FastGPTFastGPT
System Configuration/Model Configuration

Voyage AI Integration Example

Configure Voyage AI embedding, multimodal embedding, and rerank models in a self-hosted FastGPT deployment through AI Proxy.

Voyage AI provides text embedding, multimodal embedding, and rerank models. FastGPT reaches them through the Voyage channel type of AI Proxy, which converts FastGPT's OpenAI-style embedding requests and its /rerank requests to the Voyage API, so no extra service is needed.

Before reading this guide, make sure you've read the Model Configuration Guide.

The Voyage channel type and the built-in Voyage model presets require an AI Proxy and a FastGPT Plugin version that include them. The contextualized embedding models (voyage-context-*) are served as ordinary embedding models, one input per document (see the notes below).

1. Get an API Key

  1. Visit the Voyage AI dashboard and sign in.
  2. Create an API key on the API Keys page and store it securely.

2. Add a Channel

On the Model providers page, click "Add Channel" and configure the Voyage channel:

  • Name: Custom channel name, e.g., Voyage AI
  • Protocol type: Select voyage
  • Proxy URL: Leave empty to use the default https://api.voyageai.com/v1
  • API Key: Enter the Voyage API Key obtained in the previous step
  • Models: Select the Voyage models you want to use

3. Models

Model IDTypeContextPrice (USD / 1M tokens)
voyage-4-large, voyage-code-4Embedding32K0.12
voyage-4, voyage-3.5Embedding32K0.06
voyage-4-lite, voyage-3.5-liteEmbedding32K0.02
voyage-3-large, voyage-code-3Embedding32K0.18
voyage-context-4Embedding (contextualized)32K0.12
voyage-context-3Embedding (contextualized)32K0.18
voyage-finance-2Embedding32K0.12
voyage-law-2Embedding16K0.12
voyage-multimodal-3.5, voyage-multimodal-3Embedding (text and images)32K0.12 text, 0.60 per 1B image pixels
rerank-3, rerank-2.5Rerank32K0.05
rerank-3-lite, rerank-2.5-liteRerank32K0.02

Notes for embedding models:

  • FastGPT stores vectors with a fixed size of 1536. Voyage returns 1024 dimensions by default, and FastGPT pads them with zeros, which does not change cosine similarity. Keep the default dimension; other output_dimension values (256, 512, 2048) are not needed, and 2048 would be cut to 1536.
  • The built-in presets send input_type: document when text is indexed and input_type: query when it is searched. When you add a custom model, set the same in the model config:
{
  "type": "embedding",
  "provider": "Voyage",
  "model": "voyage-4",
  "name": "voyage-4",
  "isActive": true,
  "pricing": { "unitPrice": 0 },
  "config": {
    "defaultToken": 512,
    "maxToken": 32000,
    "dbConfig": { "input_type": "document" },
    "queryConfig": { "input_type": "query" }
  }
}
  • voyage-context-4 and voyage-context-3 use the contextualized embeddings API. AI Proxy sends every input as its own document with enable_auto_chunking: true and chunk_size: 32000, and does not auto-chunk queries. FastGPT sends one chunk per input, so the vector of a chunk is not conditioned on the other chunks of its file. A request fails when Voyage splits an input into more than one chunk; the preset limit of 30000 tokens keeps inputs well below that. Voyage rejects these models without input_type, so their presets also set input_type: document as the default.
  • Mark voyage-multimodal-3.5 and voyage-multimodal-3 as accepting images (vision) to use them for image indexing.

4. Test Models

After configuration, click the test button in the channel list to verify channel connectivity and model availability.

On this page

Put your business knowledge to work with AI

Import company documents and build accurate, reliable, traceable AI answers.