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

    1Kdl/month
    28likes
    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" });
    await mx.collections.ingest({
    collection_id: "visual-docs",
    source: { url: "s3://docs/screenshots/" },
    feature_extractors: [{
    feature: "visual_embeddings",
    model: "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/mo1K
    Likes28

    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.

    Open Studio