DeepLakeVectorStore

pydantic model llama_index.vector_stores.DeepLakeVectorStore

The DeepLake Vector Store.

In this vector store we store the text, its embedding and a few pieces of its metadata in a deeplake dataset. This implementation allows the use of an already existing deeplake dataset if it is one that was created this vector store. It also supports creating a new one if the dataset doesn’t exist or if overwrite is set to True.

Show JSON schema

{
   "title": "DeepLakeVectorStore",
   "description": "The DeepLake Vector Store.\n\nIn this vector store we store the text, its embedding and\na few pieces of its metadata in a deeplake dataset. This implementation\nallows the use of an already existing deeplake dataset if it is one that was created\nthis vector store. It also supports creating a new one if the dataset doesn't\nexist or if `overwrite` is set to True.",
   "type": "object",
   "properties": {
      "stores_text": {
         "title": "Stores Text",
         "default": true,
         "type": "boolean"
      },
      "is_embedding_query": {
         "title": "Is Embedding Query",
         "default": true,
         "type": "boolean"
      },
      "flat_metadata": {
         "title": "Flat Metadata",
         "default": true,
         "type": "boolean"
      },
      "ingestion_batch_size": {
         "title": "Ingestion Batch Size",
         "type": "integer"
      },
      "num_workers": {
         "title": "Num Workers",
         "type": "integer"
      },
      "token": {
         "title": "Token",
         "type": "string"
      },
      "read_only": {
         "title": "Read Only",
         "type": "boolean"
      },
      "dataset_path": {
         "title": "Dataset Path",
         "type": "string"
      },
      "class_name": {
         "title": "Class Name",
         "type": "string",
         "default": "base_component"
      }
   },
   "required": [
      "ingestion_batch_size",
      "num_workers",
      "dataset_path"
   ]
}

Config

• schema_extra: function = <function BaseComponent.Config.schema_extra at 0x7ff1e41e53a0>

Fields

• dataset_path (str)

• flat_metadata (bool)

• ingestion_batch_size (int)

• num_workers (int)

• read_only (Optional[bool])

• stores_text (bool)

• token (Optional[str])

field dataset_path: str [Required]

field flat_metadata: bool = True

field ingestion_batch_size: int [Required]

field num_workers: int [Required]

field read_only: Optional[bool] = None

field stores_text: bool = True

field token: Optional[str] = None

add(nodes: List[BaseNode], **add_kwargs: Any) → List[str]

Add the embeddings and their nodes into DeepLake.

Parameters

nodes (List[BaseNode]) – List of nodes with embeddings to insert.

Returns

List of ids inserted.

Return type

List[str]

delete(ref_doc_id: str, **delete_kwargs: Any) → None

Delete nodes using with ref_doc_id.

Parameters

ref_doc_id (str) – The doc_id of the document to delete.

query(query: VectorStoreQuery, **kwargs: Any) → VectorStoreQueryResult

Query index for top k most similar nodes.

Parameters

• query (VectorStoreQuery) – VectorStoreQuery class input, it has the following attributes: 1. query_embedding (List[float]): query embedding 2. similarity_top_k (int): top k most similar nodes

• deep_memory (bool) – Whether to use deep memory for query execution.

Returns

VectorStoreQueryResult

property client: Any

Get client.

Returns

DeepLake vectorstore dataset.

Return type

Any