@promptbook/openai 0.44.0-19 → 0.44.0-20

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +3 -67
  2. package/package.json +2 -2
package/README.md CHANGED
@@ -593,9 +593,8 @@ Include:
593
593
 
594
594
  GPTs are chat assistants that can be assigned to specific tasks and materials. But they are still chat assistants. Promptbooks are a way to orchestrate many more predefined tasks to have much tighter control over the process. Promptbooks are not a good technology for creating human-like chatbots, GPTs are not a good technology for creating outputs with specific requirements.
595
595
 
596
-
597
596
  <!--
598
- TODO:!!!
597
+ TODO:!!!
599
598
  ### Promptbooks vs. Semantic Kernel
600
599
 
601
600
 
@@ -641,16 +640,15 @@ TODO: (Maybe)
641
640
  ### Why you need to explicitly specify input and output parameters?
642
641
  -->
643
642
 
644
-
645
643
  <!--
646
644
 
647
645
 
648
646
 
649
- !!!!
647
+ !!!!
650
648
 
651
649
 
652
650
 
653
- unit testing
651
+ unit testing
654
652
 
655
653
  escaping
656
654
 
@@ -665,51 +663,10 @@ iterations
665
663
 
666
664
  -->
667
665
 
668
-
669
666
  ## ⌚ Changelog
670
667
 
671
668
  See [CHANGELOG.md](./CHANGELOG.md)
672
669
 
673
- ## 🎯 TODOs
674
-
675
- - [ ][🧙‍♂️] Make Wizzard
676
- - [x] Make from this folder a separate repository + npm package
677
- - [x] Add tests
678
- - [ ] Annotate all entities
679
- - [ ] Make internal string aliases
680
- - [ ] Make branded types instead of pure `string` aliases
681
- - [ ] Remove all `any`
682
- - [ ][👧] Make strongy typed input+output parameters in executors
683
- - [x] Make promptbooks non-linear
684
- - [x] Logging pipeline name, version, step,...
685
- - [ ][🧠] Wording: "param" vs "parameter" vs "variable" vs "argument"
686
- - [ ] All entities must have public / private / protected modifiers
687
- - [ ] Everything not needed should be private or not exported
688
- - [ ] Refactor circular dependencies
689
- - [ ] Importing subtemplates
690
- - [ ] Use `spaceTrim` more effectively
691
- - [ ] [🤹‍♂️] Allow chats to be continued with previous message
692
- - [ ] [🧠][🤹‍♂️] How to mark continued chat in .ptbk.md format?
693
- - [ ] Use newest version of socket.io for remote server
694
- - [ ] [🧠] Allow to use and define [function calling](https://platform.openai.com/docs/guides/gpt/function-calling)
695
- - [x] Register .ptbk file extension
696
- - [ ] Fix error `content.js:73 Uncaught (in promise) TypeError: object null is not iterable (cannot read property Symbol(Symbol.iterator))`
697
- - [ ] Aborting execution, maybe use native AbortController
698
- - [ ] Change `import {...} from '...';` to `import type {...} from '...';` when importing only types
699
- - [x] Wrap OpenAI billing errors:
700
- - [ ] Integrate word stemmer https://github.com/maxpatiiuk/porter-stemming/blob/main/src/index.ts
701
- - [ ] Integrate faker to generate simple mocked data
702
- - [ ] Put postprocessing + expectations into mermaid graphs
703
- - [ ] mermaid graphs as exported CLI util
704
- - [ ] Preprocessing
705
- - [ ] System to bundle up Preprocessing + Postprocessing + Expectations
706
- - [ ] Integrate ceaser-cipher to auto preprocess some and postprocess templates
707
- - [ ] Scenario: Expect all information (for example in incomming email), when not then return = kinda reverse joker
708
- - [ ] Make VSCode extension for validation/syntax highlite (and for other editors)
709
-
710
- - "Billing hard limit has been reached"
711
- - "You exceeded your current quota, please check your plan and billing details."
712
-
713
670
  <!--Contributing-->
714
671
  <!--⚠️WARNING: This section was generated by https://github.com/hejny/batch-project-editor/blob/main/src/workflows/810-contributing/contributing.ts so every manual change will be overwritten.-->
715
672
 
@@ -720,24 +677,3 @@ I am open to pull requests, feedback, and suggestions. Or if you like this utili
720
677
  You can also ⭐ star the promptbook package, [follow me on GitHub](https://github.com/hejny) or [various other social networks](https://www.pavolhejny.com/contact/).
721
678
 
722
679
  <!--/Contributing-->
723
-
724
- <!--Custom Partners-->
725
- <!--⚠️WARNING: This section was generated by https://github.com/hejny/batch-project-editor/blob/main/src/workflows/820-partners/partners.ts so every manual change will be overwritten.-->
726
-
727
- ## ✨ Partners
728
-
729
- <a href="https://webgpt.cz/">
730
- <img src="https://webgpt.cz/_next/static/media/webgpt.white.04a40f79.svg" alt="SigmaStamp logo" height="50" />
731
- </a>
732
- &nbsp;&nbsp;&nbsp;
733
- <a href="https://collboard.com/">
734
- <img src="https://collboard.fra1.cdn.digitaloceanspaces.com/assets/18.12.1/logo-small.png" alt="Collboard logo" height="50" />
735
- </a>
736
-
737
- <!--
738
- TODO: Add here Ai*nautes
739
- -->
740
-
741
- [Become a partner](https://www.pavolhejny.com/contact/)
742
-
743
- <!--/Custom Partners-->
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@promptbook/openai",
3
- "version": "0.44.0-19",
3
+ "version": "0.44.0-20",
4
4
  "description": "Library to supercharge your use of large language models",
5
5
  "private": false,
6
6
  "sideEffects": false,
@@ -38,7 +38,7 @@
38
38
  "openai": "4.2.0"
39
39
  },
40
40
  "peerDependencies": {
41
- "@promptbook/core": "0.44.0-19"
41
+ "@promptbook/core": "0.44.0-20"
42
42
  },
43
43
  "main": "./umd/index.umd.js",
44
44
  "module": "./esm/index.es.js",