For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
BlogLog InRequest Demo
HomeProductDevelopersSelf-HostingChangelog
HomeProductDevelopersSelf-HostingChangelog
  • Getting Started
    • Overview
  • Workflows SDK
    • Introduction
    • Installation
    • Core Concepts
    • Defining Control Flow
    • Configuration
    • Custom Docker Images
  • Client SDK
    • Introduction
    • Authentication
    • API Versioning
      • POSTSearch
      • POSTAdd Document
      • POSTCreate Document Index
      • GETRetrieve Document Index
      • GETList Document Indexes
      • PATCHUpdate Document Index
      • PUTReplace Document Index
      • DELDestroy
      • DELRemove Document
LogoLogo
BlogLog InRequest Demo
Client SDKDocument Indexes

Create Document Index

Beta
POST
https://api.vellum.ai/v1/document-indexes
POST
/v1/document-indexes
1import requests
2
3url = "https://api.vellum.ai/v1/document-indexes"
4
5payload = {
6    "label": "My Document Index",
7    "name": "my-document-index",
8    "indexing_config": {
9        "vectorizer": {
10            "model_name": "sentence-transformers/multi-qa-mpnet-base-dot-v1",
11            "config": {}
12        },
13        "chunking": {
14            "chunker_name": "sentence-chunker",
15            "chunker_config": {
16                "character_limit": 1000,
17                "min_overlap_ratio": 0.5
18            }
19        }
20    }
21}
22headers = {
23    "X-API-KEY": "<apiKey>",
24    "Content-Type": "application/json"
25}
26
27response = requests.post(url, json=payload, headers=headers)
28
29print(response.json())
201Index Using a Sentence Transformers Model
1{
2  "id": "string",
3  "created": "2024-01-15T09:30:00Z",
4  "label": "string",
5  "name": "string",
6  "indexing_config": {
7    "vectorizer": {
8      "config": {
9        "add_openai_api_key": true
10      },
11      "model_name": "text-embedding-3-small"
12    },
13    "chunking": {
14      "chunker_name": "reducto-chunker",
15      "chunker_config": {
16        "character_limit": 1000
17      }
18    }
19  },
20  "status": "ACTIVE"
21}
Creates a new document index.
Was this page helpful?
Previous

Retrieve Document Index

Next
Built with

Authentication

X-API-KEYstring
API Key authentication via header

Headers

X-API-VersionstringOptional

Request

This endpoint expects an object.
labelstringRequired1-150 characters

A human-readable label for the document index

namestringRequired1-150 characters
A name that uniquely identifies this index within its workspace
indexing_configobjectRequired
statusenumOptional

The current status of the document index

  • ACTIVE - Active
  • ARCHIVED - Archived
  • PENDING_DELETION - Pending Deletion
Allowed values:
copy_documents_from_index_idstringOptionalformat: "uuid"

Optionally specify the id of a document index from which you’d like to copy and re-index its documents into this newly created index

Response

idstringformat: "uuid"
createdstringformat: "date-time"
labelstring<=150 characters

A human-readable label for the document index

namestring<=150 characters
A name that uniquely identifies this index within its workspace
indexing_configobject
statusenum

The current status of the document index

  • ACTIVE - Active
  • ARCHIVED - Archived
  • PENDING_DELETION - Pending Deletion
Allowed values: