Agent-ModernColBERT

Name: Agent-ModernColBERT
Author: lightonai

by lightonai

150M late-interaction retriever optimized for agentic reasoning traces

1.9Kdl/month

150Mparams

HuggingFace Run it on your own data, free

Identifiers

Model ID

lightonai/Agent-ModernColBERT

Feature URI

mixpeek://text_extractor@v1/lighton_agent_moderncolbert_v1

Overview

Agent-ModernColBERT is a 150M parameter late-interaction retrieval model from LightOn, specifically trained on agentic retrieval data where queries contain reasoning traces alongside the search intent. Built on ModernBERT architecture via PyLate, it achieves 72.53% accuracy on BrowseComp-Plus, exceeding configurations using GPT-5 + Qwen3-8B despite being 26x smaller than AgentIR-4B. This makes it uniquely suited for AI agent tool-use pipelines where the query is a chain-of-thought reasoning trace, not a clean user query.

Architecture

ModernBERT-based late-interaction model trained with PyLate on AgentIR data. Uses per-token 128-dim embeddings with MaxSim scoring, like ColBERT. The key innovation is training on reasoning trace + query pairs, so the model learns to extract search intent from noisy agentic context: function calls, intermediate thoughts, and partial conclusions.

Mixpeek SDK Integration

// No extractor parameter takes a Hugging Face model id (checked against
// GET /v1/discovery/extractors, which returns 13), so Agent-ModernColBERT runs
// on your side and the output is upserted through POST
// /v1/namespaces/{namespace_id}/documents/upsert. On Enterprise the other
// path is to upload the weights instead: POST /v1/namespaces/{id}/models
// accepts the huggingface format and a custom plugin loads them.
const res = await fetch(
  "https://api.mixpeek.com/v1/namespaces/ns_your_namespace/documents/upsert",
  {
    method: "POST",
    headers: {
      Authorization: "Bearer API_KEY",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      collection_id: "col_your_collection",
      documents: [
        {
          document_id: "asset-00412",
          // The vector name has to match a vector index on the collection.
          vectors: { "text-embedding": yourVector },
          payload: { source_key: "archive/2026/asset-00412" },
        },
      ],
    }),
  },
);

// Managed alternative, if this exact model is not the requirement:
// text_extractor@v1 runs intfloat/multilingual-e5-large-instruct
// (1024-d) over a bucket, with no inference of your own.