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

# Managed embeddings

> Configure managed embedding vector fields in LambdaDB, including supported providers, supported models, dimension rules, and query behavior.

Managed embeddings let LambdaDB generate vector values from a source text field and store them in a managed `vector` field.

Use managed embeddings when you want LambdaDB to own:

* embedding model selection
* vector generation during document writes
* query embedding generation for vector search

Managed embedding generation consumes **inference usage**. Inference usage is measured in LIU (LambdaDB Inference Unit). See [Understanding costs](/guides/costs/understanding-costs#inference-usage).

## Supported providers

LambdaDB currently supports the following embedding provider:

| Provider | Status    |
| :------- | :-------- |
| `openai` | Supported |

## Supported models

The following OpenAI embedding models are currently supported for managed embedding vector fields.

| Model                    | Default dimensions | Dimensions parameter         | Similarity |
| :----------------------- | :----------------- | :--------------------------- | :--------- |
| `text-embedding-3-small` | `1536`             | Optional, from `1` to `1536` | `cosine`   |
| `text-embedding-3-large` | `3072`             | Optional, from `1` to `3072` | `cosine`   |
| `text-embedding-ada-002` | `1536`             | Fixed at `1536`              | `cosine`   |

## Collection schema

Define a managed embedding vector field with `managedEmbedding: true` and an `embedding` block.

```json theme={null}
{
  "indexConfigs": {
    "body": {
      "type": "text",
      "analyzers": ["english"]
    },
    "bodyEmbedding": {
      "type": "vector",
      "managedEmbedding": true,
      "embedding": {
        "provider": "openai",
        "model": "text-embedding-3-small",
        "sourceField": "body"
      }
    }
  }
}
```

## Schema rules

* `embedding.provider` is required
* `embedding.model` is required
* `embedding.sourceField` is required
* `embedding.sourceField` must reference a `text` field in the same collection
* managed embedding vector fields must not use top-level `dimensions`
* managed embedding vector fields must not use top-level `similarity`
* LambdaDB resolves and stores the effective `embedding.dimensions` and `embedding.similarity`

## Write behavior

For managed embedding vector fields, send the source text field and let LambdaDB generate the vector value.

Do not send direct vector values for managed embedding fields in:

* [upsert](/guides/documents/upsert-data)
* [update](/guides/documents/update-data)

Example upsert payload:

```json theme={null}
{
  "docs": [
    {
      "id": "doc-1",
      "body": "Refunds are available within 7 days of purchase."
    }
  ]
}
```

## Query behavior

For managed embedding vector fields, use `knn.queryText` instead of `knn.queryVector`.

```json theme={null}
{
  "query": {
    "knn": {
      "field": "bodyEmbedding",
      "queryText": "refund policy",
      "k": 10
    }
  }
}
```

For full query examples, see [Vector query](/guides/search/vector).

## Bulk upsert

`bulk upsert` is not supported for collections that contain managed embedding vector fields.

Use the regular document write flow instead:

* [Upsert data](/guides/documents/upsert-data)
* [Update data](/guides/documents/update-data)