@promptbook/node 0.93.0 → 0.94.0-1

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
@@ -25,6 +25,10 @@ Write AI applications using plain human language across multiple models and plat
25
25
 
26
26
 
27
27
 
28
+ <blockquote style="color: #ff8811">
29
+ <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>.
30
+ </blockquote>
31
+
28
32
  ## 📦 Package `@promptbook/node`
29
33
 
30
34
  - Promptbooks are [divided into several](#-packages) packages, all are published from [single monorepo](https://github.com/webgptorg/promptbook).
@@ -60,8 +64,6 @@ Rest of the documentation is common for **entire promptbook ecosystem**:
60
64
 
61
65
  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**!
62
66
 
63
-
64
-
65
67
  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!
66
68
 
67
69
  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.
@@ -247,8 +249,6 @@ Personas can have access to different knowledge, tools and actions. They can als
247
249
 
248
250
  - [PERSONA](https://github.com/webgptorg/promptbook/blob/main/documents/commands/PERSONA.md)
249
251
 
250
-
251
-
252
252
  ### **3. How:** Knowledge, Instruments and Actions
253
253
 
254
254
  The resources used by the personas are used to do the work.
@@ -309,6 +309,7 @@ Or you can install them separately:
309
309
  - **[@promptbook/vercel](https://www.npmjs.com/package/@promptbook/vercel)** - Adapter for Vercel functionalities
310
310
  - **[@promptbook/google](https://www.npmjs.com/package/@promptbook/google)** - Integration with Google's Gemini API
311
311
  - **[@promptbook/deepseek](https://www.npmjs.com/package/@promptbook/deepseek)** - Integration with [DeepSeek API](https://www.deepseek.com/)
312
+ - **[@promptbook/ollama](https://www.npmjs.com/package/@promptbook/ollama)** - Integration with [Ollama](https://ollama.com/) API
312
313
  - **[@promptbook/azure-openai](https://www.npmjs.com/package/@promptbook/azure-openai)** - Execution tools for Azure OpenAI API
313
314
 
314
315
  - **[@promptbook/fake-llm](https://www.npmjs.com/package/@promptbook/fake-llm)** - Mocked execution tools for testing the library and saving the tokens
@@ -347,8 +348,6 @@ The following glossary is used to clarify certain concepts:
347
348
 
348
349
  _Note: This section is not complete dictionary, more list of general AI / LLM terms that has connection with Promptbook_
349
350
 
350
-
351
-
352
351
  ### 💯 Core concepts
353
352
 
354
353
  - [📚 Collection of pipelines](https://github.com/webgptorg/promptbook/discussions/65)
package/esm/index.es.js CHANGED
@@ -30,7 +30,7 @@ const BOOK_LANGUAGE_VERSION = '1.0.0';
30
30
  * @generated
31
31
  * @see https://github.com/webgptorg/promptbook
32
32
  */
33
- const PROMPTBOOK_ENGINE_VERSION = '0.93.0';
33
+ const PROMPTBOOK_ENGINE_VERSION = '0.94.0-1';
34
34
  /**
35
35
  * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
36
36
  * Note: [💞] Ignore a discrepancy between file name and entity name
@@ -4545,6 +4545,13 @@ async function executePipeline(options) {
4545
4545
  * Note: This is a flag to prevent `onProgress` call after the pipeline execution is finished
4546
4546
  */
4547
4547
  let isReturned = false;
4548
+ // Note: Report all output parameters upfront as empty strings
4549
+ if (onProgress) {
4550
+ const emptyOutputParameters = Object.fromEntries(preparedPipeline.parameters.filter((param) => !param.isInput).map((param) => [param.name, '']));
4551
+ onProgress({
4552
+ outputParameters: emptyOutputParameters,
4553
+ });
4554
+ }
4548
4555
  // Note: Check that all input input parameters are defined
4549
4556
  for (const parameter of preparedPipeline.parameters.filter(({ isInput }) => isInput)) {
4550
4557
  if (inputParameters[parameter.name] === undefined) {