@promptbook/openai 0.74.0-5 → 0.74.0-7

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.
package/README.md CHANGED
@@ -228,8 +228,6 @@ Rest of the documentation is common for **entire promptbook ecosystem**:
228
228
 
229
229
  ## 🤍 The Promptbook Whitepaper
230
230
 
231
-
232
-
233
231
  If you have a simple, single prompt for ChatGPT, GPT-4, Anthropic Claude, Google Gemini, Llama 3, or whatever, it doesn't matter how you integrate it. Whether it's calling a REST API directly, using the SDK, hardcoding the prompt into the source code, or importing a text file, the process remains the same.
234
232
 
235
233
  But often you will struggle with the **limitations of LLMs**, such as **hallucinations, off-topic responses, poor quality output, language and prompt drift, word repetition repetition repetition repetition or misuse, lack of context, or just plain w𝒆𝐢rd resp0nses**. When this happens, you generally have three options:
@@ -298,23 +296,17 @@ Promptbook project is ecosystem of multiple projects and tools, following is a l
298
296
 
299
297
  ## 💙 Book language _(for prompt-engineer)_
300
298
 
301
- Promptbook [pipelines](https://github.com/webgptorg/promptbook/discussions/64) are written in markdown-like language called [Book](https://github.com/webgptorg/book). It is designed to be understandable by non-programmers and non-technical people.
302
-
303
299
 
304
300
 
305
- ```markdown
306
- # 🌟 My first Book
307
301
 
308
- - INPUT PARAMETER {subject}
309
- - OUTPUT PARAMETER {article}
302
+ ## 💙 The blueprint of book language
310
303
 
311
- ## Sample subject
304
+ Following is the documentation and blueprint of the Book language.
312
305
 
313
- > Promptbook
306
+ ### Example
314
307
 
315
- -> {subject}
316
-
317
- ## Write an article
308
+ ```markdown
309
+ # 🌟 My first Book
318
310
 
319
311
  - PERSONA Jane, marketing specialist with prior experience in writing articles about technology and artificial intelligence
320
312
  - KNOWLEDGE https://ptbk.io
@@ -323,11 +315,65 @@ Promptbook [pipelines](https://github.com/webgptorg/promptbook/discussions/64) a
323
315
  - EXPECT MAX 1 Paragraph
324
316
 
325
317
  > Write an article about the future of artificial intelligence in the next 10 years and how metalanguages will change the way AI is used in the world.
326
- > Look specifically at the impact of {subject} on the AI industry.
318
+ > Look specifically at the impact of Promptbook on the AI industry.
327
319
 
328
320
  -> {article}
329
321
  ```
330
322
 
323
+ ### Goals and principles of book language
324
+
325
+ File is designed to be easy to read and write. It is strict subset of markdown. It is designed to be understandable by both humans and machines and without specific knowledge of the language.
326
+
327
+ It has file with `.ptbk.md` or `.book` extension with `UTF-8` non BOM encoding.
328
+
329
+ As it is source code, it can leverage all the features of version control systems like git and does not suffer from the problems of binary formats, proprietary formats, or no-code solutions.
330
+
331
+ But unlike programming languages, it is designed to be understandable by non-programmers and non-technical people.
332
+
333
+ ### Structure
334
+
335
+ Book is divided into sections. Each section starts with heading. The language itself is not sensitive to the type of heading _(`h1`, `h2`, `h3`, ...)_ but it is recommended to use `h1` for header section and `h2` for other sections.
336
+
337
+ ### Header
338
+
339
+ Header is the first section of the book. It contains metadata about the pipeline. It is recommended to use `h1` heading for header section but it is not required.
340
+
341
+ ### Parameter
342
+
343
+ Foo bar
344
+
345
+ #### Parameter names
346
+
347
+ Reserved words:
348
+
349
+ - _each command_ like `PERSONA`, `EXPECT`, `KNOWLEDGE`, etc.
350
+ - `content`
351
+ - `context`
352
+ - `knowledge`
353
+ - `examples`
354
+ - `modelName`
355
+ - `currentDate`
356
+
357
+ #### Parameter notation
358
+
359
+ ### Template
360
+
361
+ Todo todo
362
+
363
+ ### Command
364
+
365
+ Todo todo
366
+
367
+ ### Block
368
+
369
+ Todo todo
370
+
371
+ ### Return parameter
372
+
373
+ ### Examples
374
+
375
+
376
+
331
377
  ## 📦 Packages _(for developers)_
332
378
 
333
379
  This library is divided into several packages, all are published from [single monorepo](https://github.com/webgptorg/promptbook).
package/esm/index.es.js CHANGED
@@ -14,7 +14,7 @@ var BOOK_LANGUAGE_VERSION = '1.0.0';
14
14
  *
15
15
  * @see https://github.com/webgptorg/promptbook
16
16
  */
17
- var PROMPTBOOK_ENGINE_VERSION = '0.74.0-4';
17
+ var PROMPTBOOK_ENGINE_VERSION = '0.74.0-6';
18
18
  /**
19
19
  * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
20
20
  */
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@promptbook/openai",
3
- "version": "0.74.0-5",
3
+ "version": "0.74.0-7",
4
4
  "description": "Supercharge your use of large language models",
5
5
  "private": false,
6
6
  "sideEffects": false,
@@ -53,7 +53,7 @@
53
53
  "module": "./esm/index.es.js",
54
54
  "typings": "./esm/typings/src/_packages/openai.index.d.ts",
55
55
  "peerDependencies": {
56
- "@promptbook/core": "0.74.0-5"
56
+ "@promptbook/core": "0.74.0-7"
57
57
  },
58
58
  "dependencies": {
59
59
  "colors": "1.4.0",
package/umd/index.umd.js CHANGED
@@ -22,7 +22,7 @@
22
22
  *
23
23
  * @see https://github.com/webgptorg/promptbook
24
24
  */
25
- var PROMPTBOOK_ENGINE_VERSION = '0.74.0-4';
25
+ var PROMPTBOOK_ENGINE_VERSION = '0.74.0-6';
26
26
  /**
27
27
  * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
28
28
  */