@promptbook/utils 0.60.1 → 0.61.0-0

package/README.md

@@ -37,19 +37,19 @@ Here is a overview of the functions which are exported from the `@promptbook/uti
 
 Sometimes you need to postprocess the output of the LLM model, every postprocessing function that is available through `POSTPROCESS` command in promptbook is exported from `@promptbook/utils`. You can use:
 
-`spaceTrim`,
-`extractAllBlocksFromMarkdown`, 
-`extractAllListItemsFromMarkdown`,
-`extractBlock` ,
-`extractOneBlockFromMarkdown`,
-`prettifyPipelineString`,
-`removeContentComments`,
-`removeEmojis`,
-`removeMarkdownFormatting`,
-`removeQuotes`,
-`trimCodeBlock`,
-`trimEndOfCodeBlock`,
-`unwrapResult`
+-   `spaceTrim`
+-   `extractAllBlocksFromMarkdown`, _<- Note: Exported from `@promptbook/markdown-utils`_
+-   `extractAllListItemsFromMarkdown` _<- Note: Exported from `@promptbook/markdown-utils`_
+-   `extractBlock`
+-   `extractOneBlockFromMarkdown `_<- Note: Exported from `@promptbook/markdown-utils`_
+-   `prettifyPipelineString`
+-   `removeContentComments`
+-   `removeEmojis`
+-   `removeMarkdownFormatting` _<- Note: Exported from `@promptbook/markdown-utils`_
+-   `removeQuotes`
+-   `trimCodeBlock`
+-   `trimEndOfCodeBlock`
+-   `unwrapResult`
 
 Very often you will use `unwrapResult`, which is used to extract the result you need from output with some additional information:
 
@@ -437,6 +437,7 @@ Or you can install them separately:
 -   **[@promptbook/core](https://www.npmjs.com/package/@promptbook/core)** - Core of the library, it contains the main logic for promptbooks
 -   **[@promptbook/node](https://www.npmjs.com/package/@promptbook/node)** - Core of the library for Node.js
 -   ⭐ **[@promptbook/utils](https://www.npmjs.com/package/@promptbook/utils)** - Utility functions used in the library but also useful for individual use in preprocessing and postprocessing LLM inputs and outputs
+-   **[@promptbook/markdown-utils](https://www.npmjs.com/package/@promptbook/markdown-utils)** - Utility functions used for processing markdown
 -   _(Not finished)_ **[@promptbook/wizzard](https://www.npmjs.com/package/@promptbook/wizzard)** - Wizard for creating+running promptbooks in single line
 -   **[@promptbook/execute-javascript](https://www.npmjs.com/package/@promptbook/execute-javascript)** - Execution tools for javascript inside promptbooks
 -   **[@promptbook/openai](https://www.npmjs.com/package/@promptbook/openai)** - Execution tools for OpenAI API, wrapper around OpenAI SDK
@@ -510,7 +511,7 @@ For example:
 }
 ```
 
-### Execution type
+### Block type
 
 Each block of promptbook can have a different execution type.
 It is specified in list of requirements for the block.
@@ -599,9 +600,8 @@ Internally it calls OpenAI, Azure, GPU, proxy, cache, logging,...
 -   _(Not implemented yet)_ `BardExecutionTools`
 -   _(Not implemented yet)_ `LamaExecutionTools`
 -   _(Not implemented yet)_ `GpuExecutionTools`
--   And a special case are `MultipleLlmExecutionTools` that combines multiple execution tools together and tries to execute the prompt on the best one.
--   Another special case are `RemoteLlmExecutionTools` that connect to a remote server and run one of the above execution tools on that server.
--   The another special case is `MockedEchoLlmExecutionTools` that is used for testing and mocking.
+-   Special case are `RemoteLlmExecutionTools` that connect to a remote server and run one of the above execution tools on that server.
+-   Another special case is `MockedEchoLlmExecutionTools` that is used for testing and mocking.
 -   The another special case is `LogLlmExecutionToolsWrapper` that is technically also an execution tools but it is more proxy wrapper around other execution tools that logs all calls to execution tools.
 
 #### Script Execution Tools
@@ -689,8 +689,6 @@ There are two types of expectations which are not strictly symmetrical:
 
 Look at [expectations.ptbk.md](samples/templates/45-expectations.ptbk.md) and [expect-json.ptbk.md](samples/templates/45-expect-json.ptbk.md) samples for more.
 
-
-
 ### Execution report
 
 Execution report is a simple object or markdown that contains information about the execution of the pipeline.