• Write the underlying exception details to streamed response a3e05c2
• feat: switch to rust wasm port of tiktoken tokenizer a51ecdb
• docs: tweak wording 1fdf218
• 🐲 6abb431

v4.7.2...v4.8.0

Fix ChatGPTUnofficialProxyAPI enable custom fetch

• Merge pull request #372 from fjc0k/main 8943cd3
• Merge pull request #373 from billylo1/main 96c2afe
• Update readme.md e346e85
• Merge pull request #1 from billylo1/billylo1-patch-1 dd25790
• add DomainGPT as an interesting use case for chatgpt-api 52a5abc
• fix(ChatGPTUnofficialProxyAPI): pass fetch f0ce925
• 🏜 70e4797
• ⚰ efa1ed8

v4.7.1...v4.7.2

Bug fix for CLI

• fix: cwd bug with packageJson e65a54f

v4.7.0...v4.7.1

Add chatgpt CLI 🔥

This release adds CLI functionality to chatgpt – Huge props to @zeke for the great idea and initial PR 🔥

To run the CLI, you'll need an OpenAI API key:

export OPENAI_API_KEY="sk-TODO"
npx chatgpt "your prompt here"

By default, the response is streamed to stdout, the results are stored in a local config file, and every invocation starts a new conversation. You can use -c to continue the previous conversation and --no-stream to disable streaming.

Under the hood, the CLI uses ChatGPTAPI with text-davinci-003 to mimic ChatGPT.

Usage:
  $ chatgpt <prompt>

Commands:
  <prompt>  Ask ChatGPT a question
  rm-cache  Clears the local message cache
  ls-cache  Prints the local message cache path

For more info, run any command with the `--help` flag:
  $ chatgpt --help
  $ chatgpt rm-cache --help
  $ chatgpt ls-cache --help

Options:
  -c, --continue          Continue last conversation (default: false)
  -d, --debug             Enables debug logging (default: false)
  -s, --stream            Streams the response (default: true)
  -s, --store             Enables the local message cache (default: true)
  -t, --timeout           Timeout in milliseconds
  -k, --apiKey            OpenAI API key
  -n, --conversationName  Unique name for the conversation
  -h, --help              Display this message
  -v, --version           Display version number

---

• chore: update ts docs 42d163b
• 🥒 607fccf
• 🔻 df0d6ef
• 🛍 535d220
• 🌿 7c3a894
• feat: improve CLI and add to readme d9c307c
• fix: fix cli build => ts 1224e0c
• Merge pull request #363 from zeke/add-cli 5f7609c by @zeke 🔥
• Merge pull request #359 from linjungz/main b1f10a6
• add a CLI 30f3abd
• Update readme.md 2b1fafa

v4.6.0...v4.7.0

Replace gpt-3-encoder with gpt3-tokenizer

There should be no public changes with this release. It's just changing internals for hopefully better compatibility.

• feat: switch from gpt-3-encoder to gpt3-tokenizer d8eeb1a
• 🚸 fc9869a
• 🚬 2460e5a
• 💐 218bdf8
• 👤 bc3a6ac

v4.5.1...v4.6.0