AI API - Indexes, embedding model and AI search readiness (vdb_info)

AI API: Vectors, Images & LLM

Tells you which indexes you have, which embedding model and language model the API servers run and, for one index, whether it is ready for AI search with vectors.

Endpointhttps://api.opensolr.com/solr_manager/api/vdb_info
MethodGET or POST
Authemail and api_key of your account, as GET or POST parameters: Authentication.

01 · Parameters

index_nameOptional

Also check this index.

02 · Example

curl -s "https://api.opensolr.com/solr_manager/api/vdb_info?email=YOUR_EMAIL&api_key=YOUR_API_KEY&index_name=my_index"

03 · Answer

{
    "status": true,
    "indexes": [
        "my_index",
        "my_other_index"
    ],
    "embedder": {
        "model": "...",
        "dimension": 1024,
        "max_tokens": 512
    },
    "llm": {
        "id": "...",
        "max_model_len": 32768,
        "max_output_tokens": 8192
    },
    "index": {
        "name": "my_index",
        "dimension": 1024,
        "ready": true,
        "entity_docs": 1520
    }
}
indexes

Your indexes. A scoped key gets only the ones it was given.

embedder

The model that makes the meaning vectors: name, vector size, longest text it reads.

llm

The language model of chat_completions and its window.

index.ready

true when the index answers a vector search. When not, msg says why.

index.entity_docs

Documents of the index that stand for Drupal entities.

Values shown are an example.

04 · Errors

ERROR_EMBEDDING_SERVICE_UNAVAILABLEHTTP 200

The embedding model did not answer. Retry.

VECTOR_NOT_ALLOWEDHTTP 200

AI is switched off on the plan of the index owner.

ERROR_NOT_CORE_OWNERHTTP 200

The index is not yours.

WRONG_API_HOSTHTTP 404

Called on opensolr.com.

ERROR_AUTHENTICATION_FAILEDHTTP 403

The email and API key do not match.

05 · Related

Search the index: vdb_search. What an index needs: What your index needs.

Every error code and HTTP status of the API: API errors. Calls per minute and per hour: Rate limits.