@promptbook/fake-llm 0.103.0-0 → 0.103.0-2

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
@@ -1,8 +1,10 @@
1
1
  <!-- ⚠️ WARNING: This code has been generated so that any manual changes will be overwritten -->
2
2
 
3
- # ✨ Promptbook: AI apps in plain Language
3
+ # ✨ Promptbook: AI Agents
4
+
5
+ Turn your company's scattered knowledge into AI ready Books
6
+
4
7
 
5
- Write AI applications using plain human language across multiple models and platforms.
6
8
 
7
9
 
8
10
 
@@ -61,19 +63,131 @@ Rest of the documentation is common for **entire promptbook ecosystem**:
61
63
 
62
64
 
63
65
 
64
- ## 🤍 The Book Abstract
66
+ ## 📖 The Book Whitepaper
67
+
68
+ For most business applications nowadays, the biggest challenge isn't about the raw capabilities of AI models. Large language models like GPT-5 or Claude-4.1 are extremely capable.
69
+
70
+ The main challenge is to narrow it down, constrain it, set the proper **context, rules, knowledge, and personality**. There are a lot of tools which can do exactly this. On one side, there are no-code platforms which can launch your agent in seconds. On the other side, there are heavy frameworks like Langchain or Semantic Kernel, which can give you deep control.
71
+
72
+ Promptbook takes the best from both worlds. You are defining your AI behavior by simple **books**, which are very explicit. They are automatically enforced, but they are very easy to understand, very easy to write, and very reliable and portable.
73
+
74
+
75
+
76
+ <img
77
+ alt="Paul Smith & Associés Book"
78
+ src="https://promptbook.studio/embed/book-preview.png?book=Paul%20Smith%20%26%20Associ%C3%A9s%0A%20%20%20%20%20%20%7C%20PERSONA%20You%20are%20a%20company%20lawyer.%0A%20%20%20%20%20%20%7C%20Your%20job%20is%20to%20provide%20legal%20advice%20and%20support%20to%20the%20company%20and%20its%20employees.%0A%20%20%20%20%20%20%7C%20You%20are%20knowledgeable%2C%20professional%2C%20and%20detail-oriented.&width=800&height=450&nonce=0"
79
+ />
80
+
81
+ <div style="page-break-after: always;"></div>
82
+
83
+ ### Aspects of great AI agent
84
+
85
+ We have created a language called **Book**, which allows you to write AI agents in their native language and create your own AI persona. Book provides a guide to define all the traits and commitments.
86
+
87
+ You can look at it as prompting (or writing a system message), but decorated by **commitments**.
88
+
89
+ #### `Persona` commitment
90
+
91
+ Personas define the character of your AI persona, its role, and how it should interact with users. It sets the tone and style of communication.
92
+
93
+
94
+
95
+ <img
96
+ alt="Paul Smith & Associés Book"
97
+ src="https://promptbook.studio/embed/book-preview.png?book=Paul%20Smith%20%26%20Associ%C3%A9s%0A%20%20%20%20%20%20%7C%20PERSONA%20You%20are%20a%20company%20lawyer.%0A%20%20%20%20%20%20%7C%20Your%20job%20is%20to%20provide%20legal%20advice%20and%20support%20to%20the%20company%20and%20its%20employees.%0A%20%20%20%20%20%20%7C%20You%20are%20knowledgeable%2C%20professional%2C%20and%20detail-oriented.&width=800&height=450&nonce=0"
98
+ />
99
+
100
+ #### `Knowledge` commitment
101
+
102
+ Knowledge Commitment allows you to provide specific information, facts, or context that the AI should be aware of when responding.
103
+
104
+ This can include domain-specific knowledge, company policies, or any other relevant information.
105
+
106
+ Promptbook Engine will automatically enforce this knowledge during interactions. When the knowledge is short enough, it will be included in the prompt. When it is too long, it will be stored in vector databases and RAG retrieved when needed. But you don't need to care about it.
107
+
108
+
109
+
110
+ <img
111
+ alt="Paul Smith & Associés Book"
112
+ src="https://promptbook.studio/embed/book-preview.png?book=Paul%20Smith%20%26%20Associ%C3%A9s%0A%20%20%20%20%20%20%7C%20PERSONA%20You%20are%20a%20company%20lawyer.%0A%20%20%20%20%20%20%7C%20Your%20job%20is%20to%20provide%20legal%20advice%20and%20support%20to%20the%20company%20and%20its%20employees.%0A%20%20%20%20%20%20%7C%20You%20are%20knowledgeable%2C%20professional%2C%20and%20detail-oriented.%0A%20%20%20%20%20%20%7C%20KNOWLEDGE%20%20https%3A%2F%2Fcompany.com%2Fcompany-policies.pdf%0A%20%20%20%20%20%20%7C%20KNOWLEDGE%20https%3A%2F%2Fcompany.com%2Finternal-documents%2Femployee-handbook.docx&width=800&height=450&nonce=0"
113
+ />
114
+
115
+ #### `Rule` commitment
116
+
117
+ Rules will enforce specific behaviors or constraints on the AI's responses. This can include ethical guidelines, communication styles, or any other rules you want the AI to follow.
118
+
119
+ Depending on rule strictness, Promptbook will either propagate it to the prompt or use other techniques, like adversary agent, to enforce it.
120
+
121
+
122
+
123
+ <img
124
+ alt="Paul Smith & Associés Book"
125
+ src="https://promptbook.studio/embed/book-preview.png?book=Paul%20Smith%20%26%20Associ%C3%A9s%0A%20%20%20%20%20%20%7C%20PERSONA%20You%20are%20a%20company%20lawyer.%0A%20%20%20%20%20%20%7C%20Your%20job%20is%20to%20provide%20legal%20advice%20and%20support%20to%20the%20company%20and%20its%20employees.%0A%20%20%20%20%20%20%7C%20You%20are%20knowledgeable%2C%20professional%2C%20and%20detail-oriented.%0A%20%20%20%20%20%20%7C%20RULE%20Always%20ensure%20compliance%20with%20laws%20and%20regulations.%0A%20%20%20%20%20%20%7C%20RULE%20Never%20provide%20legal%20advice%20outside%20your%20area%20of%20expertise.%0A%20%20%20%20%20%20%7C%20RULE%20Never%20provide%20legal%20advice%20about%20criminal%20law.%0A%20%20%20%20%20%20%7C%20KNOWLEDGE%20%20https%3A%2F%2Fcompany.com%2Fcompany-policies.pdf%0A%20%20%20%20%20%20%7C%20KNOWLEDGE%20https%3A%2F%2Fcompany.com%2Finternal-documents%2Femployee-handbook.docx&width=800&height=450&nonce=0"
126
+ />
127
+
128
+ #### `Action` commitment
65
129
 
66
- **It's time for a paradigm shift! The future of software is written in plain English, French, or Latin.**
130
+ Action Commitment allows you to define specific actions that the AI can take during interactions. This can include things like posting on a social media platform, sending emails, creating calendar events, or interacting with your internal systems.
67
131
 
68
- During the computer revolution, we have seen [multiple generations of computer languages](https://github.com/webgptorg/promptbook/discussions/180), from the physical rewiring of the vacuum tubes through low-level machine code to the high-level languages like Python or JavaScript. And now, we're on the edge of the **next revolution**!
69
132
 
70
- It's a revolution of writing software in **plain human language** that is understandable and executable by both humans and machines – and it's going to change everything!
71
133
 
72
- The incredible growth in power of microprocessors and the Moore's Law have been the driving force behind the ever-more powerful languages, and it's been an amazing journey! Similarly, the large language models (like GPT or Claude) are the next big thing in language technology, and they're set to transform the way we interact with computers.
134
+ <img
135
+ alt="Paul Smith & Associés Book"
136
+ src="https://promptbook.studio/embed/book-preview.png?book=Paul%20Smith%20%26%20Associ%C3%A9s%0A%20%20%20%20%20%20%7C%20PERSONA%20You%20are%20a%20company%20lawyer.%0A%20%20%20%20%20%20%7C%20Your%20job%20is%20to%20provide%20legal%20advice%20and%20support%20to%20the%20company%20and%20its%20employees.%0A%20%20%20%20%20%20%7C%20You%20are%20knowledgeable%2C%20professional%2C%20and%20detail-oriented.%0A%20%20%20%20%20%20%7C%20RULE%20Always%20ensure%20compliance%20with%20laws%20and%20regulations.%0A%20%20%20%20%20%20%7C%20RULE%20Never%20provide%20legal%20advice%20outside%20your%20area%20of%20expertise.%0A%20%20%20%20%20%20%7C%20RULE%20Never%20provide%20legal%20advice%20about%20criminal%20law.%0A%20%20%20%20%20%20%7C%20KNOWLEDGE%20%20https%3A%2F%2Fcompany.com%2Fcompany-policies.pdf%0A%20%20%20%20%20%20%7C%20KNOWLEDGE%20https%3A%2F%2Fcompany.com%2Finternal-documents%2Femployee-handbook.docx%0A%20%20%20%20%20%20%7C%20ACTION%20When%20a%20user%20asks%20about%20an%20issue%20that%20could%20be%20treated%20as%20a%20crime%2C%20notify%20legal%40company.com.&width=800&height=450&nonce=0"
137
+ />
73
138
 
74
- This shift will happen whether we're ready or not. Our mission is to make it excellent, not just good.
139
+ [Read more about the language](./BLUEPRINT.md)
75
140
 
76
- **Join us in this journey!**
141
+ <div style="page-break-after: always;"></div>
142
+
143
+ ### Where to use your AI agent in book
144
+
145
+ Books can be useful in various applications and scenarios. Here are some examples:
146
+
147
+ #### Chat apps:
148
+
149
+ Create your own chat shopping assistant and place it in your eShop.
150
+ You will be able to answer customer questions, help them find products, and provide personalized recommendations. Everything is tightly controlled by the book you have written.
151
+
152
+ #### Reply Agent:
153
+
154
+ Create your own AI agent, which will look at your emails and reply to them. It can even create drafts for you to review before sending.
155
+
156
+ #### Coding Agent:
157
+
158
+ Do you love Vibecoding, but the AI code is not always aligned with your coding style and architecture, rules, security, etc.? Create your own coding agent to help enforce your specific coding standards and practices.
159
+
160
+ This can be integrated to almost any Vibecoding platform, like GitHub Copilot, Amazon CodeWhisperer, Cursor, Cline, Kilocode, Roocode,...
161
+
162
+ They will work the same as you are used to, but with your specific rules written in book.
163
+
164
+ #### Internal Expertise
165
+
166
+ Do you have an app written in TypeScript, Python, C#, Java, or any other language, and you are integrating the AI.
167
+
168
+ You can avoid struggle with choosing the best model, its settings like temperature, max tokens, etc., by writing a book agent and using it as your AI expertise.
169
+
170
+ Doesn't matter if you do automations, data analysis, customer support, sentiment analysis, classification, or any other task. Your AI agent will be tailored to your specific needs and requirements.
171
+
172
+ Even works in no-code platforms!
173
+
174
+ <div style="page-break-after: always;"></div>
175
+
176
+ ### How to create your AI agent in book
177
+
178
+ Now you want to use it. There are several ways how to write your first book:
179
+
180
+ #### From scratch with help from Paul
181
+
182
+ We have written ai asistant in book who can help you with writing your first book.
183
+
184
+ #### Your AI twin
185
+
186
+ Copy your own behavior, personality, and knowledge into book and create your AI twin. It can help you with your work, personal life, or any other task.
187
+
188
+ #### AI persona workpool
189
+
190
+ Or you can pick from our library of pre-written books for various roles and tasks. You can find books for customer support, coding, marketing, sales, HR, legal, and many other roles.
77
191
 
78
192
 
79
193
 
@@ -190,78 +304,207 @@ Join our growing community of developers and users:
190
304
 
191
305
  ## 📘 Book Language Blueprint
192
306
 
193
- _A concise, Markdown-based DSL for crafting AI workflows and automations._
307
+ <blockquote style="color:#FFE600">
308
+ ⚠ This file is a work in progress and may be incomplete or inaccurate.
309
+ </blockquote>
194
310
 
195
- ### Introduction
311
+ ---
196
312
 
197
- Book is a Markdown-based language that simplifies the creation of AI applications, workflows, and automations. With human-readable commands, you can define inputs, outputs, personas, knowledge sources, and actions—without needing model-specific details.
313
+ Book is a simple format do define AI apps and agents. It is the source code the soul of AI apps and agents.. It's purpose is to avoid ambiguous UIs with multiple fields and low-level ways like programming in langchain.
198
314
 
199
- ### Example
315
+ Book is defined in file with `.book` extension
200
316
 
201
- ```book
202
- # 🌟 My First Book
317
+ ### Examples
203
318
 
204
- - BOOK VERSION 1.0.0
205
- - URL https://promptbook.studio/hello.book
206
- - INPUT PARAMETER {topic}
207
- - OUTPUT PARAMETER {article}
208
319
 
209
- # Write an Article
210
320
 
211
- - PERSONA Jane, marketing specialist with prior experience in tech and AI writing
212
- - KNOWLEDGE https://wikipedia.org/
213
- - KNOWLEDGE ./journalist-ethics.pdf
214
- - EXPECT MIN 1 Sentence
215
- - EXPECT MAX 5 Pages
321
+ <img
322
+ alt="Write an article about {topic} Book"
323
+ src="https://promptbook.studio/embed/book-preview.png?book=Write%20an%20article%20about%20%7Btopic%7D%0A%20%20%20%20%20%20%7C%20PERSONA%20Jane%2C%20marketing%20specialist%20with%20prior%20experience%20in%20tech%20and%20AI%20writing%0A%20%20%20%20%20%20%7C%20KNOWLEDGE%20https%3A%2F%2Fwikipedia.org%2F%0A%20%20%20%20%20%20%7C%20KNOWLEDGE%20.%2Fjournalist-ethics.pdf%0A%20%20%20%20%20%20%7C%20EXPECT%201%20Sentence%20-%205%20Pages%0A%20%20%20%20%20%20%7C%20RESULT%20%7Barticle%7D&width=800&height=450&nonce=0"
324
+ />
216
325
 
217
- > Write an article about {topic}
326
+ ---
218
327
 
219
- → {article}
220
- ```
221
328
 
222
- Each part of the book defines one of three circles:
223
329
 
224
- ### **1. What:** Workflows, Tasks and Parameters
330
+ <img
331
+ alt="Make post on LinkedIn based on @Input. Book"
332
+ src="https://promptbook.studio/embed/book-preview.png?book=Make%20post%20on%20LinkedIn%20based%20on%20%40Input.%0A%20%20%20%20%20%20%7C%20PERSONA%20%40Jane%2C%20an%20experienced%20copywriter%20and%20HR%20expert%0A%20%20%20%20%20%20%7C%20KNOWLEDGE%20cetin.cz%0A%20%20%20%20%20%20%7C%20KNOWLEDGE%20linkedin.com%2Fcompany%2Fcetin%2F&width=800&height=450&nonce=0"
333
+ />
334
+
335
+ ---
336
+
337
+
338
+
339
+ <img
340
+ alt="Odpověz na Email Book"
341
+ src="https://promptbook.studio/embed/book-preview.png?book=Odpov%C4%9Bz%20na%20Email%0A%20%20%20%20%20%20%7C%20%7BEmail%20content%7D%0A%20%20%20%20%20%20%7C%20PERSONA%20%40Pavol%20-%20pavolhejny.com%0A%20%20%20%20%20%20%7C%20KNOWLEDGE%20.%2Finstructions.pdf%0A%20%20%20%20%20%20%7C%20STYLE%20Professional%20tone%20of%20voice&width=800&height=450&nonce=0"
342
+ />
343
+
344
+ ---
345
+
346
+
347
+
348
+ <img
349
+ alt="Analyzuj {Případ}. Book"
350
+ src="https://promptbook.studio/embed/book-preview.png?book=Analyzuj%20%7BP%C5%99%C3%ADpad%7D.%0A%20%20%20%20%20%20%7C%20%7BDetaily%7D%0A%20%20%20%20%20%20%7C%20PERSONA%20%40Ji%C5%99%C3%AD%2C%20pr%C3%A1vn%C3%ADk%2C%20kter%C3%BD%20nikdy%20neode%C5%A1le%20informace%20o%20klientech%20mimo%20EU%0A%20%20%20%20%20%20%7C%20KNOWLEDGE%20%7B89%2F2012%20Sb.%20Ob%C4%8Dansk%C3%BD%20z%C3%A1kon%C3%ADk%7D&width=800&height=450&nonce=0"
351
+ />
352
+
353
+ iframe:
354
+
355
+ <iframe frameborder="0" style="width:100%;height:455px;" src="https://viewer.diagrams.net/?tags=%7B%7D&lightbox=1&highlight=0000ff&edit=_blank&layers=1&nav=1&title=#R%3Cmxfile%20scale%3D%221%22%20border%3D%220%22%20disableSvgWarning%3D%22true%22%20linkTarget%3D%22_blank%22%3E%3Cdiagram%20name%3D%22Page-1%22%20id%3D%22zo4WBBcyATChdUDADUly%22%3E7ZxtU%2BM2EMc%2FjWfaF2b8kMTwEkKOu%2Fa468BM77ViK4mKLLmy8nSfvitbihPiNEAaIHTfYHm1luzVT7vG%2F5l4cT9f3ChSTG5lRrkXBdnCi6%2B9KAo7YQ8OxrK0liBKastYsczaGsM9%2B0mdo7VOWUbLDUctJdes2DSmUgia6g0bUUrON91Gkm%2FOWpCxnTFoDPcp4XTL7QfL9KS2nnfXvD9TNp64mcPA9uTEOVtDOSGZnK%2BZ4oEX95WUum7liz7lJnouLvV1n3b0rm5MUaGfcoFdiRnhU%2Ftsf1KlGTwqWPtSaMIEVfZe9dIFoJyznBMBZ1fzCdP0viCp6ZrDgoNtonMOZyE07fgwKF3svMdw9eTADJU51WoJLvYCP7qw0bK8JPZ03sQ%2B7lnbZC3ukQs7ses9Xo3dhAQaNirtEbrYipAX9TjMcFUWRDSOvb%2BnZtGuMpmWPhOaKkG4b0j1R2EcdbNO6iej0cgfhufQGiaJnw7PaXIRJT2adpsBoDW2x2qaYiP0zovDuvjuYS%2FDs%2FgcjDlRYyZ8LQtjiwrd2IZSa5k35vX5goypzcG12n0%2F9rG3b2kEuPhltVkvwWE1UVB1jEjO%2BLLugmtIbkCxV95JuD0JHbdSyMedXtQ3Owd6ypqyq2pnc6nqwdR4%2BEtQO7nDr7XTkKQPYyWnIvPX%2FLUionT0rW5vRhQjcBTTnCqW1q5Cqhx2wrYXJaX2SQntPY6EVyBok63%2B1bGQJdNM7huP5vIvtu0zs5sW5mNjO8aQlNRQUntU29SvImiCwUlR2nUqFC2pmtFHUNSLfkseqPGRpYaDNAv%2FlYkHmn0RdorM2R0fsKFqRN4%2FNhe1Uxh060YUJi9AZ%2B52IRgSYBCh2gOV1wm%2BiGKqT5AYTDRHYuJsDwxgLl5WGTtRGHW3imOntTgGH7A2ht34YGgxxT0T5z8Gd%2Fffv11iWURmnlMWfzP%2FU50eMFgVj4VEFdBqwemigMhQkVZv3KkslnMFY6qq35g%2B3zmvfS9WB9TSoLddSwMspZgWj7cHfv%2F2%2FcfXwfXN4DSLKebGI3GRUs3EWfoTkx0muw8D9TGSXYjJ7uS54NVHV5PvIN9En%2BAvrP7StEwWNGLG87NgxmbI1P%2BYKbfoQ9VCyw6IWpjZcn6kFWq6MPY1TdA%2ByDWnI9PjHvDSmnOWZXyXtFgtOTWSW7CabI%2B62GtXF62Y2HmimBg64yFiohOw37XeGjod20bIf2qI%2FhO9NQxRcH3%2FL4eYlFFwxS%2FLpwIVCq7IBAqur4Usfjh5A5xRcEVmUHDFqoiCK5ZSTIsH7QEUXJGLNi5QcMVk9%2BGgRsEVuWjjAgVXZAoFV%2B9FgmsYtOuLb6K4RieouK504tdRXGNUXN%2F%2F2yFmZVRc8dPyqUCFiisygYrrayGLX07eAGdUXJEZVFyxKqLiiqUU0%2BJBewAVV%2BSijQtUXDHZfTioUXFFLtq4QMUVmULF1XuZ4hq9meIKp83PFVd9N82vPseDfwA%3D%3C%2Fdiagram%3E%3C%2Fmxfile%3E"></iframe>
356
+
357
+ books.svg
358
+
359
+ ![Books](./books/diagram/books.svg)
360
+
361
+ books.png
362
+
363
+ ![Books](./books/diagram/books.png)
364
+
365
+ ### Basic Commitments:
366
+
367
+ Book is composed of commitments, which are the building blocks of the book. Each commitment defines a specific task or action to be performed by the AI agent. The commitments are defined in a structured format, allowing for easy parsing and execution.
368
+
369
+ #### `PERSONA`
370
+
371
+ defines basic contour of
372
+
373
+ > PERSONA @Joe Average man with
374
+
375
+ also the PERSONA is
376
+
377
+ Describes
378
+
379
+ #### `RULE` or `RULES`
380
+
381
+ defines
382
+
383
+ #### `STYLE`
384
+
385
+ xxx
386
+
387
+ #### `SAMPLE`
388
+
389
+ xxx
390
+
391
+ #### `KNOWLEDGE`
392
+
393
+ xxx
394
+
395
+ #### `EXPECT`
396
+
397
+ xxx
398
+
399
+ #### `FORMAT`
400
+
401
+ xxx
402
+
403
+ #### `JOKER`
404
+
405
+ xxx
406
+
407
+ #### `MODEL`
408
+
409
+ xxx
410
+
411
+ #### `ACTION`
412
+
413
+ xxx
414
+
415
+ #### `META`
416
+
417
+ ### Names
418
+
419
+ each commitment is
420
+
421
+ `PERSONA`
422
+
423
+ Variable names
424
+
425
+ ### Types
426
+
427
+ ### Miscellaneous aspects of Book language
428
+
429
+ #### Named vs Anonymous commitments
430
+
431
+ #### Single line vs multiline
432
+
433
+ #### Bookish vs Non-bookish definitions
434
+
435
+ ---
436
+
437
+ ## **\_\_\_\_**
438
+
439
+ Great context and prompt can make or break you AI app. In last few years we have came from simple one-shot prompts. When you want to add conplexity you have finetunned the model or add better orchestration. But with really large large language models the context seems to be a king.
440
+
441
+ The Book is the language to describe and define your AI app. Its like a shem for a Golem, book is the shem and model is the golem.
442
+
443
+
444
+
445
+ <img
446
+ alt="Franz Kafka Book"
447
+ src="https://promptbook.studio/embed/book-preview.png?book=Franz%20Kafka%0A%20%20%20%20%20%20%7C%20PERSONA%20Franz%20Kafka%2C%20a%20writer%20who%20is%20interested%20in%20the%20human%20condition%20and%20the%20absurdity%20of%20life%2C%20speaks%20German%20and%20Czech%20and%20English%0A%20%20%20%20%20%20%7C%20STYLE%20%7Bkafka.com%2Fthe-castle%7D%0A%20%20%20%20%20%20%7C%20STYLE%20%7Bkafka.com%2Fthe-trial.pdf%7D%0A%20%20%20%20%20%20%7C%20STYLE%20%7Bkafka.com%2Fmetamorphosis.docx%7D%0A%20%20%20%20%20%20%7C%20KNOWLEDGE%20Franz%20Kafka%20has%20a%20deep%20understanding%20of%20existentialism%2C%20surrealism%2C%20and%20the%20human%20psyche%0A%20%20%20%20%20%20%7C%20GOAL%20Write%20a%20short%20story%20that%20explores%20the%20themes%20of%20alienation%2C%20bureaucracy%2C%20and%20the%20absurd%0A%20%20%20%20%20%20%7C%20ACTION%20%7Bmcp&width=800&height=450&nonce=0"
448
+ />
449
+
450
+ ## Who, what and how?
451
+
452
+ To write a good prompt and the book you will be answering 3 main questions
453
+
454
+ - **Who** is working on the task, is it a team or an individual? What is the role of the person in the team? What is the background of the person? What is the motivation of the person to work on this task?
455
+ You rather want `Paul, an typescript developer who prefers SOLID code` not `gemini-2`
456
+ - **What**
457
+ - **How**
225
458
 
226
- What work needs to be done. Each book defines a [workflow _(scenario or pipeline)_](https://github.com/webgptorg/promptbook/discussions/88), which is one or more tasks. Each workflow has a fixed input and output. For example, you have a book that generates an article from a topic. Once it generates an article about AI, once about marketing, once about cooking. The workflow (= your AI program) is the same, only the input and output change.
459
+ each commitment (described bellow) is connected with one of theese 3 questions.
227
460
 
228
- **Related commands:**
461
+ ### Commitments
229
462
 
230
- - [PARAMETER](https://github.com/webgptorg/promptbook/blob/main/documents/commands/PARAMETER.md)
463
+ Commitment is one piece of book, you can imagine it as one paragraph of book.
231
464
 
232
- ### **2. Who:** Personas
465
+ Each commitment starts in a new line with commitment name, its usually in UPPERCASE and follows a contents of that commitment. Contents of the commithemt is defined in natural language.
233
466
 
234
- Who does the work. Each task is performed by a persona. A persona is a description of your virtual employee. It is a higher abstraction than the model, tokens, temperature, top-k, top-p and other model parameters.
467
+ Commitments are chained one after another, in general commitments which are written later are more important and redefines things defined earlier.
235
468
 
236
- You can describe what you want in human language like `Jane, creative writer with a sense of sharp humour` instead of `gpt-4-2024-13-31, temperature 1.2, top-k 40, STOP token ".\n",...`.
469
+ Each commitment falls into one or more of cathegory who, what or how
237
470
 
238
- Personas can have access to different knowledge, tools and actions. They can also consult their work with other personas or user, if allowed.
471
+ Here are some basic commintemts:
239
472
 
240
- **Related commands:**
473
+ - `PERSONA` tells **who** is working on the task
474
+ - `KNOWLEDGE` describes **what** knowledge the person has
475
+ - `GOAL` describes **what** is the goal of the task
476
+ - `ACTION` describes **what** actions can be done
477
+ - `RULE` describes **what** rules should be followed
478
+ - `STYLE` describes **how** the output should be presented
241
479
 
242
- - [PERSONA](https://github.com/webgptorg/promptbook/blob/main/documents/commands/PERSONA.md)
480
+ ### Variables and references
243
481
 
244
- ### **3. How:** Knowledge, Instruments and Actions
482
+ When the prompt should be to be useful it should have some fixed static part and some variable dynamic part
245
483
 
246
- The resources used by the personas are used to do the work.
247
484
 
248
- **Related commands:**
249
485
 
250
- - [KNOWLEDGE](https://github.com/webgptorg/promptbook/blob/main/documents/commands/KNOWLEDGE.md) of documents, websites, and other resources
251
- - [INSTRUMENT](https://github.com/webgptorg/promptbook/blob/main/documents/commands/INSTRUMENT.md) for real-time data like time, location, weather, stock prices, searching the internet, calculations, etc.
252
- - [ACTION](https://github.com/webgptorg/promptbook/blob/main/documents/commands/ACTION.md) for actions like sending emails, creating files, ending a workflow, etc.
486
+ <img
487
+ alt="Untitled Book"
488
+ src="https://promptbook.studio/embed/book-preview.png?book=&width=800&height=450&nonce=0"
489
+ />
253
490
 
254
- ### General Principles
491
+ ### Imports
255
492
 
256
- Book language is based on markdown. It is subset of markdown. It is designed to be easy to read and write. It is designed to be understandable by both humans and machines and without specific knowledge of the language.
493
+ ### Layering
257
494
 
258
- The file has a `.book` extension and uses UTF-8 encoding without BOM.
495
+ ### Book defined in book
259
496
 
260
- Books have two variants: flat — just a prompt without structure, and full — with tasks, commands, and prompts.
497
+ ###
261
498
 
262
- 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.
499
+ Book vs:
263
500
 
264
- But unlike programming languages, it is designed to be understandable by non-programmers and non-technical people.
501
+ - Why just dont pick the right model
502
+ - Orchestration frameworks - Langchain, Google Agent ..., Semantic Kernel,...
503
+ - Finetunning
504
+ - Temperature, top_t, top_k,... etc.
505
+ - System message
506
+ - MCP server
507
+ - function calling
265
508
 
266
509
 
267
510
 
package/esm/index.es.js CHANGED
@@ -18,7 +18,7 @@ const BOOK_LANGUAGE_VERSION = '1.0.0';
18
18
  * @generated
19
19
  * @see https://github.com/webgptorg/promptbook
20
20
  */
21
- const PROMPTBOOK_ENGINE_VERSION = '0.103.0-0';
21
+ const PROMPTBOOK_ENGINE_VERSION = '0.103.0-2';
22
22
  /**
23
23
  * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
24
24
  * Note: [💞] Ignore a discrepancy between file name and entity name
@@ -35,7 +35,7 @@ export declare const ADMIN_GITHUB_NAME: string_name;
35
35
  *
36
36
  * @public exported from `@promptbook/core`
37
37
  */
38
- export declare const CLAIM = "It's time for a paradigm shift. The future of software in plain English, French or Latin";
38
+ export declare const CLAIM = "Turn your company's scattered knowledge into AI ready books";
39
39
  /**
40
40
  * Color of the Promptbook
41
41
  *
@@ -15,7 +15,7 @@ export declare const BOOK_LANGUAGE_VERSION: string_semantic_version;
15
15
  export declare const PROMPTBOOK_ENGINE_VERSION: string_promptbook_version;
16
16
  /**
17
17
  * Represents the version string of the Promptbook engine.
18
- * It follows semantic versioning (e.g., `0.102.0`).
18
+ * It follows semantic versioning (e.g., `0.103.0-1`).
19
19
  *
20
20
  * @generated
21
21
  */
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "@promptbook/fake-llm",
3
- "version": "0.103.0-0",
4
- "description": "Promptbook: Run AI apps in plain human language across multiple models and platforms",
3
+ "version": "0.103.0-2",
4
+ "description": "Promptbook: Turn your company's scattered knowledge into AI ready books",
5
5
  "private": false,
6
6
  "sideEffects": false,
7
7
  "repository": {
@@ -96,7 +96,7 @@
96
96
  "module": "./esm/index.es.js",
97
97
  "typings": "./esm/typings/src/_packages/fake-llm.index.d.ts",
98
98
  "peerDependencies": {
99
- "@promptbook/core": "0.103.0-0"
99
+ "@promptbook/core": "0.103.0-2"
100
100
  },
101
101
  "dependencies": {
102
102
  "crypto": "1.0.1",
package/umd/index.umd.js CHANGED
@@ -22,7 +22,7 @@
22
22
  * @generated
23
23
  * @see https://github.com/webgptorg/promptbook
24
24
  */
25
- const PROMPTBOOK_ENGINE_VERSION = '0.103.0-0';
25
+ const PROMPTBOOK_ENGINE_VERSION = '0.103.0-2';
26
26
  /**
27
27
  * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
28
28
  * Note: [💞] Ignore a discrepancy between file name and entity name