ptbk 0.94.0-7 → 0.94.0
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 +6 -7
- package/package.json +26 -3
package/README.md
CHANGED
|
@@ -32,7 +32,7 @@ Write AI applications using plain human language across multiple models and plat
|
|
|
32
32
|
|
|
33
33
|
## 🤍 The Book Abstract
|
|
34
34
|
|
|
35
|
-
**It's time for a paradigm shift! The future of software is in plain English, French or Latin.**
|
|
35
|
+
**It's time for a paradigm shift! The future of software is written in plain English, French, or Latin.**
|
|
36
36
|
|
|
37
37
|
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**!
|
|
38
38
|
|
|
@@ -42,7 +42,7 @@ It's a revolution of writing software in **plain human language** that is unders
|
|
|
42
42
|
|
|
43
43
|
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.
|
|
44
44
|
|
|
45
|
-
This shift
|
|
45
|
+
This shift will happen whether we're ready or not. Our mission is to make it excellent, not just good.
|
|
46
46
|
|
|
47
47
|
**Join us in this journey!**
|
|
48
48
|
|
|
@@ -165,7 +165,6 @@ _A concise, Markdown-based DSL for crafting AI workflows and automations._
|
|
|
165
165
|
|
|
166
166
|
|
|
167
167
|
|
|
168
|
-
|
|
169
168
|
### Introduction
|
|
170
169
|
|
|
171
170
|
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.
|
|
@@ -193,7 +192,7 @@ Book is a Markdown-based language that simplifies the creation of AI application
|
|
|
193
192
|
→ {article}
|
|
194
193
|
```
|
|
195
194
|
|
|
196
|
-
Each part of the book defines one of
|
|
195
|
+
Each part of the book defines one of three circles:
|
|
197
196
|
|
|
198
197
|
### **1. What:** Workflows, Tasks and Parameters
|
|
199
198
|
|
|
@@ -231,9 +230,9 @@ The resources used by the personas are used to do the work.
|
|
|
231
230
|
|
|
232
231
|
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.
|
|
233
232
|
|
|
234
|
-
The file has `.book` extension
|
|
233
|
+
The file has a `.book` extension and uses UTF-8 encoding without BOM.
|
|
235
234
|
|
|
236
|
-
|
|
235
|
+
Books have two variants: flat — just a prompt without structure, and full — with tasks, commands, and prompts.
|
|
237
236
|
|
|
238
237
|
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.
|
|
239
238
|
|
|
@@ -314,7 +313,7 @@ The following glossary is used to clarify certain concepts:
|
|
|
314
313
|
- **Retrieval-augmented generation** is a machine learning paradigm where a model generates text by retrieving relevant information from a large database of text. This approach combines the benefits of generative models and retrieval models.
|
|
315
314
|
- **Longtail** refers to non-common or rare events, items, or entities that are not well-represented in the training data of machine learning models. Longtail items are often challenging for models to predict accurately.
|
|
316
315
|
|
|
317
|
-
_Note: This section is not complete dictionary, more list of general AI / LLM terms that has connection with Promptbook_
|
|
316
|
+
_Note: This section is not a complete dictionary, more list of general AI / LLM terms that has connection with Promptbook_
|
|
318
317
|
|
|
319
318
|
|
|
320
319
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "ptbk",
|
|
3
|
-
"version": "0.94.0
|
|
3
|
+
"version": "0.94.0",
|
|
4
4
|
"description": "Promptbook: Run AI apps in plain human language across multiple models and platforms",
|
|
5
5
|
"private": false,
|
|
6
6
|
"sideEffects": false,
|
|
@@ -36,6 +36,29 @@
|
|
|
36
36
|
"o1-mini",
|
|
37
37
|
"o1-preview",
|
|
38
38
|
"anthropic",
|
|
39
|
+
"claude",
|
|
40
|
+
"claude-3",
|
|
41
|
+
"claude-3-opus",
|
|
42
|
+
"claude-3-sonnet",
|
|
43
|
+
"claude-3-haiku",
|
|
44
|
+
"gemini",
|
|
45
|
+
"gemini-pro",
|
|
46
|
+
"gemini-flash",
|
|
47
|
+
"mixtral",
|
|
48
|
+
"mistral",
|
|
49
|
+
"ollama",
|
|
50
|
+
"ai-orchestration",
|
|
51
|
+
"prompt-engineering",
|
|
52
|
+
"llmops",
|
|
53
|
+
"multimodal",
|
|
54
|
+
"reasoning",
|
|
55
|
+
"rag",
|
|
56
|
+
"embeddings",
|
|
57
|
+
"function-calling",
|
|
58
|
+
"large-language-models",
|
|
59
|
+
"ai-application-framework",
|
|
60
|
+
"text-generation",
|
|
61
|
+
"ai-agents",
|
|
39
62
|
"LLMOps"
|
|
40
63
|
],
|
|
41
64
|
"license": "BUSL-1.1",
|
|
@@ -60,10 +83,10 @@
|
|
|
60
83
|
"words": []
|
|
61
84
|
},
|
|
62
85
|
"peerDependencies": {
|
|
63
|
-
"@promptbook/core": "0.94.0
|
|
86
|
+
"@promptbook/core": "0.94.0"
|
|
64
87
|
},
|
|
65
88
|
"dependencies": {
|
|
66
|
-
"promptbook": "0.94.0
|
|
89
|
+
"promptbook": "0.94.0"
|
|
67
90
|
},
|
|
68
91
|
"bin": {
|
|
69
92
|
"ptbk": "bin/promptbook-cli-proxy.js"
|