Embeddings

BGE-Base-EN v1.5

This model maps any text to a low-dimensional dense vector using FlagEmbedding.

About model

BGE-Base-EN v1.5 generates English text embeddings using a BERT-based encoder architecture, achieving strong retrieval performance at a compact 109M parameter size. It enhances retrieval without requiring query instructions and is widely used for its balance of embedding quality and efficiency. Suitable for developers building search and RAG applications.

Quickstart guides

RAG

Building a RAG Workflow

RAG

How to Improve Search With Rerankers

RAG

AI Search Engine

API usage

cURL
Python
Typescript

Endpoint:

BAAI/bge-base-en-v1.5-vllm

curl -X POST https://api.together.xyz/v1/embeddings \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "Our solar system orbits the Milky Way galaxy at about 515,000 mph.",
    "model": "BAAI/bge-base-en-v1.5-vllm"
  }'

from together import Together

client = Together()

response = client.embeddings.create(
  model = "BAAI/bge-base-en-v1.5-vllm",
  input = "Our solar system orbits the Milky Way galaxy at about 515,000 mph"
)

import Together from "together-ai";

const together = new Together();

const response = await client.embeddings.create({
  model: 'BAAI/bge-base-en-v1.5-vllm',
  input: 'Our solar system orbits the Milky Way galaxy at about 515,000 mph',
});

Related models

Model specifications

Model data

Model provider
BAAI
Type
Embeddings
Main use cases
Embeddings
Deployment
Serverless
Monthly Reserved
Endpoint
BAAI/bge-base-en-v1.5-vllm
Parameters
109M
Context length
512
Input price
$0.01 / 1M tokens
Input modalities
Text
Output modalities
Structured Data

External link
Provider docs
Category
Embeddings

Run in Playground

Quickstart docs

Deploy model