PineconeVectorStore

pydantic model llama_index.vector_stores.PineconeVectorStore

Pinecone Vector Store.

In this vector store, embeddings and docs are stored within a Pinecone index.

During query time, the index uses Pinecone to query for the top k most similar nodes.

Parameters

• pinecone_index (Optional[Union[pinecone.Pinecone.Index, pinecone.Index]]) – Pinecone index instance,

• clients. (pinecone.Pinecone.Index for clients >= 3.0.0; pinecone.Index for older) –

• insert_kwargs (Optional[Dict]) – insert kwargs during upsert call.

• add_sparse_vector (bool) – whether to add sparse vector to index.

• tokenizer (Optional[Callable]) – tokenizer to use to generate sparse

• default_empty_query_vector (Optional[List[float]]) – default empty query vector. Defaults to None. If not None, then this vector will be used as the query vector if the query is empty.

Show JSON schema

{
   "title": "PineconeVectorStore",
   "description": "Pinecone Vector Store.\n\nIn this vector store, embeddings and docs are stored within a\nPinecone index.\n\nDuring query time, the index uses Pinecone to query for the top\nk most similar nodes.\n\nArgs:\n    pinecone_index (Optional[Union[pinecone.Pinecone.Index, pinecone.Index]]): Pinecone index instance,\n    pinecone.Pinecone.Index for clients >= 3.0.0; pinecone.Index for older clients.\n    insert_kwargs (Optional[Dict]): insert kwargs during `upsert` call.\n    add_sparse_vector (bool): whether to add sparse vector to index.\n    tokenizer (Optional[Callable]): tokenizer to use to generate sparse\n    default_empty_query_vector (Optional[List[float]]): default empty query vector.\n        Defaults to None. If not None, then this vector will be used as the query\n        vector if the query is empty.",
   "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": false,
         "type": "boolean"
      },
      "api_key": {
         "title": "Api Key",
         "type": "string"
      },
      "index_name": {
         "title": "Index Name",
         "type": "string"
      },
      "environment": {
         "title": "Environment",
         "type": "string"
      },
      "namespace": {
         "title": "Namespace",
         "type": "string"
      },
      "insert_kwargs": {
         "title": "Insert Kwargs",
         "type": "object"
      },
      "add_sparse_vector": {
         "title": "Add Sparse Vector",
         "type": "boolean"
      },
      "text_key": {
         "title": "Text Key",
         "type": "string"
      },
      "batch_size": {
         "title": "Batch Size",
         "type": "integer"
      },
      "remove_text_from_metadata": {
         "title": "Remove Text From Metadata",
         "type": "boolean"
      },
      "class_name": {
         "title": "Class Name",
         "type": "string",
         "default": "PinconeVectorStore"
      }
   },
   "required": [
      "add_sparse_vector",
      "text_key",
      "batch_size",
      "remove_text_from_metadata"
   ]
}

Config

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

Fields

• add_sparse_vector (bool)

• api_key (Optional[str])

• batch_size (int)

• environment (Optional[str])

• flat_metadata (bool)

• index_name (Optional[str])

• insert_kwargs (Optional[Dict])

• namespace (Optional[str])

• remove_text_from_metadata (bool)

• stores_text (bool)

• text_key (str)

field add_sparse_vector: bool [Required]

field api_key: Optional[str] = None

field batch_size: int [Required]

field environment: Optional[str] = None

field flat_metadata: bool = False

field index_name: Optional[str] = None

field insert_kwargs: Optional[Dict] = None

field namespace: Optional[str] = None

field remove_text_from_metadata: bool [Required]

field stores_text: bool = True

field text_key: str [Required]

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

Add nodes to index.

Parameters

nodes – List[BaseNode]: list of nodes with embeddings

classmethod class_name() → str

Get the class name, used as a unique ID in serialization.

This provides a key that makes serialization robust against actual class name changes.

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.

classmethod from_params(api_key: Optional[str] = None, index_name: Optional[str] = None, environment: Optional[str] = None, namespace: Optional[str] = None, insert_kwargs: Optional[Dict] = None, add_sparse_vector: bool = False, tokenizer: Optional[Callable] = None, text_key: str = 'text', batch_size: int = 100, remove_text_from_metadata: bool = False, default_empty_query_vector: Optional[List[float]] = None, **kwargs: Any) → PineconeVectorStore

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

Query index for top k most similar nodes.

Parameters

• query_embedding (List[float]) – query embedding

• similarity_top_k (int) – top k most similar nodes

property client: Any

Return Pinecone client.