> ## Documentation Index
> Fetch the complete documentation index at: https://phidatainc-agui.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Embedders

> Convert text into vector representations for semantic search.

Embedders convert text into vectors (lists of numbers) that capture meaning. These vectors enable semantic search, so "How do I reset my passcode?" finds documents mentioning "change PIN" even without keyword matches.

```python theme={null}
from agno.knowledge.knowledge import Knowledge
from agno.knowledge.embedder.openai import OpenAIEmbedder
from agno.vectordb.pgvector import PgVector

knowledge = Knowledge(
    vector_db=PgVector(
        table_name="docs",
        db_url=db_url,
        embedder=OpenAIEmbedder(),  # Default
    ),
)
```

## How It Works

1. **Insert**: When you add content, each chunk is converted to a vector
2. **Store**: Vectors are saved in your vector database
3. **Search**: Queries are embedded and matched against stored vectors by similarity

Agno uses `OpenAIEmbedder` by default, but you can swap in any supported embedder.

## Configuration

```python theme={null}
from agno.knowledge.embedder.openai import OpenAIEmbedder

embedder = OpenAIEmbedder(
    id="text-embedding-3-small",
    dimensions=1536,
)
```

### Using with Knowledge

```python theme={null}
from agno.knowledge.knowledge import Knowledge
from agno.vectordb.pgvector import PgVector

knowledge = Knowledge(
    vector_db=PgVector(
        table_name="docs",
        db_url=db_url,
        embedder=OpenAIEmbedder(id="text-embedding-3-small"),
    ),
)

# Content is embedded automatically on insert
knowledge.insert(path="documents/")
```

## Batch Embeddings

Process multiple texts in a single API call to reduce requests and improve performance:

```python theme={null}
embedder = OpenAIEmbedder(
    id="text-embedding-3-small",
    dimensions=1536,
    enable_batch=True,
    batch_size=100,
)
```

Embedders with batch support: OpenAI, Azure OpenAI, Gemini, Cohere, Voyage AI, Mistral, Fireworks, Together, Jina, Nebius.

## Best Practices

<Warning>
  **Re-embed when changing models**: Vectors from different embedders aren't compatible. If you switch embedders, you must re-embed all content.
</Warning>

<Tip>
  **Test retrieval quality**: Use sample queries to verify you're finding the right chunks. Adjust chunking strategy or embedder if results are poor.
</Tip>

<Tip>
  **Match dimensions**: Ensure your embedder's output dimensions match what your vector database expects.
</Tip>

## Supported Embedders

| Embedder                                                            | Type         | Cost    | Notes                          |
| ------------------------------------------------------------------- | ------------ | ------- | ------------------------------ |
| [OpenAI](/knowledge/concepts/embedder/openai/overview)              | Hosted       | \$\$    | Default, excellent quality     |
| [Gemini](/knowledge/concepts/embedder/gemini/overview)              | Hosted       | \$\$    | Multilingual, Google ecosystem |
| [Cohere](/knowledge/concepts/embedder/cohere/overview)              | Hosted       | \$\$    | Strong retrieval performance   |
| [Voyage AI](/knowledge/concepts/embedder/voyageai/overview)         | Hosted       | \$\$\$  | Specialized for retrieval      |
| [Mistral](/knowledge/concepts/embedder/mistral/overview)            | Hosted       | \$\$    | European provider              |
| [Ollama](/knowledge/concepts/embedder/ollama/overview)              | Local        | Free    | Privacy, offline               |
| [FastEmbed](/knowledge/concepts/embedder/qdrant-fastembed/overview) | Local        | Free    | Fast local embeddings          |
| [HuggingFace](/knowledge/concepts/embedder/huggingface/overview)    | Local/Hosted | Free/\$ | Open source models             |
| [AWS Bedrock](/knowledge/concepts/embedder/aws-bedrock/overview)    | Hosted       | \$\$    | AWS ecosystem                  |
| [Azure OpenAI](/knowledge/concepts/embedder/azure-openai/overview)  | Hosted       | \$\$    | Azure ecosystem                |
| [Fireworks](/knowledge/concepts/embedder/fireworks/overview)        | Hosted       | \$      | Fast inference                 |
| [Together](/knowledge/concepts/embedder/together/overview)          | Hosted       | \$      | Open source models             |
| [Jina](/knowledge/concepts/embedder/jina/overview)                  | Hosted       | \$\$    | Multilingual                   |
| [Nebius](/knowledge/concepts/embedder/nebius/overview)              | Hosted       | \$      | European provider              |

## Choosing an Embedder

| Consideration          | Recommendation                                    |
| ---------------------- | ------------------------------------------------- |
| General use            | OpenAI or Gemini                                  |
| Privacy/offline        | Ollama or FastEmbed                               |
| Multilingual           | Gemini or Jina                                    |
| Cost-sensitive         | Local embedders (free) or Fireworks/Together (\$) |
| Best retrieval quality | Voyage AI or Cohere                               |

**Key factors:**

* **Hosted vs local**: Local for privacy and no API costs; hosted for quality and convenience
* **Latency and cost**: Smaller models are cheaper and faster; larger models often retrieve better
* **Language support**: Ensure your embedder supports your content's languages
* **Dimension size**: Match your vector database's expected embedding dimensions

## Next Steps

<CardGroup cols={2}>
  <Card title="OpenAI Embedder" icon="brain" href="/knowledge/concepts/embedder/openai/overview">
    Default embedder setup
  </Card>

  <Card title="Ollama Embedder" icon="server" href="/knowledge/concepts/embedder/ollama/overview">
    Local embeddings for privacy
  </Card>

  <Card title="Vector DB" icon="database" href="/knowledge/concepts/vector-db">
    Store your embeddings
  </Card>

  <Card title="Chunking" icon="scissors" href="/knowledge/concepts/chunking/overview">
    Prepare content for embedding
  </Card>
</CardGroup>