@promptbook/anthropic-claude
Advanced tools
Changelog
0.62.0
(2024-07-8)
[🎐] Better work with usage
usageToHuman
from @promptbook/core
TotalCost
to TotalUsage
uncertainNumber
which always returned "uncertain 0"OpenAiExecutionTools
Changelog
0.61.0
(2024-07-8)
Big syntax additions Working external knowledge, personas, preparation for instruments and actions
SAMPLE
command with notation for parameter samples to .ptbk.md
filesKNOWLEDGE
command to .ptbk.md
filesEXECUTE
command to BLOCK
commandexecutionType
-> templateType
SynraxError
to ParsingError
extractParameters
to extractParameterNames
ExecutionError
to PipelineExecutionError
TemplateError
and replace with ExecutionError
.ptbk.md
filescallEmbeddingModel
to LlmExecutionTools
callChatModel
and callCompletionModel
are not required to be implemented in LlmExecutionTools
anymoreMultipleLlmExecutionTools
and make joinLlmExecutionTools
functionLlmExecutionTools
into ExecutionTools
and it will be joined automatically via joinLlmExecutionTools
MarkdownStructure
and replace by simpler solution flattenMarkdown
+ splitMarkdownIntoSections
+ parseMarkdownSection
which works just with markdown strings and export from @promptbook/utils
<- [🕞]@promptbook/markdown-utils
(and removed from @promptbook/utils
)normalizeTo_SCREAMING_CASE
-> string_SCREAMING_CASE
isValidUrl
, isValidPipelineUrl
, isValidFilePath
, isValidJavascriptName
, isValidSemanticVersion
, isHostnameOnPrivateNetwork
, isUrlOnPrivateNetwork
and isValidUuid
from @promptbook/utils
systemMessage
, temperature
and seed
to ModelRequirements
stringifyPipelineJson
to stringify PipelineJson
with pretty formatting of loooooong knowledge indexes from @promptbook/core