Letta · JSON Structure

Letta Embedding Config Structure

Flat structure summary of the Letta EmbeddingConfig entity, derived from the Letta OpenAPI 1.0.0 spec.

Type: Properties: 0
Artificial IntelligenceAgentsStateful AgentsMemoryMemGPTContinual LearningMCPMulti-AgentRAGOpen-Source

letta-embedding-config is a JSON Structure definition published by Letta.

Meta-schema:

JSON Structure

Raw ↑
{
  "jsonStructure": "0.1",
  "name": "letta-embedding-config",
  "title": "Letta EmbeddingConfig",
  "description": "Flat structure summary of the Letta EmbeddingConfig entity, derived from the Letta OpenAPI 1.0.0 spec.",
  "source": "https://raw.githubusercontent.com/letta-ai/letta/main/fern/openapi.json",
  "entity": "EmbeddingConfig",
  "fields": [
    {
      "name": "embedding_endpoint_type",
      "type": "string",
      "required": true,
      "description": "The endpoint type for the model.",
      "enum": [
        "openai",
        "anthropic",
        "bedrock",
        "google_ai",
        "google_vertex",
        "azure",
        "groq",
        "ollama",
        "webui",
        "webui-legacy",
        "lmstudio",
        "lmstudio-legacy",
        "llamacpp",
        "koboldcpp",
        "vllm",
        "hugging-face",
        "mistral",
        "together",
        "pinecone"
      ],
      "format": null
    },
    {
      "name": "embedding_endpoint",
      "type": "object",
      "required": false,
      "description": "The endpoint for the model (`None` if local).",
      "enum": null,
      "format": null
    },
    {
      "name": "embedding_model",
      "type": "string",
      "required": true,
      "description": "The model for the embedding.",
      "enum": null,
      "format": null
    },
    {
      "name": "embedding_dim",
      "type": "integer",
      "required": true,
      "description": "The dimension of the embedding.",
      "enum": null,
      "format": null
    },
    {
      "name": "embedding_chunk_size",
      "type": "object",
      "required": false,
      "description": "The chunk size of the embedding.",
      "enum": null,
      "format": null
    },
    {
      "name": "handle",
      "type": "object",
      "required": false,
      "description": "The handle for this config, in the format provider/model-name.",
      "enum": null,
      "format": null
    },
    {
      "name": "batch_size",
      "type": "integer",
      "required": false,
      "description": "The maximum batch size for processing embeddings.",
      "enum": null,
      "format": null
    },
    {
      "name": "azure_endpoint",
      "type": "object",
      "required": false,
      "description": "The Azure endpoint for the model.",
      "enum": null,
      "format": null
    },
    {
      "name": "azure_version",
      "type": "object",
      "required": false,
      "description": "The Azure version for the model.",
      "enum": null,
      "format": null
    },
    {
      "name": "azure_deployment",
      "type": "object",
      "required": false,
      "description": "The Azure deployment for the model.",
      "enum": null,
      "format": null
    }
  ],
  "fieldCount": 10,
  "requiredCount": 3
}

Work with this as data

Every JSON Structure here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for json structure

4 MCP tools reach this
  • find_json_structuresBrowse and filter every JSON Structure in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools

Call it yourself

curl for this page
This JSON Structure
curl "https://apis.io/api/v1/json-structures/letta-embedding-config-structure"
All json structure
curl "https://apis.io/api/v1/json-structures?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

A second provider on the same verified email joins the account you already have.