Index
Index.
{
"id": "string",
"name": "string",
"description": "string",
"embeddings_model_endpoint": "string",
"text_splitting": "string",
"chunk_size": 0,
"chunk_overlap": 0,
"hybrid_search": false,
"text_search_config": "simple",
"knowledge_base_id": "string",
"object": "string",
"created_at": 0,
"last_indexed_at": 0,
"last_indexed_by_id": "string",
"num_documents": 0,
"status": "string",
"status_errors": [
"string"
]
}
ID of the index.
Name of the index.
Description of the index.
ID of the model to be used by the index for generating embeddings.
Maximum size (in tokens) of the text chunks. This must be at least 100 to accommodate for content metadata embedded alongside each chunk of text.
Size of the chunk overlap (in tokens) when splitting text.
Enable or disable hybrid search. If enabled, text_search_config must be provided.
The text search configuration to use for hybrid search. The available values depend on the version of the database server used by this Private AI Services instances. Please refer to the PostgreSQL server documentation for available values. For example: 'simple', 'english', 'french'.
ID of the knowledge base of the index.
Object type, which is always index.
Unix timestamp (in seconds) when the index was created.
Unix timestamp (in seconds) when the index contents were last indexed.
ID of the most recent indexing job that affected this index.
Total number of documents in the index.
Availability status of the index.
Details of the index error status, if the index is not available.