> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# VoyageAI Embedder

> Generate VoyageAI retrieval embeddings with explicit document and query input types.

`VoyageAIEmbedder` defaults to `voyage-2` with 1024 dimensions.

```python voyageai_embedder.py theme={null}
from agno.knowledge.embedder.voyageai import VoyageAIEmbedder

document_embedder = VoyageAIEmbedder(
    request_params={"input_type": "document"},
)
query_embedder = VoyageAIEmbedder(
    request_params={"input_type": "query"},
)

document_vector = document_embedder.get_embedding(
    "The quick brown fox jumps over the lazy dog."
)
query_vector = query_embedder.get_embedding("Which animal jumps?")

print(len(document_vector), len(query_vector))
```

<Warning>
  `VoyageAIEmbedder` applies one `request_params` dictionary to every call. A single instance used by a vector database therefore applies the same `input_type` to document insertion and query search. VoyageAI retrieval models distinguish `document` from `query` inputs.
</Warning>

For a nondefault vector size, set `dimensions` and `request_params={"output_dimension": ...}` to the same value.

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Export the API key">
    ```bash theme={null}
    export VOYAGE_API_KEY=your_voyage_api_key_here
    ```
  </Step>

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno voyageai
    ```
  </Step>

  <Step title="Run the example">
    ```bash theme={null}
    python voyageai_embedder.py
    ```
  </Step>
</Steps>

## Developer Resources

* [VoyageAIEmbedder reference](/reference/knowledge/embedder/voyageai)
* [VoyageAI text embeddings](https://docs.voyageai.com/docs/embeddings)
* [Embedders overview](/knowledge/concepts/embedder/overview)