@promptbook/deepseek 0.103.0-1 → 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
@@ -59,19 +59,131 @@ Rest of the documentation is common for **entire promptbook ecosystem**:
59
59
 
60
60
 
61
61
 
62
- ## 🤍 The Book Abstract
62
+ ## 📖 The Book Whitepaper
63
63
 
64
- **It's time for a paradigm shift! The future of software is written in plain English, French, or Latin.**
64
+ 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.
65
65
 
66
- 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**!
66
+ 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.
67
67
 
68
- 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!
68
+ 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.
69
69
 
70
- 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.
71
70
 
72
- This shift will happen whether we're ready or not. Our mission is to make it excellent, not just good.
73
71
 
74
- **Join us in this journey!**
72
+ <img
73
+ alt="Paul Smith & Associés Book"
74
+ 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"
75
+ />
76
+
77
+ <div style="page-break-after: always;"></div>
78
+
79
+ ### Aspects of great AI agent
80
+
81
+ 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.
82
+
83
+ You can look at it as prompting (or writing a system message), but decorated by **commitments**.
84
+
85
+ #### `Persona` commitment
86
+
87
+ 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.
88
+
89
+
90
+
91
+ <img
92
+ alt="Paul Smith & Associés Book"
93
+ 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"
94
+ />
95
+
96
+ #### `Knowledge` commitment
97
+
98
+ Knowledge Commitment allows you to provide specific information, facts, or context that the AI should be aware of when responding.
99
+
100
+ This can include domain-specific knowledge, company policies, or any other relevant information.
101
+
102
+ 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.
103
+
104
+
105
+
106
+ <img
107
+ alt="Paul Smith & Associés Book"
108
+ 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"
109
+ />
110
+
111
+ #### `Rule` commitment
112
+
113
+ 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.
114
+
115
+ Depending on rule strictness, Promptbook will either propagate it to the prompt or use other techniques, like adversary agent, to enforce it.
116
+
117
+
118
+
119
+ <img
120
+ alt="Paul Smith & Associés Book"
121
+ 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"
122
+ />
123
+
124
+ #### `Action` commitment
125
+
126
+ 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.
127
+
128
+
129
+
130
+ <img
131
+ alt="Paul Smith & Associés Book"
132
+ 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"
133
+ />
134
+
135
+ [Read more about the language](./BLUEPRINT.md)
136
+
137
+ <div style="page-break-after: always;"></div>
138
+
139
+ ### Where to use your AI agent in book
140
+
141
+ Books can be useful in various applications and scenarios. Here are some examples:
142
+
143
+ #### Chat apps:
144
+
145
+ Create your own chat shopping assistant and place it in your eShop.
146
+ 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.
147
+
148
+ #### Reply Agent:
149
+
150
+ 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.
151
+
152
+ #### Coding Agent:
153
+
154
+ 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.
155
+
156
+ This can be integrated to almost any Vibecoding platform, like GitHub Copilot, Amazon CodeWhisperer, Cursor, Cline, Kilocode, Roocode,...
157
+
158
+ They will work the same as you are used to, but with your specific rules written in book.
159
+
160
+ #### Internal Expertise
161
+
162
+ Do you have an app written in TypeScript, Python, C#, Java, or any other language, and you are integrating the AI.
163
+
164
+ 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.
165
+
166
+ 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.
167
+
168
+ Even works in no-code platforms!
169
+
170
+ <div style="page-break-after: always;"></div>
171
+
172
+ ### How to create your AI agent in book
173
+
174
+ Now you want to use it. There are several ways how to write your first book:
175
+
176
+ #### From scratch with help from Paul
177
+
178
+ We have written ai asistant in book who can help you with writing your first book.
179
+
180
+ #### Your AI twin
181
+
182
+ 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.
183
+
184
+ #### AI persona workpool
185
+
186
+ 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.
75
187
 
76
188
 
77
189
 
@@ -188,78 +300,207 @@ Join our growing community of developers and users:
188
300
 
189
301
  ## 📘 Book Language Blueprint
190
302
 
191
- _A concise, Markdown-based DSL for crafting AI workflows and automations._
303
+ <blockquote style="color:#FFE600">
304
+ ⚠ This file is a work in progress and may be incomplete or inaccurate.
305
+ </blockquote>
192
306
 
193
- ### Introduction
307
+ ---
194
308
 
195
- 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.
309
+ 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.
196
310
 
197
- ### Example
311
+ Book is defined in file with `.book` extension
198
312
 
199
- ```book
200
- # 🌟 My First Book
313
+ ### Examples
201
314
 
202
- - BOOK VERSION 1.0.0
203
- - URL https://promptbook.studio/hello.book
204
- - INPUT PARAMETER {topic}
205
- - OUTPUT PARAMETER {article}
206
315
 
207
- # Write an Article
208
316
 
209
- - PERSONA Jane, marketing specialist with prior experience in tech and AI writing
210
- - KNOWLEDGE https://wikipedia.org/
211
- - KNOWLEDGE ./journalist-ethics.pdf
212
- - EXPECT MIN 1 Sentence
213
- - EXPECT MAX 5 Pages
317
+ <img
318
+ alt="Write an article about {topic} Book"
319
+ 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"
320
+ />
214
321
 
215
- > Write an article about {topic}
322
+ ---
216
323
 
217
- → {article}
218
- ```
219
324
 
220
- Each part of the book defines one of three circles:
221
325
 
222
- ### **1. What:** Workflows, Tasks and Parameters
326
+ <img
327
+ alt="Make post on LinkedIn based on @Input. Book"
328
+ 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"
329
+ />
330
+
331
+ ---
332
+
333
+
334
+
335
+ <img
336
+ alt="Odpověz na Email Book"
337
+ 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"
338
+ />
339
+
340
+ ---
341
+
342
+
343
+
344
+ <img
345
+ alt="Analyzuj {Případ}. Book"
346
+ 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"
347
+ />
348
+
349
+ iframe:
350
+
351
+ <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>
352
+
353
+ books.svg
354
+
355
+ ![Books](./books/diagram/books.svg)
356
+
357
+ books.png
358
+
359
+ ![Books](./books/diagram/books.png)
360
+
361
+ ### Basic Commitments:
362
+
363
+ 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.
364
+
365
+ #### `PERSONA`
366
+
367
+ defines basic contour of
368
+
369
+ > PERSONA @Joe Average man with
370
+
371
+ also the PERSONA is
372
+
373
+ Describes
374
+
375
+ #### `RULE` or `RULES`
376
+
377
+ defines
378
+
379
+ #### `STYLE`
380
+
381
+ xxx
382
+
383
+ #### `SAMPLE`
384
+
385
+ xxx
386
+
387
+ #### `KNOWLEDGE`
388
+
389
+ xxx
390
+
391
+ #### `EXPECT`
392
+
393
+ xxx
394
+
395
+ #### `FORMAT`
396
+
397
+ xxx
398
+
399
+ #### `JOKER`
400
+
401
+ xxx
402
+
403
+ #### `MODEL`
404
+
405
+ xxx
406
+
407
+ #### `ACTION`
408
+
409
+ xxx
410
+
411
+ #### `META`
412
+
413
+ ### Names
414
+
415
+ each commitment is
416
+
417
+ `PERSONA`
418
+
419
+ Variable names
420
+
421
+ ### Types
422
+
423
+ ### Miscellaneous aspects of Book language
424
+
425
+ #### Named vs Anonymous commitments
426
+
427
+ #### Single line vs multiline
428
+
429
+ #### Bookish vs Non-bookish definitions
430
+
431
+ ---
432
+
433
+ ## **\_\_\_\_**
434
+
435
+ 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.
436
+
437
+ 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.
438
+
439
+
440
+
441
+ <img
442
+ alt="Franz Kafka Book"
443
+ 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"
444
+ />
445
+
446
+ ## Who, what and how?
447
+
448
+ To write a good prompt and the book you will be answering 3 main questions
449
+
450
+ - **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?
451
+ You rather want `Paul, an typescript developer who prefers SOLID code` not `gemini-2`
452
+ - **What**
453
+ - **How**
223
454
 
224
- 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.
455
+ each commitment (described bellow) is connected with one of theese 3 questions.
225
456
 
226
- **Related commands:**
457
+ ### Commitments
227
458
 
228
- - [PARAMETER](https://github.com/webgptorg/promptbook/blob/main/documents/commands/PARAMETER.md)
459
+ Commitment is one piece of book, you can imagine it as one paragraph of book.
229
460
 
230
- ### **2. Who:** Personas
461
+ 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.
231
462
 
232
- 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.
463
+ Commitments are chained one after another, in general commitments which are written later are more important and redefines things defined earlier.
233
464
 
234
- 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",...`.
465
+ Each commitment falls into one or more of cathegory who, what or how
235
466
 
236
- Personas can have access to different knowledge, tools and actions. They can also consult their work with other personas or user, if allowed.
467
+ Here are some basic commintemts:
237
468
 
238
- **Related commands:**
469
+ - `PERSONA` tells **who** is working on the task
470
+ - `KNOWLEDGE` describes **what** knowledge the person has
471
+ - `GOAL` describes **what** is the goal of the task
472
+ - `ACTION` describes **what** actions can be done
473
+ - `RULE` describes **what** rules should be followed
474
+ - `STYLE` describes **how** the output should be presented
239
475
 
240
- - [PERSONA](https://github.com/webgptorg/promptbook/blob/main/documents/commands/PERSONA.md)
476
+ ### Variables and references
241
477
 
242
- ### **3. How:** Knowledge, Instruments and Actions
478
+ When the prompt should be to be useful it should have some fixed static part and some variable dynamic part
243
479
 
244
- The resources used by the personas are used to do the work.
245
480
 
246
- **Related commands:**
247
481
 
248
- - [KNOWLEDGE](https://github.com/webgptorg/promptbook/blob/main/documents/commands/KNOWLEDGE.md) of documents, websites, and other resources
249
- - [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.
250
- - [ACTION](https://github.com/webgptorg/promptbook/blob/main/documents/commands/ACTION.md) for actions like sending emails, creating files, ending a workflow, etc.
482
+ <img
483
+ alt="Untitled Book"
484
+ src="https://promptbook.studio/embed/book-preview.png?book=&width=800&height=450&nonce=0"
485
+ />
251
486
 
252
- ### General Principles
487
+ ### Imports
253
488
 
254
- 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.
489
+ ### Layering
255
490
 
256
- The file has a `.book` extension and uses UTF-8 encoding without BOM.
491
+ ### Book defined in book
257
492
 
258
- Books have two variants: flat — just a prompt without structure, and full — with tasks, commands, and prompts.
493
+ ###
259
494
 
260
- 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.
495
+ Book vs:
261
496
 
262
- But unlike programming languages, it is designed to be understandable by non-programmers and non-technical people.
497
+ - Why just dont pick the right model
498
+ - Orchestration frameworks - Langchain, Google Agent ..., Semantic Kernel,...
499
+ - Finetunning
500
+ - Temperature, top_t, top_k,... etc.
501
+ - System message
502
+ - MCP server
503
+ - function calling
263
504
 
264
505
 
265
506
 
package/esm/index.es.js CHANGED
@@ -16,7 +16,7 @@ const BOOK_LANGUAGE_VERSION = '1.0.0';
16
16
  * @generated
17
17
  * @see https://github.com/webgptorg/promptbook
18
18
  */
19
- const PROMPTBOOK_ENGINE_VERSION = '0.103.0-1';
19
+ const PROMPTBOOK_ENGINE_VERSION = '0.103.0-2';
20
20
  /**
21
21
  * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
22
22
  * Note: [💞] Ignore a discrepancy between file name and entity name
@@ -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., `0.103.0-0`).
18
+ * It follows semantic versioning (e.g., `0.103.0-1`).
19
19
  *
20
20
  * @generated
21
21
  */
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@promptbook/deepseek",
3
- "version": "0.103.0-1",
3
+ "version": "0.103.0-2",
4
4
  "description": "Promptbook: Turn your company's scattered knowledge into AI ready books",
5
5
  "private": false,
6
6
  "sideEffects": false,
@@ -92,7 +92,7 @@
92
92
  "module": "./esm/index.es.js",
93
93
  "typings": "./esm/typings/src/_packages/deepseek.index.d.ts",
94
94
  "peerDependencies": {
95
- "@promptbook/core": "0.103.0-1"
95
+ "@promptbook/core": "0.103.0-2"
96
96
  },
97
97
  "dependencies": {
98
98
  "@ai-sdk/deepseek": "0.1.6",
package/umd/index.umd.js CHANGED
@@ -23,7 +23,7 @@
23
23
  * @generated
24
24
  * @see https://github.com/webgptorg/promptbook
25
25
  */
26
- const PROMPTBOOK_ENGINE_VERSION = '0.103.0-1';
26
+ const PROMPTBOOK_ENGINE_VERSION = '0.103.0-2';
27
27
  /**
28
28
  * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
29
29
  * Note: [💞] Ignore a discrepancy between file name and entity name