@just-every/ensemble/dist/core/ensemble_embed.js

LLM provider abstraction layer with unified streaming interface

import { getModelProvider } from '../model_providers/model_provider.js';
import { findModel } from '../data/model_data.js';
const EMBEDDING_TTL_MS = 1000 * 60 * 60;
const EMBEDDING_CACHE_MAX = 1000;
const embeddingCache = new Map();
export async function ensembleEmbed(text, agent, options) {
    const dimensions = options?.dimensions || 1536;
    const cacheKey = `${agent.model || agent.modelClass}:${text}:${dimensions}`;
    const cached = embeddingCache.get(cacheKey);
    if (cached) {
        if (Date.now() - cached.timestamp.getTime() < EMBEDDING_TTL_MS) {
            return cached.embedding;
        }
        embeddingCache.delete(cacheKey);
    }
    const model = agent.model || 'text-embedding-3-small';
    const provider = getModelProvider(model);
    if (!provider.createEmbedding) {
        throw new Error(`Provider for model ${model} does not support embeddings`);
    }
    const modelInfo = findModel(model);
    const inputTokenLimit = modelInfo?.features?.input_token_limit;
    const MAX_CHARS_PER_CHUNK = inputTokenLimit ? inputTokenLimit * 4 * 0.9 : Infinity;
    const needsChunking = inputTokenLimit && text.length > MAX_CHARS_PER_CHUNK;
    let embedding;
    if (needsChunking) {
        const chunks = [];
        for (let i = 0; i < text.length; i += MAX_CHARS_PER_CHUNK) {
            chunks.push(text.slice(i, i + MAX_CHARS_PER_CHUNK));
        }
        const result = await provider.createEmbedding(chunks, model, { ...options, dimensions });
        const embeddings = result;
        embedding = new Array(dimensions).fill(0);
        for (const vec of embeddings) {
            for (let i = 0; i < dimensions; i++) {
                embedding[i] += vec[i] / embeddings.length;
            }
        }
    }
    else {
        const result = await provider.createEmbedding(text, model, { ...options, dimensions });
        embedding = Array.isArray(result[0]) ? result[0] : result;
    }
    if (embeddingCache.size >= EMBEDDING_CACHE_MAX) {
        const oldestKey = embeddingCache.keys().next().value;
        if (oldestKey)
            embeddingCache.delete(oldestKey);
    }
    embeddingCache.set(cacheKey, {
        embedding,
        timestamp: new Date(),
    });
    return embedding;
}
//# sourceMappingURL=ensemble_embed.js.map