smartbotic/nodes/ai/perplexity-chat.js

/**
 * @node perplexity-chat
 * @name Perplexity Chat
 * @category ai
 * @version 1.0.0
 * @description Ask Perplexity a question, with an image if there is one, and optionally get JSON back
 * @icon message-square
 */

// Generated by scripts/gen-openai-compatible-nodes.py from one implementation
// shared with every other OpenAI-compatible provider. Edit the generator, not
// this file.

// The credential this node wants, named so it can be found and so a key for
// this provider is not offered to a different one. It is stored as a plain
// bearer credential - that is what decides how it is encrypted - and this only
// says which bearer credential is the Perplexity one.
const credentialTypes = [
    {
        id: 'perplexity',
        label: 'Perplexity API key',
        baseType: 'bearer',
        description: 'An API key from perplexity.ai/settings/api',
        tokenLabel: 'API key'
    }
];

const configSchema = {
    type: 'object',
    uiGroups: [
        { title: 'Connection', fields: ['baseUrl', 'credentialId'] },
        { title: 'Model', fields: ['model', 'systemPrompt', 'userPrompt'] },
        { title: 'Answer', fields: ['responseFormat', 'jsonMode', 'temperature', 'maxTokens', 'topP', 'seed'] },
        { title: 'Image', fields: ['imageMode', 'imageField', 'imageDetail', 'passthroughImage'] },
        { title: 'When it goes wrong', fields: ['retryCount', 'retryDelayMs', 'retryMaxDelayMs', 'skipOnError', 'timeoutMs'] },
        { title: 'Advanced', fields: ['extraHeaders', 'extraBody'] }
    ],
    properties: {
        baseUrl: {
            type: 'string', title: 'Base URL',
            description: 'Where the OpenAI-compatible API lives. The default is Perplexity; change it to reach a proxy or a self-hosted gateway',
            default: 'https://api.perplexity.ai'
        },
        credentialId: {
            type: 'string', title: 'Credential',
            description: 'The stored Perplexity API key',
            dynamicOptions: { source: 'credentials', filter: { type: ['perplexity', 'bearer', 'api_key'] } }
        },
        model: {
            type: 'string', title: 'Model',
            description: 'Model name. Answers are searched for as well as generated. It publishes no model list, so type the name.',
            default: 'sonar'
        },
        systemPrompt: {
            type: 'string', title: 'System Prompt', format: 'textarea',
            description: 'The role and the output contract. When Response Format is JSON, say the word JSON here - several providers refuse JSON mode without it'
        },
        userPrompt: {
            type: 'string', title: 'User Prompt', format: 'textarea',
            description: 'The message sent with the request. Supports {{variable}} interpolation',
            default: 'Describe the input.'
        },
        responseFormat: {
            type: 'string', title: 'Response Format',
            enum: ['text', 'json'],
            enumLabels: ['Plain text', 'JSON object'],
            default: 'text',
            description: 'JSON parses the reply and fails the attempt when it is not valid JSON, so a retry gets another go'
        },
        jsonMode: {
            type: 'boolean', title: 'Ask The Provider For JSON', default: true,
            showWhen: { field: 'responseFormat', value: 'json' },
            description: 'Send response_format json_object, which makes the model return JSON rather than being asked nicely. Turn it off for a provider or model that rejects the field'
        },
        temperature: {
            type: 'number', title: 'Temperature', default: 0,
            description: 'Higher is more varied. 0 for the most repeatable output'
        },
        maxTokens: {
            type: 'number', title: 'Max Tokens',
            description: 'Upper bound on the reply. Leave empty for the provider default'
        },
        topP: {
            type: 'number', title: 'Top P',
            description: 'Nucleus sampling. Leave empty for the provider default'
        },
        seed: {
            type: 'number', title: 'Seed',
            description: 'Same seed and same input gives the same answer, where the provider supports it. Leave empty for none'
        },
        imageMode: {
            type: 'string', title: 'Image Input',
            enum: ['auto', 'none'],
            enumLabels: ['Send an image when the input has one', 'Text only'],
            default: 'none',
            description: 'Auto picks up a binary file, a base64 string or an image URL from the input. Needs a model that can see'
        },
        imageField: {
            valueKind: 'path',
            type: 'string', title: 'Image Field',
            showWhen: { field: 'imageMode', value: 'auto' },
            description: 'Optional dotted path to the base64 image, such as data.file.data. Left empty, the input is searched for one'
        },
        imageDetail: {
            type: 'string', title: 'Image Detail',
            enum: ['', 'low', 'high', 'auto'],
            enumLabels: ['(provider default)', 'Low - cheaper, coarser', 'High - more tokens, more detail', 'Auto'],
            default: '',
            showWhen: { field: 'imageMode', value: 'auto' },
            description: 'How closely to look at the image, where the provider supports it'
        },
        passthroughImage: {
            type: 'boolean', title: 'Pass The Image Through', default: false,
            showWhen: { field: 'imageMode', value: 'auto' },
            description: 'Include the base64 image in the output so a later node can store or reuse it'
        },
        retryCount: {
            type: 'number', title: 'Retries', default: 0,
            description: 'Extra attempts after a failed call or an unparseable answer'
        },
        retryDelayMs: {
            type: 'number', title: 'Retry Delay (ms)', default: 2000,
            description: 'Wait before the first retry. Doubles on each further attempt'
        },
        retryMaxDelayMs: {
            type: 'number', title: 'Max Retry Delay (ms)', default: 30000,
            description: 'Upper bound for the backoff'
        },
        skipOnError: {
            type: 'boolean', title: 'Skip On Error', default: false,
            description: 'Return success false instead of failing the workflow. Useful inside a loop, where one bad item should not end the run'
        },
        timeoutMs: {
            type: 'number', title: 'Timeout (ms)', default: 120000,
            description: 'Per-attempt request timeout'
        },
        extraHeaders: {
            type: 'object', title: 'Extra Headers',
            additionalProperties: { type: 'string' },
            description: 'Sent with the request. OpenRouter reads HTTP-Referer and X-Title to attribute usage'
        },
        extraBody: {
            type: 'object', title: 'Extra Body Fields',
            description: 'Merged into the request body, for anything this provider accepts that has no setting here'
        }
    },
    required: ['credentialId', 'model']
};

const inputSchema = { type: 'object', properties: { data: { type: 'any' } } };

const outputSchema = {
    type: 'object',
    properties: {
        success: { type: 'boolean', description: 'False when the call failed and Skip On Error is on' },
        error: { type: 'string', description: 'Why it failed, when it did' },
        content: { type: 'string', description: 'The reply as text' },
        json: { type: 'any', description: 'The parsed reply, when Response Format is JSON' },
        model: { type: 'string', description: 'The model that answered, as the provider reported it' },
        finishReason: { type: 'string', description: 'Why the model stopped - stop, length, content_filter' },
        attempts: { type: 'number', description: 'How many attempts were made' },
        usage: { type: 'object', description: 'Token counts, when the provider reports them' },
        hadImage: { type: 'boolean' },
        imageBase64: { type: 'string', description: 'The image sent, when Pass The Image Through is on' },
        mimeType: { type: 'string' },
        sourceUrl: { type: 'string', description: 'Where the image came from, when it came from a URL' },
        // Only present when the node is asked for its model list rather than run.
        models: { type: 'array', description: 'The models this provider offers' }
    }
};

const PROVIDER = 'Perplexity';

// Statuses this provider documents as answers that will not change.
//
// 401 does double duty: an invalid key AND an account out of credits both return it, so a 401 here is not necessarily a wrong key.
//
// 429 is treated as transient unless a code below says otherwise - backing off
// is exactly what a rate limit asks for. 5xx is transient unless listed.
const PERMANENT_STATUSES = [400, 401, 403];
const PERMANENT_ERROR_CODES = [];

function baseOf(config) {
    const value = String(config.baseUrl || 'https://api.perplexity.ai').trim().replace(/\/+$/, '');
    if (!value) {
        throw new Error(PROVIDER + ': a base URL is required, such as https://api.perplexity.ai');
    }
    return value;
}

function authHeaders(config) {
    const headers = { 'Content-Type': 'application/json' };

    const auth = smartbotic.credentials.get(config.credentialId);
    if (!auth || auth.success !== true) {
        throw new Error(PROVIDER + ': could not read the credential: ' +
            ((auth && auth.error) || 'unknown error'));
    }
    // Whatever shape the credential is stored as, it arrives as a ready-made
    // header - bearer and api_key both work without this node knowing which.
    headers[auth.headerName] = auth.headerValue;

    const extra = config.extraHeaders;
    if (extra && typeof extra === 'object') {
        const keys = Object.keys(extra);
        for (let i = 0; i < keys.length; i++) {
            if (extra[keys[i]] !== undefined && extra[keys[i]] !== null && extra[keys[i]] !== '') {
                headers[keys[i]] = String(extra[keys[i]]);
            }
        }
    }
    return headers;
}

function request(options) {
    const response = smartbotic.http.request(options);

    let body = response.data;
    if (typeof body === 'string' && body.length > 0) {
        try {
            body = JSON.parse(body);
        } catch (e) {
            if (response.status >= 200 && response.status < 300) {
                throw new Error(PROVIDER + ': the reply was not JSON: ' +
                    body.substring(0, 200).replace(/\s+/g, ' '));
            }
        }
    }

    if (response.status < 200 || response.status >= 300) {
        let detail = 'HTTP ' + response.status;
        let code = '';
        if (body && body.error) {
            detail = typeof body.error === 'string' ? body.error :
                (body.error.message || JSON.stringify(body.error));
            code = (body.error && body.error.code) || (body.error && body.error.type) || '';
        } else if (typeof body === 'string' && body) {
            detail = body.substring(0, 200).replace(/\s+/g, ' ');
        }

        const error = new Error(PROVIDER + ' ' + options.what + ' failed: ' + detail);
        error.status = response.status;
        // Whether asking again could ever give a different answer. Retrying a
        // refusal does not just waste time - where the refusal is a spent
        // allowance or a billing stop, it spends more of whatever ran out.
        error.permanent = PERMANENT_STATUSES.indexOf(response.status) !== -1 ||
            (PERMANENT_ERROR_CODES.length > 0 && code &&
             PERMANENT_ERROR_CODES.indexOf(String(code)) !== -1);
        throw error;
    }

    return body || {};
}

function getPath(root, path) {
    if (!root || !path) {
        return undefined;
    }
    const parts = String(path).split('.');
    let current = root;
    for (let i = 0; i < parts.length; i++) {
        if (current === null || typeof current !== 'object') {
            return undefined;
        }
        current = current[parts[i]];
    }
    return current;
}

// Models are asked for JSON and answer with a fenced code block often enough
// that refusing it would mean retrying a perfectly good answer.
function stripFences(text) {
    const out = String(text || '').trim();
    if (out.indexOf('```') === -1) {
        return out;
    }
    const first = out.indexOf('{');
    const last = out.lastIndexOf('}');
    if (first !== -1 && last !== -1 && last > first) {
        return out.substring(first, last + 1);
    }
    const firstArr = out.indexOf('[');
    const lastArr = out.lastIndexOf(']');
    if (firstArr !== -1 && lastArr !== -1 && lastArr > firstArr) {
        return out.substring(firstArr, lastArr + 1);
    }
    return out;
}

// The image can be anywhere in the input: inside a loop, or with another node
// between the download and this one, it is nested rather than sitting at the
// top. So the input is searched breadth-first rather than guessed at.
function findImage(input, override) {
    const result = { base64: '', mimeType: '', url: '' };

    if (override) {
        const direct = getPath(input, override);
        if (typeof direct === 'string' && direct.length > 0) {
            result.base64 = direct;
            return result;
        }
    }

    const roots = [];
    const queue = [input];
    let guard = 0;
    while (queue.length > 0 && guard < 64) {
        guard++;
        const node = queue.shift();
        if (!node || typeof node !== 'object') {
            continue;
        }
        roots.push(node);
        const keys = Object.keys(node);
        for (let k = 0; k < keys.length; k++) {
            const child = node[keys[k]];
            if (child && typeof child === 'object' && keys[k] !== 'file') {
                queue.push(child);
            }
        }
    }

    for (let i = 0; i < roots.length; i++) {
        const root = roots[i];
        if (!root || typeof root !== 'object') {
            continue;
        }
        if (!result.base64 && root.file && typeof root.file.data === 'string') {
            result.base64 = root.file.data;
            result.mimeType = root.file.mimeType || '';
        }
        if (!result.base64 && typeof root.base64 === 'string') {
            result.base64 = root.base64;
        }
        if (!result.base64 && typeof root.imageBase64 === 'string') {
            result.base64 = root.imageBase64;
        }
        if (!result.url && typeof root.url === 'string') {
            result.url = root.url;
        }
        if (!result.url && typeof root.sourceUrl === 'string') {
            result.url = root.sourceUrl;
        }
    }
    return result;
}

function buildMessages(config, image) {
    const messages = [];

    const system = String(config.systemPrompt || '').trim();
    if (system) {
        messages.push({ role: 'system', content: system });
    }

    const text = String(config.userPrompt || 'Describe the input.');

    if (!image.base64) {
        messages.push({ role: 'user', content: text });
        return messages;
    }

    // With an image the content becomes a list of parts, which is how every
    // OpenAI-compatible provider takes one. The base64 goes in as a data URI.
    const imagePart = {
        type: 'image_url',
        image_url: { url: 'data:' + (image.mimeType || 'image/jpeg') + ';base64,' + image.base64 }
    };
    if (config.imageDetail) {
        imagePart.image_url.detail = String(config.imageDetail);
    }

    messages.push({ role: 'user', content: [{ type: 'text', text: text }, imagePart] });
    return messages;
}

function putIfSet(target, key, value) {
    if (value === undefined || value === null || value === '') {
        return;
    }
    target[key] = value;
}

function chat(config, image, headers) {
    const body = {
        model: config.model,
        messages: buildMessages(config, image),
        stream: false
    };

    // Temperature 0 is a real setting and must survive, so emptiness is the
    // test rather than truthiness.
    putIfSet(body, 'temperature', config.temperature);
    putIfSet(body, 'max_tokens', config.maxTokens);
    putIfSet(body, 'top_p', config.topP);
    putIfSet(body, 'seed', config.seed);

    if (config.responseFormat === 'json' && config.jsonMode !== false) {
        body.response_format = { type: 'json_object' };
    }

    const extra = config.extraBody;
    if (extra && typeof extra === 'object') {
        const keys = Object.keys(extra);
        for (let i = 0; i < keys.length; i++) {
            body[keys[i]] = extra[keys[i]];
        }
    }

    const answer = request({
        method: 'POST',
        url: baseOf(config) + '/chat/completions',
        headers: headers,
        body: JSON.stringify(body),
        timeout: Number(config.timeoutMs) || 120000,
        what: 'the chat request'
    });

    const choice = (answer.choices && answer.choices[0]) || {};
    const message = choice.message || {};
    let content = message.content;

    // Some providers answer with the content already split into parts.
    if (content && typeof content !== 'string' && typeof content.length === 'number') {
        let joined = '';
        for (let i = 0; i < content.length; i++) {
            const part = content[i];
            if (part && typeof part.text === 'string') { joined += part.text; }
        }
        content = joined;
    }

    if (!content) {
        // A refusal is a documented field of its own, and reporting "empty
        // response" for one sends the reader looking in the wrong place.
        if (message.refusal) {
            throw new Error(PROVIDER + ' declined to answer: ' + message.refusal);
        }
        throw new Error(PROVIDER + ' returned an empty reply' +
            (choice.finish_reason ? ' (finished: ' + choice.finish_reason + ')' : ''));
    }

    return {
        content: String(content),
        model: String(answer.model || config.model),
        finishReason: String(choice.finish_reason || ''),
        usage: answer.usage || {}
    };
}

async function execute(config, input, context) {
    // Asked for its model list by the editor rather than run. Answered before
    // anything else, because none of the generation settings apply.
    if (config.listOnly === true) {
        // This provider publishes no model list, so there is nothing to
        // offer and saying so beats an empty dropdown with no explanation.
        return { models: [] };
    }

    let image = { base64: '', mimeType: '', url: '' };

    if (config.imageMode === 'auto') {
        image = findImage(input, config.imageField);
        if (!image.base64 && image.url) {
            smartbotic.log.info(PROVIDER + ': fetching the image from ' + image.url);
            const download = smartbotic.http.request({
                method: 'GET', url: image.url, timeout: 60000
            });
            if (download.status < 200 || download.status >= 300) {
                throw new Error(PROVIDER + ': could not fetch the image: HTTP ' + download.status);
            }
            image.base64 = typeof download.data === 'string'
                ? smartbotic.utils.base64Encode(download.data) : '';
        }
    }

    // Resolved once, outside the retry loop: a missing or broken credential is
    // not transient, and retrying it with backoff only wastes time.
    const headers = authHeaders(config);

    const wantJson = config.responseFormat === 'json';
    const attempts = 1 + (Number(config.retryCount) > 0 ? Number(config.retryCount) : 0);

    let answer = null;
    let parsed = null;
    let lastError = '';
    let used = 0;

    for (let attempt = 1; attempt <= attempts; attempt++) {
        used = attempt;
        try {
            answer = chat(config, image, headers);
            if (wantJson) {
                parsed = JSON.parse(stripFences(answer.content));
            }
            lastError = '';
            break;
        } catch (err) {
            lastError = err && err.message ? err.message : String(err);
            parsed = null;
            smartbotic.log.warn(PROVIDER + ': attempt ' + attempt + ' of ' + attempts +
                ' failed: ' + lastError);
            if (err && err.permanent) {
                smartbotic.log.warn(PROVIDER + ': the request was refused (HTTP ' +
                    err.status + '), so the remaining attempts were not made');
                break;
            }
            if (attempt < attempts) {
                const base = Number(config.retryDelayMs) || 2000;
                const cap = Number(config.retryMaxDelayMs) || 30000;
                let delay = base * Math.pow(2, attempt - 1);
                if (delay > cap) { delay = cap; }
                smartbotic.log.info(PROVIDER + ': waiting ' + delay + 'ms before the next attempt');
                smartbotic.utils.sleep(delay);
            }
        }
    }

    const passImage = config.passthroughImage === true;
    const common = {
        attempts: used,
        hadImage: image.base64 ? true : false,
        imageBase64: passImage ? image.base64 : '',
        mimeType: image.mimeType,
        sourceUrl: image.url
    };

    if (lastError) {
        if (config.skipOnError !== true) {
            throw new Error(PROVIDER + ' failed after ' + used + ' attempt(s): ' + lastError);
        }
        smartbotic.log.warn(PROVIDER + ': skipping after ' + used + ' attempt(s)');
        return Object.assign({
            success: false, error: lastError, content: (answer && answer.content) || '',
            json: null, model: config.model, finishReason: '', usage: {}
        }, common);
    }

    return Object.assign({
        success: true, error: '', content: answer.content, json: parsed,
        model: answer.model, finishReason: answer.finishReason, usage: answer.usage
    }, common);
}

module.exports = { credentialTypes, configSchema, inputSchema, outputSchema, execute };