LlamaCloud

LlamaCloud Retrieval API

Query a managed index for relevant chunks.

Documentation GitHub OpenAPI

Work with this as data

Every API 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 apis

7 MCP tools reach this

find_apisBrowse and filter every API in the catalog.
get_api_artifactsOne API's artifacts, grouped by type.
get_openapiThe primary OpenAPI for this API.
find_similar_apisAPIs that look like this one.
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 API

curl "https://apis.io/api/v1/apis/llamacloud-retrieval-api"

All apis

curl "https://apis.io/api/v1/apis?limit=25"

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

Get an API key

Free tier, no email required.

GitHub Google LinkedIn

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

OpenAPI Specification

openapi: 3.0.1
info:
  title: LlamaCloud Documents Retrieval API
  description: REST API for the LlamaCloud managed document platform from LlamaIndex, covering LlamaParse document parsing, managed ingestion pipelines and indexes, document and file management, retrieval, and LlamaExtract structured extraction. All endpoints are authenticated with a Bearer API key.
  termsOfService: https://www.llamaindex.ai/terms-of-service
  contact:
    name: LlamaIndex Support
    email: support@llamaindex.ai
  version: '1.0'
servers:
- url: https://api.cloud.llamaindex.ai/api/v1
  description: LlamaCloud v1 API
security:
- bearerAuth: []
tags:
- name: Retrieval
  description: Query a managed index for relevant chunks.
paths:
  /pipelines/{pipeline_id}/retrieve:
    post:
      operationId: retrieveFromPipeline
      tags:
      - Retrieval
      summary: Retrieve relevant chunks from a pipeline index
      description: Runs a retrieval query against a pipeline's managed index and returns the most relevant nodes, with optional reranking and metadata filters.
      parameters:
      - $ref: '#/components/parameters/PipelineId'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RetrieveRequest'
      responses:
        '200':
          description: Retrieval results.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RetrieveResponse'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '422':
          $ref: '#/components/responses/ValidationError'
components:
  schemas:
    Document:
      type: object
      properties:
        id:
          type: string
        text:
          type: string
        metadata:
          type: object
          additionalProperties: true
    RetrieveRequest:
      type: object
      required:
      - query
      properties:
        query:
          type: string
        dense_similarity_top_k:
          type: integer
          default: 6
        sparse_similarity_top_k:
          type: integer
        enable_reranking:
          type: boolean
          default: true
        rerank_top_n:
          type: integer
        retrieval_mode:
          type: string
          enum:
          - chunks
          - files_via_metadata
          - files_via_content
          - auto_routed
        filters:
          type: object
          additionalProperties: true
    Error:
      type: object
      properties:
        detail:
          type: string
    RetrieveResponse:
      type: object
      properties:
        retrieval_nodes:
          type: array
          items:
            type: object
            properties:
              node:
                $ref: '#/components/schemas/Document'
              score:
                type: number
                format: float
  parameters:
    PipelineId:
      name: pipeline_id
      in: path
      required: true
      schema:
        type: string
  responses:
    ValidationError:
      description: Request validation failed.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Unauthorized:
      description: Missing or invalid API key.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: LlamaCloud API key sent as a Bearer token.