Collections

Create a document collection that OpenIndex.ai will index and calculate embeddings for.

Retrieve user collections.

GEThttps://www.openindex.ai/api/collections

Response

200

A list of collections.

Body

application/json

okboolean

collectionsarray of Collection (object)

Request

JavaScriptCurl

const response = await fetch('https://www.openindex.ai/api/collections', {
    method: 'GET',
    headers: {},
});
const data = await response.json();

Response

{
  "ok": false,
  "collections": [
    {
      "id": "text",
      "slug": "text",
      "userId": "text",
      "active": false,
      "name": "text",
      "description": "text",
      "image": "text",
      "privacy": "public",
      "namespace": "text",
      "sources": [],
      "status": "text"
    }
  ]
}

Create or update a collection.

POSThttps://www.openindex.ai/api/collections

Body

application/json

idstring

namestring

descriptionstring

imagestring

privacyPrivacy (enum)

publicprivateteam

knowledgeBasestring

A list of URLs (one per row) to add to the collection. YouTube URLs will be transcripted. Use links(url) to index the direct links at url.

Response

200400403

The result of the collection creation or update.

Body

application/json

okboolean

collectionIdstring

Request

JavaScriptCurl

const response = await fetch('https://www.openindex.ai/api/collections', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({}),
});
const data = await response.json();

Response

{
  "ok": false,
  "collectionId": "text"
}

List publicly-accessible URLs, one per line, in the knowledgeBase parameter. Any YouTube URL will be transcribed and index.

Use links(<url>) to index all direct links in url.

Search collections

GEThttps://www.openindex.ai/api/collections/search

Query parameters

Response

200

A list of collections.

Body

application/json

okboolean

resultsarray of SearchResult (object)

Request

JavaScriptCurl

const response = await fetch('https://www.openindex.ai/api/collections/search', {
    method: 'GET',
    headers: {},
});
const data = await response.json();

Response

{
  "ok": false,
  "results": [
    {
      "snippet": "text",
      "url": "text",
      "sourceId": "text",
      "source": "web",
      "collection": {
        "id": "text",
        "slug": "text",
        "userId": "text",
        "active": false,
        "name": "text",
        "description": "text",
        "image": "text",
        "privacy": "public",
        "namespace": "text",
        "sources": [],
        "status": "text"
      },
      "score": 0
    }
  ]
}

The /collections/search endpoint will run a hybrid similarity search of your query passed as parameter q and return the chunks and collections with the highest semantic similarity after a re-ranking step.

This endpoint can be used as an action in your custom OpenAI GPTs. Search the full OpenIndex.ai knowledge base by adding a new function to your custom GPT with this OpenAPI json schema.

If you want to only search a specific collection in your custom GPT, use the json schema URL https://www.openindex.ai/actions/gpt?collection_id=<collection_id>. We now show that URL in the main collection page, see for example the collection Vitalik's Essays.

For now only public OpenIndex.ai collections can be retrieved. We are looking to implement OAuth login with OpenAI GPT to also allow for private and team collections search.