Skip to main content

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 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

​
Supported providers

LambdaDB currently supports the following embedding provider:
ProviderStatus
openaiSupported

​
Supported models

The following OpenAI embedding models are currently supported for managed embedding vector fields.
ModelDefault dimensionsDimensions parameterSimilarity
text-embedding-3-small1536Optional, from 1 to 1536cosine
text-embedding-3-large3072Optional, from 1 to 3072cosine
text-embedding-ada-0021536Fixed at 1536cosine

​
Collection schema

Define a managed embedding vector field with managedEmbedding: true and an embedding block. 
{
  "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: Example upsert payload: 
{
  "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. 
{
  "query": {
    "knn": {
      "field": "bodyEmbedding",
      "queryText": "refund policy",
      "k": 10
    }
  }
}
For full query examples, see Vector query.

​
Bulk upsert

bulk upsert is not supported for collections that contain managed embedding vector fields. Use the regular document write flow instead: