com.innovaphone.assistant

This API is used for communication with a large language model (LLM) and text translation (HTML payload is also supported) against an externally hosted service.

Messages

Question
Translate
GetTargetLanguages
DetectLanguage

Question

Transfers the specified question to the LLM in order to receive a response.

{
    mt:   "Question",
    messages: [{ role: "user", content: "The actual question comes here..." }]
}

Parameters

string mt	message type [mandatory]
array of objects messages	an array of messages to be transfered [mandatory]
number temperature	a number between 0 and 1 which determines the creativity of the response (defaults to 0) [optional]
number max_tokens	limits the length of the response by specifying the maximum number of tokens (words and punctuation) to generate [optional]
number top_p	controls the probability threshold for generating tokens, ensuring that the generated tokens have a cumulative probability of at least the specified value [optional]
number n	specifies the number of chat completion choices to generate for each input message [optional]
string or array of strings stop	a string or array of strings that, if present, stops the generation process when the model outputs this token [optional]
number presence_penalty	penalizes the model for generating tokens that are already present in the conversation history, encouraging new content [optional]
number frequency_penalty	penalizes the model for generating repetitive tokens, thus reducing repetition in the responses [optional]
array of objects tools	provides function specifications to enable models to generate function arguments and invoke functions as part of the response [optional]
string tool_choice	forces the model to use a specific function or not use any function at all [optional]
number seed	sets the random seed for reproducibility, ensuring consistent outputs for the same input parameters [optional]

Note:

Not all parameters may be supported by your LLM provider! Adding them might throw a HTTP error.

Response

{
    mt:        "QuestionResult",
    message:   { role: "assistant", content: "The answer to your question is....!" }
}

Parameters

string mt	message type (is "QuestionResult")
object message	the response object of the LLM

Error Response

If you run into an error you will receive the following response.

{
    mt:    "QuestionResult",
   message:   { content: "The actual error message" },
    error: true
}

Parameters

string mt	message type (is "TranslateResult")
string object	English error message which can be shown to the User
bool error	labelling whether error was send. Only sent if true [optional]

Translate

Translate a specific payload to requested language.

{
    mt:   "Translate",
    html: "Payload we want translated",
    langDst: "de"
}

Parameters

string mt	message type [mandatory]
string html	payload to be translated [mandatory]
string langSrc	2 letter source language. If not set, the language will be detected. [optional]
string langDst	2 letter target language. If not set, the current myApps language will be used. [optional]

If you want to exclude some content from translation, you can wrap them in an HTML tag with the parameter translate="no". (Example: "Bananas are <span translate="no">yellow</span> fruits.)

Response

{
    mt:        "TranslateResult",
    html:      "Nutzdaten, die übersetzt werden sollen",
    langSrc:   "en"
    langDst:   "de"
    unchanged: false
}

Parameters

string mt	message type (is "TranslateResult")
string html	translated payload
string langSrc	2 letter source language
string langDst	2 letter target language
bool unchanged	labelling if the payload in html have been changed

Error Response

If you run into an error you will receive the following response.

{
    mt:    "TranslateResult",
    html:  "Error: [English error message which can be shown to the User]",
    error: true
}

Parameters

string mt	message type (is "TranslateResult")
string html	English error message which can be shown to the User
bool error	labelling whether error was send. Only sent if true [optional]

GetTargetLanguages

Get all possible target languages.

{
    mt:   "GetTargetLanguages"
}

Parameters

string mt

message type (is "GetTargetLanguages")

Response

{
    mt:        "GetTargetLanguagesResult",
    languages: [
        { language: "bg", name: "Bulgarian" },
        { language: "cs", name: "Czech" },
        { language: "da", name: "Danish" },
        { language: "de", name: "German" },
        { language: "el", name: "Greek" },
        ...
    ]
}

Parameters

string mt	message type (is "GetTargetLanguagesResult")
array languages	array of all supported target languages

DetectLanguage

Detect langiage from given string.

{
    mt:   "DetectLanguage",
    html: "Payload that should be detected"
}

Parameters

string mt	message type (is "DetectLanguage")
string html	payload

Response

{
    mt:   "DetectLanguageResult",
    lang: "en"
}

Parameters

string mt	message type (is "DetectLanguageResult")
array lang	2-letter detected language, empty if no match
bool error	labelling whether error was send. Only sent if true [optional]

Example

You can consume the API com.innovaphone.assistant and send request to it. Inside the callback you can access the response text via recv.msg.message.content


    var assistantApi = start.consumeApi("com.innovaphone.assistant");
    let messages = [];
    messages.push({ role: "system", content: "Answer in the language of the input!" });
    messages.push({ role: "user", content: "What do you know about innovaphone?" });

    assistantApi.sendSrc({ mt: "Question", messages: messages }, assistantApi.providers[0], (recv) => {
        if (recv.msg?.message?.content) {
            console.log('response text: ' + recv.msg.message.content);
        }
    });