`langchain_community.vectorstores.upstash`.UpstashVectorStore¶

class langchain_community.vectorstores.upstash.UpstashVectorStore(text_key: str = 'text', index: Optional[Index] = None, async_index: Optional[AsyncIndex] = None, index_url: Optional[str] = None, index_token: Optional[str] = None, embedding: Optional[Union[Embeddings, bool]] = None)[source]¶

Upstash Vector vector store

To use, the upstash-vector python package must be installed.

Also an Upstash Vector index is required. First create a new Upstash Vector index and copy the index_url and index_token variables. Then either pass them through the constructor or set the environment variables UPSTASH_VECTOR_REST_URL and UPSTASH_VECTOR_REST_TOKEN.

Example

from langchain_openai import OpenAIEmbeddings
from langchain_community.vectorstores import UpstashVectorStore

embeddings = OpenAIEmbeddings(model="text-embedding-3-large")
vectorstore = UpstashVectorStore(
    embedding=embeddings,
    index_url="...",
    index_token="..."
)

# or

import os

os.environ["UPSTASH_VECTOR_REST_URL"] = "..."
os.environ["UPSTASH_VECTOR_REST_TOKEN"] = "..."

vectorstore = UpstashVectorStore(
    embedding=embeddings
)

Constructor for UpstashVectorStore.

If index or index_url and index_token are not provided, the constructor will attempt to create an index using the environment variables UPSTASH_VECTOR_REST_URL`and `UPSTASH_VECTOR_REST_TOKEN.

Parameters

text_key (str) – Key to store the text in metadata.
index (Optional[Index]) – UpstashVector Index object.
async_index (Optional[AsyncIndex]) – UpstashVector AsyncIndex object, provide only if async
needed (functions are) –
index_url (Optional[str]) – URL of the UpstashVector index.
index_token (Optional[str]) – Token of the UpstashVector index.
embedding (Optional[Union[Embeddings, bool]]) – Embeddings object or a boolean. When false, no embedding is applied. If true, Upstash embeddings are used. When Upstash embeddings are used, text is sent directly to Upstash and embedding is applied there instead of embedding in Langchain.

Example

from langchain_community.vectorstores.upstash import UpstashVectorStore
from langchain_community.embeddings.openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings()
vectorstore = UpstashVectorStore(
    embedding=embeddings,
    index_url="...",
    index_token="..."
)

# With an existing index
from upstash_vector import Index

index = Index(url="...", token="...")
vectorstore = UpstashVectorStore(
    embedding=embeddings,
    index=index
)

Attributes

embeddings

Access the query embedding object if available.

Methods

`__init__`([text_key, index, async_index, ...])	Constructor for UpstashVectorStore.
`aadd_documents`(documents[, ids, batch_size, ...])	Get the embeddings for the documents and add them to the vectorstore.
`aadd_texts`(texts[, metadatas, ids, ...])	Get the embeddings for the texts and add them to the vectorstore.
`add_documents`(documents[, ids, batch_size, ...])	Get the embeddings for the documents and add them to the vectorstore.
`add_texts`(texts[, metadatas, ids, ...])	Get the embeddings for the texts and add them to the vectorstore.
`adelete`([ids, delete_all, batch_size])	Delete by vector IDs
`afrom_documents`(documents, embedding, **kwargs)	Return VectorStore initialized from documents and embeddings.
`afrom_texts`(texts, embedding[, metadatas, ...])	Create a new UpstashVectorStore from a list of texts.
`ainfo`()	Get statistics about the index.
`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, filter])	Return documents most similar to query.
`asimilarity_search_by_vector`(embedding[, k, ...])	Return documents closest to the given embedding.
`asimilarity_search_by_vector_with_score`(...)	Return texts whose embedding is closest to the given embedding
`asimilarity_search_with_relevance_scores`(query)	Return docs and relevance scores in the range [0, 1], asynchronously.
`asimilarity_search_with_score`(query[, k, filter])	Retrieve texts most similar to query and convert the result to Document objects.
`delete`([ids, delete_all, batch_size])	Delete by vector IDs
`from_documents`(documents, embedding, **kwargs)	Return VectorStore initialized from documents and embeddings.
`from_texts`(texts, embedding[, metadatas, ...])	Create a new UpstashVectorStore from a list of texts.
`info`()	Get statistics about the index.
`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])	Return documents most similar to query.
`similarity_search_by_vector`(embedding[, k, ...])	Return documents closest to the given embedding.
`similarity_search_by_vector_with_score`(embedding)	Return texts whose embedding is closest to the given embedding
`similarity_search_with_relevance_scores`(query)	Return docs and relevance scores in the range [0, 1].
`similarity_search_with_score`(query[, k, filter])	Retrieve texts most similar to query and convert the result to Document objects.

__init__(text_key: str = 'text', index: Optional[Index] = None, async_index: Optional[AsyncIndex] = None, index_url: Optional[str] = None, index_token: Optional[str] = None, embedding: Optional[Union[Embeddings, bool]] = None)[source]¶

Constructor for UpstashVectorStore.

If index or index_url and index_token are not provided, the constructor will attempt to create an index using the environment variables UPSTASH_VECTOR_REST_URL`and `UPSTASH_VECTOR_REST_TOKEN.

Parameters

text_key (str) – Key to store the text in metadata.
index (Optional[Index]) – UpstashVector Index object.
async_index (Optional[AsyncIndex]) – UpstashVector AsyncIndex object, provide only if async
needed (functions are) –
index_url (Optional[str]) – URL of the UpstashVector index.
index_token (Optional[str]) – Token of the UpstashVector index.
embedding (Optional[Union[Embeddings, bool]]) – Embeddings object or a boolean. When false, no embedding is applied. If true, Upstash embeddings are used. When Upstash embeddings are used, text is sent directly to Upstash and embedding is applied there instead of embedding in Langchain.

Example

from langchain_community.vectorstores.upstash import UpstashVectorStore
from langchain_community.embeddings.openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings()
vectorstore = UpstashVectorStore(
    embedding=embeddings,
    index_url="...",
    index_token="..."
)

# With an existing index
from upstash_vector import Index

index = Index(url="...", token="...")
vectorstore = UpstashVectorStore(
    embedding=embeddings,
    index=index
)

async aadd_documents(documents: Iterable[Document], ids: Optional[List[str]] = None, batch_size: int = 32, embedding_chunk_size: int = 1000, **kwargs: Any) → List[str][source]¶

Get the embeddings for the documents and add them to the vectorstore.

Documents are sent to the embeddings object in batches of size embedding_chunk_size. The embeddings are then upserted into the vectorstore in batches of size batch_size.

Parameters

documents (Iterable[Document]) – Iterable of Documents to add to the vectorstore.
batch_size (int) – Batch size to use when upserting the embeddings.
request. (Upstash supports at max 1000 vectors per) –
embedding_batch_size – Chunk size to use when embedding the texts.
ids (Optional[List[str]]) –
embedding_chunk_size (int) –
kwargs (Any) –

Returns

List of ids from adding the texts into the vectorstore.

Return type

List[str]

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

Get the embeddings for the texts and add them to the vectorstore.

Texts are sent to the embeddings object in batches of size embedding_chunk_size. The embeddings are then upserted into the vectorstore in batches of size batch_size.

Parameters

texts (Iterable[str]) – Iterable of strings to add to the vectorstore.
metadatas (Optional[List[dict]]) – Optional list of metadatas associated with the texts.
ids (Optional[List[str]]) – Optional list of ids to associate with the texts.
batch_size (int) – Batch size to use when upserting the embeddings.
request. (Upstash supports at max 1000 vectors per) –
embedding_batch_size – Chunk size to use when embedding the texts.
embedding_chunk_size (int) –
kwargs (Any) –

Returns

List of ids from adding the texts into the vectorstore.

Return type

List[str]

add_documents(documents: List[Document], ids: Optional[List[str]] = None, batch_size: int = 32, embedding_chunk_size: int = 1000, **kwargs: Any) → List[str][source]¶

Get the embeddings for the documents and add them to the vectorstore.

Documents are sent to the embeddings object in batches of size embedding_chunk_size. The embeddings are then upserted into the vectorstore in batches of size batch_size.

Parameters

documents (List[Document]) – Iterable of Documents to add to the vectorstore.
batch_size (int) – Batch size to use when upserting the embeddings.
request. (Upstash supports at max 1000 vectors per) –
embedding_batch_size – Chunk size to use when embedding the texts.
ids (Optional[List[str]]) –
embedding_chunk_size (int) –
kwargs (Any) –

Returns

List of ids from adding the texts into the vectorstore.

Return type

List[str]

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

Get the embeddings for the texts and add them to the vectorstore.

Texts are sent to the embeddings object in batches of size embedding_chunk_size. The embeddings are then upserted into the vectorstore in batches of size batch_size.

Parameters

texts (Iterable[str]) – Iterable of strings to add to the vectorstore.
metadatas (Optional[List[dict]]) – Optional list of metadatas associated with the texts.
ids (Optional[List[str]]) – Optional list of ids to associate with the texts.
batch_size (int) – Batch size to use when upserting the embeddings.
request. (Upstash supports at max 1000 vectors per) –
embedding_batch_size – Chunk size to use when embedding the texts.
embedding_chunk_size (int) –
kwargs (Any) –

Returns

List of ids from adding the texts into the vectorstore.

Return type

List[str]

async adelete(ids: Optional[List[str]] = None, delete_all: Optional[bool] = None, batch_size: Optional[int] = 1000, **kwargs: Any) → None[source]¶

Delete by vector IDs

Parameters

ids (Optional[List[str]]) – List of ids to delete.
delete_all (Optional[bool]) – Delete all vectors in the index.
batch_size (Optional[int]) – Batch size to use when deleting the embeddings.
request. (Upstash supports at max 1000 deletions per) –
kwargs (Any) –

Return type

None

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

Return VectorStore initialized from documents and embeddings.

Parameters

documents (List[Document]) –
embedding (Embeddings) –
kwargs (Any) –

Return type

VST

async classmethod afrom_texts(texts: List[str], embedding: Embeddings, metadatas: Optional[List[dict]] = None, ids: Optional[List[str]] = None, embedding_chunk_size: int = 1000, batch_size: int = 32, text_key: str = 'text', index: Optional[Index] = None, async_index: Optional[AsyncIndex] = None, index_url: Optional[str] = None, index_token: Optional[str] = None, **kwargs: Any) → UpstashVectorStore[source]¶

Create a new UpstashVectorStore from a list of texts.

Example

Parameters

texts (List[str]) –
embedding (Embeddings) –
metadatas (Optional[List[dict]]) –
ids (Optional[List[str]]) –
embedding_chunk_size (int) –
batch_size (int) –
text_key (str) –
index (Optional[Index]) –
async_index (Optional[AsyncIndex]) –
index_url (Optional[str]) –
index_token (Optional[str]) –
kwargs (Any) –

Return type

UpstashVectorStore

async ainfo() → InfoResult[source]¶

Get statistics about the index.

Returns

total number of vectors
total number of vectors waiting to be indexed
total size of the index on disk in bytes
dimension count for the index
similarity function selected for the index

Return type

InfoResult

async amax_marginal_relevance_search(query: str, k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, filter: Optional[str] = None, **kwargs: Any) → List[Document][source]¶

Return docs selected using the maximal marginal relevance.

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

Parameters

query (str) – Text to look up documents similar to.
k (int) – Number of Documents to return. Defaults to 4.
fetch_k (int) – Number of Documents to fetch to pass to MMR algorithm.
lambda_mult (float) – 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.
filter (Optional[str]) – Optional metadata filter in str format
kwargs (Any) –

Returns

List of Documents selected by maximal marginal relevance.

Return type

List[Document]

async amax_marginal_relevance_search_by_vector(embedding: Union[List[float], str], k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, filter: Optional[str] = None, **kwargs: Any) → List[Document][source]¶

Return docs selected using the maximal marginal relevance.

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

Parameters

embedding (Union[List[float], str]) – Embedding to look up documents similar to.
k (int) – Number of Documents to return. Defaults to 4.
fetch_k (int) – Number of Documents to fetch to pass to MMR algorithm.
lambda_mult (float) – 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.
filter (Optional[str]) – Optional metadata filter in str format
kwargs (Any) –

Returns

List of Documents selected by maximal marginal relevance.

Return type

List[Document]

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
kwargs (Any) –

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.

Parameters

query (str) –
search_type (str) –
kwargs (Any) –

Return type

List[Document]

async asimilarity_search(query: str, k: int = 4, filter: Optional[str] = None, **kwargs: Any) → List[Document][source]¶

Return documents most similar to query.

Parameters

query (str) – Text to look up documents similar to.
k (int) – Number of Documents to return. Defaults to 4.
filter (Optional[str]) – Optional metadata filter in str format
kwargs (Any) –

Returns

List of Documents most similar to the query

Return type

List[Document]

async asimilarity_search_by_vector(embedding: Union[List[float], str], k: int = 4, filter: Optional[str] = None, **kwargs: Any) → List[Document][source]¶

Return documents closest to the given embedding.

Parameters

embedding (Union[List[float], str]) – Embedding to look up documents similar to.
k (int) – Number of Documents to return. Defaults to 4.
filter (Optional[str]) – Optional metadata filter in str format
kwargs (Any) –

Returns

List of Documents most similar to the query

Return type

List[Document]

async asimilarity_search_by_vector_with_score(embedding: Union[List[float], str], k: int = 4, filter: Optional[str] = None, **kwargs: Any) → List[Tuple[Document, float]][source]¶

Return texts whose embedding is closest to the given embedding

Parameters

embedding (Union[List[float], str]) –
k (int) –
filter (Optional[str]) –
kwargs (Any) –

Return type

List[Tuple[Document, float]]

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 (str) – input text
k (int) – Number of Documents to return. Defaults to 4.
**kwargs (Any) –
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)

Return type

List[Tuple[Document, float]]

async asimilarity_search_with_score(query: str, k: int = 4, filter: Optional[str] = None, **kwargs: Any) → List[Tuple[Document, float]][source]¶

Retrieve texts most similar to query and convert the result to Document objects.

Parameters

query (str) – Text to look up documents similar to.
k (int) – Number of Documents to return. Defaults to 4.
filter (Optional[str]) – Optional metadata filter in str format
kwargs (Any) –

Returns

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

Return type

List[Tuple[Document, float]]

delete(ids: Optional[List[str]] = None, delete_all: Optional[bool] = None, batch_size: Optional[int] = 1000, **kwargs: Any) → None[source]¶

Delete by vector IDs

Parameters

ids (Optional[List[str]]) – List of ids to delete.
delete_all (Optional[bool]) – Delete all vectors in the index.
batch_size (Optional[int]) – Batch size to use when deleting the embeddings.
request. (Upstash supports at max 1000 deletions per) –
kwargs (Any) –

Return type

None

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

Return VectorStore initialized from documents and embeddings.

Parameters

documents (List[Document]) –
embedding (Embeddings) –
kwargs (Any) –

Return type

VST

classmethod from_texts(texts: List[str], embedding: Embeddings, metadatas: Optional[List[dict]] = None, ids: Optional[List[str]] = None, embedding_chunk_size: int = 1000, batch_size: int = 32, text_key: str = 'text', index: Optional[Index] = None, async_index: Optional[AsyncIndex] = None, index_url: Optional[str] = None, index_token: Optional[str] = None, **kwargs: Any) → UpstashVectorStore[source]¶

Create a new UpstashVectorStore from a list of texts.

Example

Parameters

texts (List[str]) –
embedding (Embeddings) –
metadatas (Optional[List[dict]]) –
ids (Optional[List[str]]) –
embedding_chunk_size (int) –
batch_size (int) –
text_key (str) –
index (Optional[Index]) –
async_index (Optional[AsyncIndex]) –
index_url (Optional[str]) –
index_token (Optional[str]) –
kwargs (Any) –

Return type

UpstashVectorStore

info() → InfoResult[source]¶

Get statistics about the index.

Returns

total number of vectors
total number of vectors waiting to be indexed
total size of the index on disk in bytes
dimension count for the index
similarity function selected for the index

Return type

InfoResult

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

Return docs selected using the maximal marginal relevance.

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

Parameters

query (str) – Text to look up documents similar to.
k (int) – Number of Documents to return. Defaults to 4.
fetch_k (int) – Number of Documents to fetch to pass to MMR algorithm.
lambda_mult (float) – 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.
filter (Optional[str]) – Optional metadata filter in str format
kwargs (Any) –

Returns

List of Documents selected by maximal marginal relevance.

Return type

List[Document]

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

Return docs selected using the maximal marginal relevance.

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

Parameters

embedding (Union[List[float], str]) – Embedding to look up documents similar to.
k (int) – Number of Documents to return. Defaults to 4.
fetch_k (int) – Number of Documents to fetch to pass to MMR algorithm.
lambda_mult (float) – 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.
filter (Optional[str]) – Optional metadata filter in str format
kwargs (Any) –

Returns

List of Documents selected by maximal marginal relevance.

Return type

List[Document]

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

Return docs most similar to query using specified search type.

Parameters

query (str) –
search_type (str) –
kwargs (Any) –

Return type

List[Document]

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

Return documents most similar to query.

Parameters

query (str) – Text to look up documents similar to.
k (int) – Number of Documents to return. Defaults to 4.
filter (Optional[str]) – Optional metadata filter in str format
kwargs (Any) –

Returns

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

Return type

List[Document]

similarity_search_by_vector(embedding: Union[List[float], str], k: int = 4, filter: Optional[str] = None, **kwargs: Any) → List[Document][source]¶

Return documents closest to the given embedding.

Parameters

embedding (Union[List[float], str]) – Embedding to look up documents similar to.
k (int) – Number of Documents to return. Defaults to 4.
filter (Optional[str]) – Optional metadata filter in str format
kwargs (Any) –

Returns

List of Documents most similar to the query

Return type

List[Document]

similarity_search_by_vector_with_score(embedding: Union[List[float], str], k: int = 4, filter: Optional[str] = None, **kwargs: Any) → List[Tuple[Document, float]][source]¶

Return texts whose embedding is closest to the given embedding

Parameters

embedding (Union[List[float], str]) –
k (int) –
filter (Optional[str]) –
kwargs (Any) –

Return type

List[Tuple[Document, float]]

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 (str) – input text
k (int) – Number of Documents to return. Defaults to 4.
**kwargs (Any) –
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)

Return type

List[Tuple[Document, float]]

similarity_search_with_score(query: str, k: int = 4, filter: Optional[str] = None, **kwargs: Any) → List[Tuple[Document, float]][source]¶

Retrieve texts most similar to query and convert the result to Document objects.

Parameters

query (str) – Text to look up documents similar to.
k (int) – Number of Documents to return. Defaults to 4.
filter (Optional[str]) – Optional metadata filter in str format
kwargs (Any) –

Returns

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

Return type

List[Tuple[Document, float]]

langchain_community.vectorstores.upstash.UpstashVectorStore¶

`langchain_community.vectorstores.upstash`.UpstashVectorStore¶