promptbook 0.72.0-8 → 0.72.0

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.
Files changed (2) hide show
  1. package/README.md +8 -8
  2. package/package.json +22 -17
package/README.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  # ![Promptbook logo - cube with letters P and B](./other/design/logo-h1.png) Promptbook
4
4
 
5
- Supercharge your use of large language models
5
+ Build responsible, controlled and transparent applications on top of LLM models!
6
6
 
7
7
 
8
8
 
@@ -20,10 +20,6 @@ Supercharge your use of large language models
20
20
 
21
21
  - ✨ **Support of [OpenAI o1 model](https://openai.com/o1/)**
22
22
 
23
- <blockquote style="color: #ff8811">
24
- <b>⚠ Warning:</b> This is a pre-release version of the library. It is not yet ready for production use. Please look at <a href="https://www.npmjs.com/package/@promptbook/core?activeTab=versions">latest stable release</a>.
25
- </blockquote>
26
-
27
23
 
28
24
 
29
25
 
@@ -32,15 +28,15 @@ Supercharge your use of large language models
32
28
 
33
29
 
34
30
 
35
- If you have a simple, single prompt for ChatGPT, GPT-4, Anthropic Claude, Google Gemini, Llama 2, 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.
31
+ 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.
36
32
 
37
- But often you will struggle with the limitations of LLMs, such as hallucinations, off-topic responses, poor quality output, language drift, word repetition repetition repetition repetition or misuse, lack of context, or just plain w𝒆𝐢rd responses. When this happens, you generally have three options:
33
+ 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 responses**. When this happens, you generally have three options:
38
34
 
39
35
  1. **Fine-tune** the model to your specifications or even train your own.
40
36
  2. **Prompt-engineer** the prompt to the best shape you can achieve.
41
37
  3. Orchestrate **multiple prompts** in a [pipeline](https://github.com/webgptorg/promptbook/discussions/64) to get the best result.
42
38
 
43
- In all of these situations, but especially in 3., the Promptbook library can make your life easier.
39
+ In all of these situations, but especially in 3., the **✨ Promptbook can make your life waaaaaaaaaay easier**.
44
40
 
45
41
  - [**Separates concerns**](https://github.com/webgptorg/promptbook/discussions/32) between prompt-engineer and programmer, between code files and prompt files, and between prompts and their execution logic.
46
42
  - Establishes a [**common format `.ptbk.md`**](https://github.com/webgptorg/promptbook/discussions/85) that can be used to describe your prompt business logic without having to write code or deal with the technicalities of LLMs.
@@ -312,6 +308,10 @@ Or you can install them separately:
312
308
  - **[@promptbook/fake-llm](https://www.npmjs.com/package/@promptbook/fake-llm)** - Mocked execution tools for testing the library and saving the tokens
313
309
  - **[@promptbook/remote-client](https://www.npmjs.com/package/@promptbook/remote-client)** - Remote client for remote execution of promptbooks
314
310
  - **[@promptbook/remote-server](https://www.npmjs.com/package/@promptbook/remote-server)** - Remote server for remote execution of promptbooks
311
+ - **[@promptbook/pdf](https://www.npmjs.com/package/@promptbook/pdf)** - Read knowledge from `.pdf` documents
312
+ - **[@promptbook/documents](https://www.npmjs.com/package/@promptbook/documents)** - Read knowledge from documents like `.docx`, `.odt`,…
313
+ - **[@promptbook/legacy-documents](https://www.npmjs.com/package/@promptbook/legacy-documents)** - Read knowledge from legacy documents like `.doc`, `.rtf`,…
314
+ - **[@promptbook/website-crawler](https://www.npmjs.com/package/@promptbook/website-crawler)** - Crawl knowledge from the web
315
315
  - **[@promptbook/types](https://www.npmjs.com/package/@promptbook/types)** - Just typescript types used in the library
316
316
  - **[@promptbook/cli](https://www.npmjs.com/package/@promptbook/cli)** - Command line interface utilities for promptbooks
317
317
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "promptbook",
3
- "version": "0.72.0-8",
3
+ "version": "0.72.0",
4
4
  "description": "Supercharge your use of large language models",
5
5
  "private": false,
6
6
  "sideEffects": false,
@@ -11,6 +11,7 @@
11
11
  "contributors": [
12
12
  "Pavol Hejný <me@pavolhejny.com> (https://www.pavolhejny.com/)"
13
13
  ],
14
+ "todo-0": "TODO: [❇️] Make better list of keywords",
14
15
  "keywords": [
15
16
  "ai",
16
17
  "llm",
@@ -48,23 +49,27 @@
48
49
  }
49
50
  ],
50
51
  "peerDependencies": {
51
- "@promptbook/core": "0.72.0-8"
52
+ "@promptbook/core": "0.72.0"
52
53
  },
53
54
  "dependencies": {
54
- "@promptbook/anthropic-claude": "0.72.0-8",
55
- "@promptbook/azure-openai": "0.72.0-8",
56
- "@promptbook/browser": "0.72.0-8",
57
- "@promptbook/cli": "0.72.0-8",
58
- "@promptbook/core": "0.72.0-8",
59
- "@promptbook/execute-javascript": "0.72.0-8",
60
- "@promptbook/fake-llm": "0.72.0-8",
61
- "@promptbook/langtail": "0.72.0-8",
62
- "@promptbook/markdown-utils": "0.72.0-8",
63
- "@promptbook/node": "0.72.0-8",
64
- "@promptbook/openai": "0.72.0-8",
65
- "@promptbook/remote-client": "0.72.0-8",
66
- "@promptbook/remote-server": "0.72.0-8",
67
- "@promptbook/types": "0.72.0-8",
68
- "@promptbook/utils": "0.72.0-8"
55
+ "@promptbook/anthropic-claude": "0.72.0",
56
+ "@promptbook/azure-openai": "0.72.0",
57
+ "@promptbook/browser": "0.72.0",
58
+ "@promptbook/cli": "0.72.0",
59
+ "@promptbook/core": "0.72.0",
60
+ "@promptbook/documents": "0.72.0",
61
+ "@promptbook/execute-javascript": "0.72.0",
62
+ "@promptbook/fake-llm": "0.72.0",
63
+ "@promptbook/langtail": "0.72.0",
64
+ "@promptbook/legacy-documents": "0.72.0",
65
+ "@promptbook/markdown-utils": "0.72.0",
66
+ "@promptbook/node": "0.72.0",
67
+ "@promptbook/openai": "0.72.0",
68
+ "@promptbook/pdf": "0.72.0",
69
+ "@promptbook/remote-client": "0.72.0",
70
+ "@promptbook/remote-server": "0.72.0",
71
+ "@promptbook/types": "0.72.0",
72
+ "@promptbook/utils": "0.72.0",
73
+ "@promptbook/website-crawler": "0.72.0"
69
74
  }
70
75
  }