docs/en/models/doubao.mdx
Doubao (Volcengine Ark) supports text chat, image understanding, image generation (Seedream), and embedding. A single ark_api_key enables all capabilities.
{
"model": "doubao-seed-2-0-pro-260215",
"ark_api_key": "YOUR_API_KEY"
}
| Parameter | Description |
|---|---|
model | Can be doubao-seed-2-0-pro-260215, doubao-seed-2-0-code-preview-260215, doubao-seed-2-0-lite-260215, etc. |
ark_api_key | Create one in the Volcengine Ark Console |
ark_base_url | Optional, defaults to https://ark.cn-beijing.volces.com/api/v3 |
Once ark_api_key is configured, the Agent's Vision tool automatically uses doubao-seed-2-0-pro-260215 to recognize images, with no extra setup required.
To manually specify a Vision model:
{
"tools": {
"vision": {
"model": "doubao-seed-2-0-pro-260215"
}
}
}
{
"skills": {
"image-generation": {
"model": "seedream-5.0-lite"
}
}
}
Available models: seedream-5.0-lite, seedream-4.5.
{
"embedding_provider": "doubao",
"embedding_model": "doubao-embedding-vision-251215"
}
The default model is doubao-embedding-vision-251215 (multimodal embedding); the dimension (1024 or 2048) can be set via embedding_dimensions in the configuration file. After changing the embedding, run /memory rebuild-index to rebuild the index.