@markprompt/core
is the core library for Markprompt, a conversational AI
component for your website, trained on your data.
It contains core functionality for Markprompt and allows you to build abstractions on top of it.
npm install @markprompt/core
In browsers with esm.sh:
<script type="module">
import {
submitChat,
submitSearchQuery,
submitFeedback,
} from 'https://esm.sh/@markprompt/core';
</script>
import { submitChat } from '@markprompt/core/chat';
for await (const chunk of submitChat(
[{ content: 'What is Markprompt?', role: 'user' }],
'YOUR-PROJECT-KEY',
{
model: 'gpt-4o',
systemPrompt: 'You are a helpful AI assistant'
}
)) {
console.debug(chunk);
}
Submit a prompt to the Markprompt Completions API.
-
messages
(ChatMessage[]
): Chat messages to submit to the model -
projectKey
(string
): Project key for the project -
options
(SubmitChatOptions
): Optional parameters
All options are optional.
-
threadId
(string
): Thread ID -
iDontKnowMessage
(string
): Message returned when the model does not have an answer -
model
(OpenAIModelId
): The OpenAI model to use -
systemPrompt
(string
): The prompt template -
temperature
(number
): The model temperature -
topP
(number
): The model top P -
frequencyPenalty
(number
): The model frequency penalty -
presencePenalty
(number
): The model present penalty -
maxTokens
(number
): The max number of tokens to include in the response -
sectionsMatchCount
(number
): The number of sections to include in the prompt context -
sectionsMatchThreshold
(number
): The similarity threshold between the -
signal
(AbortSignal
): AbortController signal -
tools
: (OpenAI.ChatCompletionTool[]
): A list of tools the model may call -
toolChoice
: (OpenAI.ChatCompletionToolChoiceOption
): Controls which (if any) function is called by the model
A promise that resolves when the response is fully handled.
Submit a search query to the Markprompt Search API.
-
query
(string
): Search query -
projectKey
(string
): Project key for the project -
options
(object
): Optional parameters
-
limit
(number
): Maximum amount of results to return -
signal
(AbortSignal
): AbortController signal
A list of search results.
Submit feedback to the Markprompt Feedback API about a specific prompt.
-
feedback
(object
): Feedback to submit -
feedback.feedback
(object
): Feedback data -
feedback.feedback.vote
("1" | "-1" | "escalated"
): Vote -
feedback.messageId
(string
): Message ID -
projectKey
(string
): Project key for the project -
options
(object
): Optional parameters -
options.onFeedbackSubmitted
(function
): Callback function when feedback is submitted -
options.signal
(AbortSignal
): AbortController signal
A promise that resolves when the feedback is submitted. Has no return value.
The full documentation for the package can be found on the Markprompt docs.
This library is created by the team behind Markprompt (@markprompt).