NEWVectors or files. Pick a path.Start →
    Models/Embeddings/BAAI/BGE-VL-base
    HFVisual Embeddingsmit

    BGE-VL-base

    by BAAI

    Lightweight vision-language embeddings for image and document retrieval

    3Kdl/month
    31likes
    150Mparams
    Identifiers
    Model ID
    BAAI/BGE-VL-base
    Feature URI
    mixpeek://image_extractor@v1/baai_bge_vl_base_v1

    Overview

    BGE-VL Base is BAAI's compact vision-language embedding model for image-text retrieval and visual document search. It gives teams a smaller open model option when CLIP-style embeddings are too generic and larger multimodal retrievers are unnecessary.

    On Mixpeek, BGE-VL Base can index screenshots, product images, scanned pages, and video keyframes so an agent can retrieve visual evidence with natural-language queries before asking a VLM to reason over the result.

    Architecture

    Sentence Transformers compatible vision-language embedding model with a compact parameter footprint. It maps visual and text inputs into a shared retrieval space for semantic similarity search.

    Mixpeek SDK Integration

    import { Mixpeek } from "mixpeek";
    
    const mx = new Mixpeek({ apiKey: "API_KEY" });
    
    // Managed: create a collection over a bucket; Mixpeek runs this model's extractor
    const collection = await mx.collections.create({
      namespace_id: "my-namespace",
      collection_name: "my-collection",
      source: { type: "bucket", bucket_ids: ["bkt_your_bucket"] },
      feature_extractor: {
        feature_extractor_name: "visual_embeddings",
        version: "v1",
        parameters: { model_id: "BAAI/BGE-VL-base" },
      },
    });

    Capabilities

    • Image-text retrieval with compact inference cost
    • Visual document and screenshot search
    • Sentence Transformers integration
    • MIT license

    Use Cases on Mixpeek

    Search product imagery by natural-language attributes
    Retrieve UI screenshots that match an agent's task description
    Index scanned pages before page-level reranking
    Build lightweight visual memory for autonomous QA agents

    Specification

    FrameworkHF
    OrganizationBAAI
    FeatureVisual Embeddings
    Output768-dim vector
    Modalitiesvideo, image
    RetrieverVector Search
    Parameters150M
    Licensemit
    Downloads/mo3K
    Likes31

    Research Paper

    BGE-VL Base

    arxiv.org

    Build a pipeline with BGE-VL-base

    Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

    Run on your data, free