Trieve

Trieve Chunk API

The Chunk API from Trieve — 1 operation(s) for chunk.

Documentation GitHub OpenAPI

Specifications

⚙

OpenAPI

https://raw.githubusercontent.com/api-evangelist/trieve/refs/heads/main/openapi/trieve-chunk-api-openapi.yml

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/trieve-chunk-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: 3.1.0
info:
  title: Trieve REST Chunk API
  version: '1'
  description: 'Trieve REST API for search, recommendations, RAG, and analytics. Endpoints

    derived from https://docs.trieve.ai/api-reference and the Redoc spec at

    https://api.trieve.ai/redoc.

    '
  contact:
    name: Trieve (Devflow, Inc.)
    url: https://docs.trieve.ai/api-reference
servers:
- url: https://api.trieve.ai
  description: Trieve Cloud (production)
- url: http://localhost:8090
  description: Self-hosted (local dev)
security:
- ApiKeyAuth: []
tags:
- name: Chunk
paths:
  /api/chunk:
    post:
      tags:
      - Chunk
      summary: Create or upsert chunk(s)
      description: 'Creates new chunks. A chunk with the same tracking_id as an existing chunk

        will cause the request to fail. Bulk uploads are capped at 120 chunks

        per request.

        '
      parameters:
      - in: header
        name: TR-Dataset
        required: true
        schema:
          type: string
        description: Dataset UUID or tracking_id targeted by the request.
      responses:
        '200':
          description: Chunk(s) created
        '400':
          description: Deserialization error
        '413':
          description: Too many chunks (exceeds 120)
        '426':
          description: Upgrade required
components:
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: Authorization
      description: 'Trieve API key. User or API key must have admin or owner role on the

        targeted dataset''s organization.

        '