langchain_community.vectorstores.pinecone.Pinecone

class langchain_community.vectorstores.pinecone.Pinecone(index: Any, embedding: Union[Embeddings, Callable], text_key: str, namespace: Optional[str] = None, distance_strategy: Optional[DistanceStrategy] = DistanceStrategy.COSINE)

Pinecone vector store.

To use, you should have the pinecone-client python package installed.

Example

from langchain_community.vectorstores import Pinecone
from langchain_community.embeddings.openai import OpenAIEmbeddings
import pinecone

# The environment should be the one specified next to the API key
# in your Pinecone console
pinecone.init(api_key="***", environment="...")
index = pinecone.Index("langchain-demo")
embeddings = OpenAIEmbeddings()
vectorstore = Pinecone(index, embeddings.embed_query, "text")

Initialize with Pinecone client.

Attributes

embeddings

Access the query embedding object if available.

Methods

__init__(index, embedding, text_key[, ...])	Initialize with Pinecone client.
aadd_documents(documents, **kwargs)	Run more documents through the embeddings and add to the vectorstore.
aadd_texts(texts[, metadatas])	Run more texts through the embeddings and add to the vectorstore.
add_documents(documents, **kwargs)	Run more documents through the embeddings and add to the vectorstore.
add_texts(texts[, metadatas, ids, ...])	Run more texts through the embeddings and add to the vectorstore.
adelete([ids])	Delete by vector ID or other criteria.
afrom_documents(documents, embedding, **kwargs)	Return VectorStore initialized from documents and embeddings.
afrom_texts(texts, embedding[, metadatas])	Return VectorStore initialized from texts and embeddings.
amax_marginal_relevance_search(query[, k, ...])	Return docs selected using the maximal marginal relevance.
amax_marginal_relevance_search_by_vector(...)	Return docs selected using the maximal marginal relevance.
as_retriever(**kwargs)	Return VectorStoreRetriever initialized from this VectorStore.
asearch(query, search_type, **kwargs)	Return docs most similar to query using specified search type.
asimilarity_search(query[, k])	Return docs most similar to query.
asimilarity_search_by_vector(embedding[, k])	Return docs most similar to embedding vector.
asimilarity_search_with_relevance_scores(query)	Return docs and relevance scores in the range [0, 1], asynchronously.
asimilarity_search_with_score(*args, **kwargs)	Run similarity search with distance asynchronously.
delete([ids, delete_all, namespace, filter])	Delete by vector IDs or filter.
from_documents(documents, embedding, **kwargs)	Return VectorStore initialized from documents and embeddings.
from_existing_index(index_name, embedding[, ...])	Load pinecone vectorstore from index name.
from_texts(texts, embedding[, metadatas, ...])	Construct Pinecone wrapper from raw documents.
get_pinecone_index(index_name[, pool_threads])	Return a Pinecone Index instance.
max_marginal_relevance_search(query[, k, ...])	Return docs selected using the maximal marginal relevance.
max_marginal_relevance_search_by_vector(...)	Return docs selected using the maximal marginal relevance.
search(query, search_type, **kwargs)	Return docs most similar to query using specified search type.
similarity_search(query[, k, filter, namespace])	Return pinecone documents most similar to query.
similarity_search_by_vector(embedding[, k])	Return docs most similar to embedding vector.
similarity_search_by_vector_with_score(...)	Return pinecone documents most similar to embedding, along with scores.
similarity_search_with_relevance_scores(query)	Return docs and relevance scores in the range [0, 1].
similarity_search_with_score(query[, k, ...])	Return pinecone documents most similar to query, along with scores.

__init__(index: Any, embedding: Union[Embeddings, Callable], text_key: str, namespace: Optional[str] = None, distance_strategy: Optional[DistanceStrategy] = DistanceStrategy.COSINE)

Initialize with Pinecone client.

async aadd_documents(documents: List[Document], **kwargs: Any) → List[str]

Run more documents through the embeddings and add to the vectorstore.

Parameters

(List[Document] (documents) – Documents to add to the vectorstore.

Returns

List of IDs of the added texts.

Return type

List[str]

async aadd_texts(texts: Iterable[str], metadatas: Optional[List[dict]] = None, **kwargs: Any) → List[str]

Run more texts through the embeddings and add to the vectorstore.

add_documents(documents: List[Document], **kwargs: Any) → List[str]

Run more documents through the embeddings and add to the vectorstore.

Parameters

(List[Document] (documents) – Documents to add to the vectorstore.

Returns

List of IDs of the added texts.

Return type

List[str]

add_texts(texts: Iterable[str], metadatas: Optional[List[dict]] = None, ids: Optional[List[str]] = None, namespace: Optional[str] = None, batch_size: int = 32, embedding_chunk_size: int = 1000, **kwargs: Any) → List[str]

Run more texts through the embeddings and add to the vectorstore.

Upsert optimization is done by chunking the embeddings and upserting them. This is done to avoid memory issues and optimize using HTTP based embeddings. For OpenAI embeddings, use pool_threads>4 when constructing the pinecone.Index, embedding_chunk_size>1000 and batch_size~64 for best performance. :param texts: Iterable of strings to add to the vectorstore. :param metadatas: Optional list of metadatas associated with the texts. :param ids: Optional list of ids to associate with the texts. :param namespace: Optional pinecone namespace to add the texts to. :param batch_size: Batch size to use when adding the texts to the vectorstore. :param embedding_chunk_size: Chunk size to use when embedding the texts.

Returns

List of ids from adding the texts into the vectorstore.

async adelete(ids: Optional[List[str]] = None, **kwargs: Any) → Optional[bool]

Delete by vector ID or other criteria.

Parameters

• ids – List of ids to delete.

• **kwargs – Other keyword arguments that subclasses might use.

Returns

True if deletion is successful, False otherwise, None if not implemented.

Return type

Optional[bool]

async classmethod afrom_documents(documents: List[Document], embedding: Embeddings, **kwargs: Any) → VST

Return VectorStore initialized from documents and embeddings.

async classmethod afrom_texts(texts: List[str], embedding: Embeddings, metadatas: Optional[List[dict]] = None, **kwargs: Any) → VST

Return VectorStore initialized from texts and embeddings.

async amax_marginal_relevance_search(query: str, k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, **kwargs: Any) → List[Document]

Return docs selected using the maximal marginal relevance.

async amax_marginal_relevance_search_by_vector(embedding: List[float], k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, **kwargs: Any) → List[Document]

Return docs selected using the maximal marginal relevance.

as_retriever(**kwargs: Any) → VectorStoreRetriever

Return VectorStoreRetriever initialized from this VectorStore.

Parameters

• search_type (Optional[str]) – Defines the type of search that the Retriever should perform. Can be “similarity” (default), “mmr”, or “similarity_score_threshold”.

• search_kwargs (Optional[Dict]) –

  Keyword arguments to pass to the search function. Can include things like:

  k: Amount of documents to return (Default: 4) score_threshold: Minimum relevance threshold

  for similarity_score_threshold

  fetch_k: Amount of documents to pass to MMR algorithm (Default: 20) lambda_mult: Diversity of results returned by MMR;

  1 for minimum diversity and 0 for maximum. (Default: 0.5)

  filter: Filter by document metadata

Returns

Retriever class for VectorStore.

Return type

VectorStoreRetriever

Examples:

# Retrieve more documents with higher diversity
# Useful if your dataset has many similar documents
docsearch.as_retriever(
    search_type="mmr",
    search_kwargs={'k': 6, 'lambda_mult': 0.25}
)

# Fetch more documents for the MMR algorithm to consider
# But only return the top 5
docsearch.as_retriever(
    search_type="mmr",
    search_kwargs={'k': 5, 'fetch_k': 50}
)

# Only retrieve documents that have a relevance score
# Above a certain threshold
docsearch.as_retriever(
    search_type="similarity_score_threshold",
    search_kwargs={'score_threshold': 0.8}
)

# Only get the single most similar document from the dataset
docsearch.as_retriever(search_kwargs={'k': 1})

# Use a filter to only retrieve documents from a specific paper
docsearch.as_retriever(
    search_kwargs={'filter': {'paper_title':'GPT-4 Technical Report'}}
)

async asearch(query: str, search_type: str, **kwargs: Any) → List[Document]

Return docs most similar to query using specified search type.

async asimilarity_search(query: str, k: int = 4, **kwargs: Any) → List[Document]

Return docs most similar to query.

async asimilarity_search_by_vector(embedding: List[float], k: int = 4, **kwargs: Any) → List[Document]

Return docs most similar to embedding vector.

async asimilarity_search_with_relevance_scores(query: str, k: int = 4, **kwargs: Any) → List[Tuple[Document, float]]

Return docs and relevance scores in the range [0, 1], asynchronously.

0 is dissimilar, 1 is most similar.

Parameters

• query – input text

• k – Number of Documents to return. Defaults to 4.

• **kwargs –

  kwargs to be passed to similarity search. Should include: score_threshold: Optional, a floating point value between 0 to 1 to

  filter the resulting set of retrieved docs

Returns

List of Tuples of (doc, similarity_score)

async asimilarity_search_with_score(*args: Any, **kwargs: Any) → List[Tuple[Document, float]]

Run similarity search with distance asynchronously.

delete(ids: Optional[List[str]] = None, delete_all: Optional[bool] = None, namespace: Optional[str] = None, filter: Optional[dict] = None, **kwargs: Any) → None

Delete by vector IDs or filter. :param ids: List of ids to delete. :param filter: Dictionary of conditions to filter vectors to delete.

classmethod from_documents(documents: List[Document], embedding: Embeddings, **kwargs: Any) → VST

Return VectorStore initialized from documents and embeddings.

classmethod from_existing_index(index_name: str, embedding: Embeddings, text_key: str = 'text', namespace: Optional[str] = None, pool_threads: int = 4) → Pinecone

Load pinecone vectorstore from index name.

classmethod from_texts(texts: List[str], embedding: Embeddings, metadatas: Optional[List[dict]] = None, ids: Optional[List[str]] = None, batch_size: int = 32, text_key: str = 'text', namespace: Optional[str] = None, index_name: Optional[str] = None, upsert_kwargs: Optional[dict] = None, pool_threads: int = 4, embeddings_chunk_size: int = 1000, **kwargs: Any) → Pinecone

Construct Pinecone wrapper from raw documents.

This is a user friendly interface that:

1. Embeds documents.

2. Adds the documents to a provided Pinecone index

This is intended to be a quick way to get started.

The pool_threads affects the speed of the upsert operations. .. rubric:: Example

from langchain_community.vectorstores import Pinecone
from langchain_community.embeddings import OpenAIEmbeddings
import pinecone

# The environment should be the one specified next to the API key
# in your Pinecone console
pinecone.init(api_key="***", environment="...")
embeddings = OpenAIEmbeddings()
pinecone = Pinecone.from_texts(
    texts,
    embeddings,
    index_name="langchain-demo"
)

classmethod get_pinecone_index(index_name: Optional[str], pool_threads: int = 4) → Index

Return a Pinecone Index instance.

Parameters

• index_name – Name of the index to use.

• pool_threads – Number of threads to use for index upsert.

Returns

Pinecone Index instance.

max_marginal_relevance_search(query: str, k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, filter: Optional[dict] = None, namespace: Optional[str] = None, **kwargs: Any) → List[Document]

Return docs selected using the maximal marginal relevance.

Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.

Parameters

• query – Text to look up documents similar to.

• k – Number of Documents to return. Defaults to 4.

• fetch_k – Number of Documents to fetch to pass to MMR algorithm.

• lambda_mult – Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5.

Returns

List of Documents selected by maximal marginal relevance.

max_marginal_relevance_search_by_vector(embedding: List[float], k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, filter: Optional[dict] = None, namespace: Optional[str] = None, **kwargs: Any) → List[Document]

Return docs selected using the maximal marginal relevance.

Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.

Parameters

• embedding – Embedding to look up documents similar to.

• k – Number of Documents to return. Defaults to 4.

• fetch_k – Number of Documents to fetch to pass to MMR algorithm.

• lambda_mult – Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5.

Returns

List of Documents selected by maximal marginal relevance.

search(query: str, search_type: str, **kwargs: Any) → List[Document]

Return docs most similar to query using specified search type.

similarity_search(query: str, k: int = 4, filter: Optional[dict] = None, namespace: Optional[str] = None, **kwargs: Any) → List[Document]

Return pinecone documents most similar to query.

Parameters

• query – Text to look up documents similar to.

• k – Number of Documents to return. Defaults to 4.

• filter – Dictionary of argument(s) to filter on metadata

• namespace – Namespace to search in. Default will search in ‘’ namespace.

Returns

List of Documents most similar to the query and score for each

similarity_search_by_vector(embedding: List[float], k: int = 4, **kwargs: Any) → List[Document]

Return docs most similar to embedding vector.

Parameters

• embedding – Embedding to look up documents similar to.

• k – Number of Documents to return. Defaults to 4.

Returns

List of Documents most similar to the query vector.

similarity_search_by_vector_with_score(embedding: List[float], *, k: int = 4, filter: Optional[dict] = None, namespace: Optional[str] = None) → List[Tuple[Document, float]]

Return pinecone documents most similar to embedding, along with scores.

similarity_search_with_relevance_scores(query: str, k: int = 4, **kwargs: Any) → List[Tuple[Document, float]]

Return docs and relevance scores in the range [0, 1].

0 is dissimilar, 1 is most similar.

Parameters

• query – input text

• k – Number of Documents to return. Defaults to 4.

• **kwargs –

  kwargs to be passed to similarity search. Should include: score_threshold: Optional, a floating point value between 0 to 1 to

  filter the resulting set of retrieved docs

Returns

List of Tuples of (doc, similarity_score)

similarity_search_with_score(query: str, k: int = 4, filter: Optional[dict] = None, namespace: Optional[str] = None) → List[Tuple[Document, float]]

Return pinecone documents most similar to query, along with scores.

Parameters

• query – Text to look up documents similar to.

• k – Number of Documents to return. Defaults to 4.

• filter – Dictionary of argument(s) to filter on metadata

• namespace – Namespace to search in. Default will search in ‘’ namespace.

Returns

List of Documents most similar to the query and score for each

Examples using Pinecone

• Pinecone