@promptbook/openai 0.45.0 → 0.46.0-1

package/README.md

@@ -2,15 +2,15 @@
 
 Library to supercharge your use of large language models
 
-<!--Badges-->
-<!--⚠️WARNING: This section was generated by https://github.com/hejny/batch-project-editor/blob/main/src/workflows/800-badges/badges.ts so every manual change will be overwritten.-->
+
+
 
 [![License of 📖 Prompt book](https://img.shields.io/github/license/webgptorg/promptbook.svg?style=flat)](https://github.com/webgptorg/promptbook/blob/main/LICENSE)
 [![Known Vulnerabilities](https://snyk.io/test/github/webgptorg/promptbook/badge.svg)](https://snyk.io/test/github/webgptorg/promptbook)
 [![Issues](https://img.shields.io/github/issues/webgptorg/promptbook.svg?style=flat)](https://github.com/webgptorg/promptbook/issues)
 [![Socket Badge](https://socket.dev/api/badge/npm/package/@promptbook/openai)](https://socket.dev/npm/package/@promptbook/openai)
 
-<!--/Badges-->
+
 
 ## 📦 Package `@promptbook/openai`
 
@@ -25,17 +25,14 @@ npm i @promptbook/openai
 
 Wrapper around [OpenAI's SDK](https://www.npmjs.com/package/openai) to make it easier to use inside Promptbooks.
 
-<!-- Link Simillar wrappers -->
+
 
 
 ---
 
 Rest of the documentation is common for **entire promptbook ecosystem**:
 
-<!--
-TODO: Probbably remove this section only in packages
-> ⚠ Warning: This library is still in early development.
--->
+
 
 ## 🤍 Whitepaper
 
@@ -78,13 +75,13 @@ In any of these situations, but especially in (3), the Promptbook library can ma
 -   Multiple promptbooks forms a library which will become a **part of your application codebase**.
 -   Theese promptbooks are designed such as they **can be written by non-programmers**.
 
-<!-- TODO: [🧠] Make some more clear escaping -->
+
 
 ### Sample:
 
 File `write-website-content.ptbk.md`:
 
-<!------------------------[ Sample: ]------------------------>
+
 
 > # 🌍 Create website content
 >
@@ -255,7 +252,7 @@ File `write-website-content.ptbk.md`:
 >
 > `-> {content}`
 
-<!------------------------[ /Sample ]------------------------>
+
 
 Following is the scheme how the promptbook above is executed:
 
@@ -308,15 +305,27 @@ _Note: We are using [postprocessing functions](#postprocessing-functions) like `
 
 ## 📦 Packages
 
-This library is divided into several packages, all are published from [single monorepo](https://github.com/webgptorg/promptbook):
+This library is divided into several packages, all are published from [single monorepo](https://github.com/webgptorg/promptbook).
+You can install all of them at once:
+
+```bash
+npm i ptbk
+```
 
-<!--[🔠]-->
+Or you can install them separately:
 
+
+
+
+-   ⭐ **[ptbk](https://www.npmjs.com/package/@promptbook/core)** - Bundle of all packages, when you want to install everything and you don't care about the size
+-   **[promptbook](https://www.npmjs.com/package/@promptbook/core)** - Just alias for `ptbk`
 -   **[@promptbook/core](https://www.npmjs.com/package/@promptbook/core)** - Core of the library, it contains the main logic for promptbooks
-- ⭐ **[@promptbook/utils](https://www.npmjs.com/package/@promptbook/utils)** - Utility functions used in the library but also useful for individual use in preprocessing and postprocessing LLM inputs and outputs
+-   ⭐ **[@promptbook/utils](https://www.npmjs.com/package/@promptbook/utils)** - Utility functions used in the library but also useful for individual use in preprocessing and postprocessing LLM inputs and outputs
 -   _(Not finished)_ **[@promptbook/wizzard](https://www.npmjs.com/package/@promptbook/wizzard)** - Wizard for creating+running promptbooks in single line
 -   **[@promptbook/execute-javascript](https://www.npmjs.com/package/@promptbook/execute-javascript)** - Execution tools for javascript inside promptbooks
 -   **[@promptbook/openai](https://www.npmjs.com/package/@promptbook/openai)** - Execution tools for OpenAI API, wrapper around OpenAI SDK
+-   **[@promptbook/langtail](https://www.npmjs.com/package/@promptbook/langtail)** - Execution tools for Langtail API, wrapper around Langtail SDK
+-   **[@promptbook/mock](https://www.npmjs.com/package/@promptbook/mock)** - Mocked execution tools for testing the library and saving the tokens
 -   **[@promptbook/remote-client](https://www.npmjs.com/package/@promptbook/remote-client)** - Remote client for remote execution of promptbooks
 -   **[@promptbook/remote-server](https://www.npmjs.com/package/@promptbook/remote-server)** - Remote server for remote execution of promptbooks
 -   **[@promptbook/types](https://www.npmjs.com/package/@promptbook/types)** - Just typescript types used in the library
@@ -488,7 +497,7 @@ There are [postprocessing functions](#postprocessing-functions) that can be used
 
 -   _(Not implemented yet)_ `ConsoleInterfaceTools` is a wrapper around `readline` module that interacts with the user via console.
 -   `SimplePromptInterfaceTools` is a wrapper around `window.prompt` synchronous function that interacts with the user via browser prompt. It is used for testing and mocking **NOT intended to use in the production** due to its synchronous nature.
--   `CallbackInterfaceTools` delagates the user interaction to a async callback function. You need to provide your own implementation of this callback function and its bind to UI. <!-- <- TODO: Provide here a way how to do it with some our plugin -->
+-   `CallbackInterfaceTools` delagates the user interaction to a async callback function. You need to provide your own implementation of this callback function and its bind to UI. 
 
 ### Executor
 
@@ -558,10 +567,7 @@ There are two types of expectations which are not strictly symmetrical:
 
 Look at [expectations.ptbk.md](samples/templates/45-expectations.ptbk.md) and [expect-json.ptbk.md](samples/templates/45-expect-json.ptbk.md) samples for more.
 
-<!--
-### New
-[🥻] Insert here when making new command
--->
+
 
 ### Execution report
 
@@ -569,7 +575,7 @@ Execution report is a simple object or markdown that contains information about
 
 [See the example of such a report](/samples/templates/50-advanced.report.md)
 
-<!-- TODO: Write more -->
+
 
 ### Remote server
 
@@ -580,23 +586,7 @@ This is useful to make all logic on browser side but not expose your API keys or
 
 ## 👨‍💻 Usage and integration _(for developers)_
 
-<!--
-
-TODO: [🧙‍♂️]
-
-### 🧙‍♂️ Using wizzard
-
-First you need to install this library:
-
-```bash
-npm install --save @promptbook/wizzard
-```
-
-> TODO: !! Write the Wizzard sample
-
-[Usage samples](./samples/usage/)
 
--->
 
 ### 🔌 Usage in Typescript / Javascript
 
@@ -621,11 +611,11 @@ npm install --save @promptbook/wizzard
 
 ## 🐜 Known issues
 
-<!-- TODO:  -->
+
 
 ## 🧼 Intentionally not implemented features
 
-<!-- TODO:  -->
+
 
 ## ❔ FAQ
 
@@ -641,42 +631,17 @@ Langchain is primarily aimed at ML developers working in Python. This library is
 
 We are considering creating a bridge/converter between these two libraries.
 
-<!--
 
-==========
-Include:
-- Langchain is the python library and JavaScript is on second place
-- Langchain primarily focused on making templates, not on combining templates into larger structures
-- at the language level it distinguishes between chat and completion, I need to mix the two into one template pipeline
-- for a non-programmer it's quite hard to work with such a thing and write templates - I would much prefer a system that allows non-technical people to write templates (of which there are many more on the market than free pythonists)
-- The focus of promptbooks is primarily on building user applications, not the data processing, training or autogpt.
--->
 
 ### Promptbooks vs. OpenAI`s GPTs
 
 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.
 
-<!--
-TODO:
-### Promptbooks vs. Semantic Kernel
-
 
--->
 
-<!--
-TODO: !
-### Promptbooks vs. Langtail
 
 
--->
 
-<!--
-TODO:
-### Promptbooks vs. Evidentally AI
-
-Logging and monitoring
-
--->
 
 ### Where should I store my promptbooks?
 
@@ -698,34 +663,10 @@ In large language models, you will get better results if you have prompts in the
 
 The best way to manage this is to have suffixed promptbooks like `write-website-content.en.ptbk.md` and `write-website-content.cs.ptbk.md` for each supported language.
 
-<!--
-TODO: (Maybe)
-### Why you need to explicitly specify input and output parameters?
--->
-
-<!--
-
-
 
-!
 
 
 
-unit testing
-
-escaping
-
-how i get block into prompt
-
-
-## 🚷 Limitations
-
-function calling
-system message
-iterations
-
--->
-
 ## ⌚ Changelog
 
 See [CHANGELOG.md](./CHANGELOG.md)
@@ -734,13 +675,11 @@ See [CHANGELOG.md](./CHANGELOG.md)
 
 <p xmlns:cc="http://creativecommons.org/ns#" xmlns:dct="http://purl.org/dc/terms/"><a property="dct:title" rel="cc:attributionURL" href="https://github.com/webgptorg/promptbook">Promptbook</a> by <a rel="cc:attributionURL dct:creator" property="cc:attributionName" href="https://github.com/hejny/">Pavol Hejný</a> is licensed under <a href="https://creativecommons.org/licenses/by/4.0/?ref=chooser-v1" target="_blank" rel="license noopener noreferrer" style="display:inline-block;">CC BY 4.0</a></p>
 
-<!--Contributing-->
-<!--⚠️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.-->
+
+
 
 ## 🖋️ Contributing
 
 I am open to pull requests, feedback, and suggestions. Or if you like this utility, you can [☕ buy me a coffee](https://www.buymeacoffee.com/hejny) or [donate via cryptocurrencies](https://github.com/hejny/hejny/blob/main/documents/crypto.md).
 
-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/).
-
-<!--/Contributing-->
+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/).

package/esm/typings/_packages/core.index.d.ts

@@ -1,8 +1,6 @@
 import { promptbookStringToJson } from '../conversion/promptbookStringToJson';
 import { validatePromptbookJson } from '../conversion/validation/validatePromptbookJson';
 import { createPromptbookExecutor } from '../execution/createPromptbookExecutor';
-import { MockedEchoNaturalExecutionTools } from '../execution/plugins/natural-execution-tools/mocked/MockedEchoNaturalExecutionTools';
-import { MockedFackedNaturalExecutionTools } from '../execution/plugins/natural-execution-tools/mocked/MockedFackedNaturalExecutionTools';
 import { CallbackInterfaceTools } from '../execution/plugins/user-interface-execution-tools/callback/CallbackInterfaceTools';
 import { CallbackInterfaceToolsOptions } from '../execution/plugins/user-interface-execution-tools/callback/CallbackInterfaceToolsOptions';
 import { SimplePromptInterfaceTools } from '../execution/plugins/user-interface-execution-tools/simple-prompt/SimplePromptInterfaceTools';
@@ -16,6 +14,5 @@ export { ExecutionTypes, PROMPTBOOK_VERSION };
 export { createPromptbookLibraryFromPromise, createPromptbookLibraryFromSources, createPromptbookSublibrary, SimplePromptbookLibrary, };
 export { SimplePromptInterfaceTools };
 export { promptbookStringToJson, validatePromptbookJson };
-export { MockedEchoNaturalExecutionTools, MockedFackedNaturalExecutionTools };
 export { createPromptbookExecutor };
 export { CallbackInterfaceTools, CallbackInterfaceToolsOptions };

package/esm/typings/_packages/langtail.index.d.ts

@@ -0,0 +1,3 @@
+import { LangtailExecutionTools } from '../execution/plugins/natural-execution-tools/langtail/LangtailExecutionTools';
+import { LangtailExecutionToolsOptions } from '../execution/plugins/natural-execution-tools/langtail/LangtailExecutionToolsOptions';
+export { LangtailExecutionTools, LangtailExecutionToolsOptions };

package/esm/typings/_packages/mock.index.d.ts

@@ -0,0 +1,6 @@
+import { MockedEchoNaturalExecutionTools } from '../execution/plugins/natural-execution-tools/mocked/MockedEchoNaturalExecutionTools';
+import { MockedFackedNaturalExecutionTools } from '../execution/plugins/natural-execution-tools/mocked/MockedFackedNaturalExecutionTools';
+export { MockedEchoNaturalExecutionTools, MockedFackedNaturalExecutionTools };
+/**
+ * TODO: [🚏] FakeLLM
+ */

package/esm/typings/execution/plugins/natural-execution-tools/langtail/LangtailExecutionToolsOptions.d.ts

@@ -0,0 +1,11 @@
+import type { OpenAiExecutionToolsOptions } from '../openai/OpenAiExecutionToolsOptions';
+/**
+ * Options for LangtailExecutionTools
+ *
+ * This extends OpenAI's `ClientOptions` with are directly passed to the OpenAI client.
+ * Rest is used by the `OpenAiExecutionTools`.
+ */
+export type LangtailExecutionToolsOptions = OpenAiExecutionToolsOptions;
+/**
+ * TODO: !!! Use or remove
+ */

package/esm/typings/execution/plugins/natural-execution-tools/mocked/fakeTextToExpectations.d.ts

@@ -10,6 +10,6 @@ import { PostprocessingFunction } from '../../script-execution-tools/javascript/
  */
 export declare function $fakeTextToExpectations(expectations: Expectations, postprocessing?: Array<PostprocessingFunction>): Promise<string>;
 /**
- * TODO: Implement better - create FakeLLM from this
+ * TODO: [🚏] Implement better - create FakeLLM from this
  * TODO: [💝] Unite object for expecting amount and format - use here also a format
  */

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@promptbook/openai",
-    "version": "0.45.0",
+    "version": "0.46.0-1",
     "description": "Library to supercharge your use of large language models",
     "private": false,
     "sideEffects": false,
@@ -38,7 +38,7 @@
         "openai": "4.2.0"
     },
     "peerDependencies": {
-        "@promptbook/core": "0.45.0"
+        "@promptbook/core": "0.46.0-1"
     },
     "main": "./umd/index.umd.js",
     "module": "./esm/index.es.js",

package/umd/typings/_packages/core.index.d.ts

@@ -1,8 +1,6 @@
 import { promptbookStringToJson } from '../conversion/promptbookStringToJson';
 import { validatePromptbookJson } from '../conversion/validation/validatePromptbookJson';
 import { createPromptbookExecutor } from '../execution/createPromptbookExecutor';
-import { MockedEchoNaturalExecutionTools } from '../execution/plugins/natural-execution-tools/mocked/MockedEchoNaturalExecutionTools';
-import { MockedFackedNaturalExecutionTools } from '../execution/plugins/natural-execution-tools/mocked/MockedFackedNaturalExecutionTools';
 import { CallbackInterfaceTools } from '../execution/plugins/user-interface-execution-tools/callback/CallbackInterfaceTools';
 import { CallbackInterfaceToolsOptions } from '../execution/plugins/user-interface-execution-tools/callback/CallbackInterfaceToolsOptions';
 import { SimplePromptInterfaceTools } from '../execution/plugins/user-interface-execution-tools/simple-prompt/SimplePromptInterfaceTools';
@@ -16,6 +14,5 @@ export { ExecutionTypes, PROMPTBOOK_VERSION };
 export { createPromptbookLibraryFromPromise, createPromptbookLibraryFromSources, createPromptbookSublibrary, SimplePromptbookLibrary, };
 export { SimplePromptInterfaceTools };
 export { promptbookStringToJson, validatePromptbookJson };
-export { MockedEchoNaturalExecutionTools, MockedFackedNaturalExecutionTools };
 export { createPromptbookExecutor };
 export { CallbackInterfaceTools, CallbackInterfaceToolsOptions };

package/umd/typings/_packages/langtail.index.d.ts

@@ -0,0 +1,3 @@
+import { LangtailExecutionTools } from '../execution/plugins/natural-execution-tools/langtail/LangtailExecutionTools';
+import { LangtailExecutionToolsOptions } from '../execution/plugins/natural-execution-tools/langtail/LangtailExecutionToolsOptions';
+export { LangtailExecutionTools, LangtailExecutionToolsOptions };

package/umd/typings/_packages/mock.index.d.ts

@@ -0,0 +1,6 @@
+import { MockedEchoNaturalExecutionTools } from '../execution/plugins/natural-execution-tools/mocked/MockedEchoNaturalExecutionTools';
+import { MockedFackedNaturalExecutionTools } from '../execution/plugins/natural-execution-tools/mocked/MockedFackedNaturalExecutionTools';
+export { MockedEchoNaturalExecutionTools, MockedFackedNaturalExecutionTools };
+/**
+ * TODO: [🚏] FakeLLM
+ */

package/umd/typings/execution/plugins/natural-execution-tools/langtail/LangtailExecutionToolsOptions.d.ts

@@ -0,0 +1,11 @@
+import type { OpenAiExecutionToolsOptions } from '../openai/OpenAiExecutionToolsOptions';
+/**
+ * Options for LangtailExecutionTools
+ *
+ * This extends OpenAI's `ClientOptions` with are directly passed to the OpenAI client.
+ * Rest is used by the `OpenAiExecutionTools`.
+ */
+export type LangtailExecutionToolsOptions = OpenAiExecutionToolsOptions;
+/**
+ * TODO: !!! Use or remove
+ */

package/umd/typings/execution/plugins/natural-execution-tools/mocked/fakeTextToExpectations.d.ts

@@ -10,6 +10,6 @@ import { PostprocessingFunction } from '../../script-execution-tools/javascript/
  */
 export declare function $fakeTextToExpectations(expectations: Expectations, postprocessing?: Array<PostprocessingFunction>): Promise<string>;
 /**
- * TODO: Implement better - create FakeLLM from this
+ * TODO: [🚏] Implement better - create FakeLLM from this
  * TODO: [💝] Unite object for expecting amount and format - use here also a format
  */