langchain_community.vectorstores.lantern
.Lantern¶
- class langchain_community.vectorstores.lantern.Lantern(connection_string: str, embedding_function: Embeddings, distance_strategy: DistanceStrategy = DistanceStrategy.COSINE, collection_name: str = 'langchain', collection_metadata: Optional[dict] = None, pre_delete_collection: bool = False, logger: Optional[Logger] = None, relevance_score_fn: Optional[Callable[[float], float]] = None)[source]¶
Postgres with the lantern extension as a vector store.
lantern uses sequential scan by default. but you can create a HNSW index using the create_hnsw_index method. - connection_string is a postgres connection string. - embedding_function any embedding function implementing
langchain.embeddings.base.Embeddings interface.
- collection_name is the name of the collection to use. (default: langchain)
- NOTE: This is the name of the table in which embedding data will be stored
The table will be created when initializing the store (if not exists) So, make sure the user has the right permissions to create tables.
- distance_strategy is the distance strategy to use. (default: EUCLIDEAN)
EUCLIDEAN is the euclidean distance.
COSINE is the cosine distance.
HAMMING is the hamming distance.
- pre_delete_collection if True, will delete the collection if it exists.
(default: False) - Useful for testing.
Attributes
distance_function
distance_strategy
embeddings
Access the query embedding object if available.
Methods
__init__
(connection_string, embedding_function)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_embeddings
(texts, embeddings, metadatas, ...)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.
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.
Return docs and relevance scores in the range [0, 1], asynchronously.
asimilarity_search_with_score
(*args, **kwargs)Run similarity search with distance asynchronously.
connect
()connection_string_from_db_params
(driver, ...)Return connection string from database parameters.
create_hnsw_index
([dims, m, ...])Create HNSW index on collection.
delete
([ids])Delete vectors by ids or uuids.
from_documents
(documents, embedding[, ...])Initialize a vector store with a set of documents.
from_embeddings
(text_embeddings, embedding)Construct Lantern wrapper from raw documents and pre- generated embeddings.
from_existing_index
(embedding[, ...])Get instance of an existing Lantern store.This method will return the instance of the store without inserting any new embeddings
from_texts
(texts, embedding[, metadatas, ...])Initialize Lantern vectorstore from list of texts.
max_marginal_relevance_search
(query[, k, ...])Return docs selected using the maximal marginal relevance.
Return docs selected using the maximal marginal relevance
Return docs selected using the maximal marginal relevance with score.
Return docs selected using the maximal marginal relevance with score
search
(query, search_type, **kwargs)Return docs most similar to query using specified search type.
similarity_search
(query[, k, filter])Return docs most similar to query.
similarity_search_by_vector
(embedding[, k, ...])Return docs most similar to embedding vector.
Return docs and relevance scores in the range [0, 1].
similarity_search_with_score
(query[, k, filter])Run similarity search with distance.
similarity_search_with_score_by_vector
(embedding)- __init__(connection_string: str, embedding_function: Embeddings, distance_strategy: DistanceStrategy = DistanceStrategy.COSINE, collection_name: str = 'langchain', collection_metadata: Optional[dict] = None, pre_delete_collection: bool = False, logger: Optional[Logger] = None, relevance_score_fn: Optional[Callable[[float], float]] = None) None [source]¶
- 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_embeddings(texts: List[str], embeddings: List[List[float]], metadatas: List[dict], ids: List[str], **kwargs: Any) None [source]¶
- add_texts(texts: Iterable[str], metadatas: Optional[List[dict]] = None, ids: Optional[List[str]] = None, **kwargs: Any) List[str] [source]¶
Run more texts through the embeddings and add to the vectorstore.
- Parameters
texts – Iterable of strings to add to the vectorstore.
metadatas – Optional list of metadatas associated with the texts.
kwargs – vectorstore specific parameters
- 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
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.
- classmethod connection_string_from_db_params(driver: str, host: str, port: int, database: str, user: str, password: str) str [source]¶
Return connection string from database parameters.
- create_hnsw_index(dims: int = 1536, m: int = 16, ef_construction: int = 64, ef_search: int = 64, **_kwargs: Any) None [source]¶
Create HNSW index on collection.
- Optional Keyword Args for HNSW Index:
engine: “nmslib”, “faiss”, “lucene”; default: “nmslib”
ef: Size of the dynamic list used during k-NN searches. Higher values lead to more accurate but slower searches; default: 64
ef_construction: Size of the dynamic list used during k-NN graph creation. Higher values lead to more accurate graph but slower indexing speed; default: 64
m: Number of bidirectional links created for each new element. Large impact on memory consumption. Between 2 and 100; default: 16
dims: Dimensions of the vectors in collection. default: 1536
- delete(ids: Optional[List[str]] = None, **kwargs: Any) None [source]¶
Delete vectors by ids or uuids.
- Parameters
ids – List of ids to delete.
- classmethod from_documents(documents: List[Document], embedding: Embeddings, collection_name: str = 'langchain', distance_strategy: DistanceStrategy = DistanceStrategy.COSINE, ids: Optional[List[str]] = None, pre_delete_collection: bool = False, **kwargs: Any) Lantern [source]¶
Initialize a vector store with a set of documents.
Postgres connection string is required “Either pass it as connection_string parameter or set the LANTERN_CONNECTION_STRING environment variable.
connection_string is a postgres connection string.
documents is list of
Document
to initialize the vector store with- embedding is
Embeddings
that will be used for embedding the text sent. If none is sent, then the multilingual Tensorflow Universal Sentence Encoder will be used.
- embedding is
- collection_name is the name of the collection to use. (default: langchain)
- NOTE: This is the name of the table in which embedding data will be stored
The table will be created when initializing the store (if not exists) So, make sure the user has the right permissions to create tables.
- distance_strategy is the distance strategy to use. (default: EUCLIDEAN)
EUCLIDEAN is the euclidean distance.
COSINE is the cosine distance.
HAMMING is the hamming distance.
ids row ids to insert into collection.
- pre_delete_collection if True, will delete the collection if it exists.
(default: False) - Useful for testing.
- classmethod from_embeddings(text_embeddings: List[Tuple[str, List[float]]], embedding: Embeddings, metadatas: Optional[List[dict]] = None, collection_name: str = 'langchain', ids: Optional[List[str]] = None, pre_delete_collection: bool = False, distance_strategy: DistanceStrategy = DistanceStrategy.COSINE, **kwargs: Any) Lantern [source]¶
Construct Lantern wrapper from raw documents and pre- generated embeddings.
Postgres connection string is required “Either pass it as connection_string parameter or set the LANTERN_CONNECTION_STRING environment variable.
Order of elements for lists ids, text_embeddings, metadatas should match, so each row will be associated with correct values.
connection_string is fully populated connection string for postgres database
- text_embeddings is array with tuples (text, embedding)
to insert into collection.
- embedding is
Embeddings
that will be used for embedding the text sent. If none is sent, then the multilingual Tensorflow Universal Sentence Encoder will be used.
- embedding is
metadatas row metadata to insert into collection.
- collection_name is the name of the collection to use. (default: langchain)
- NOTE: This is the name of the table in which embedding data will be stored
The table will be created when initializing the store (if not exists) So, make sure the user has the right permissions to create tables.
ids row ids to insert into collection.
- pre_delete_collection if True, will delete the collection if it exists.
(default: False) - Useful for testing.
- distance_strategy is the distance strategy to use. (default: EUCLIDEAN)
EUCLIDEAN is the euclidean distance.
COSINE is the cosine distance.
HAMMING is the hamming distance.
- classmethod from_existing_index(embedding: Embeddings, collection_name: str = 'langchain', pre_delete_collection: bool = False, distance_strategy: DistanceStrategy = DistanceStrategy.COSINE, **kwargs: Any) Lantern [source]¶
Get instance of an existing Lantern store.This method will return the instance of the store without inserting any new embeddings
Postgres connection string is required “Either pass it as connection_string parameter or set the LANTERN_CONNECTION_STRING environment variable.
connection_string is a postgres connection string.
- embedding is
Embeddings
that will be used for embedding the text sent. If none is sent, then the multilingual Tensorflow Universal Sentence Encoder will be used.
- embedding is
- collection_name is the name of the collection to use. (default: langchain)
- NOTE: This is the name of the table in which embedding data will be stored
The table will be created when initializing the store (if not exists) So, make sure the user has the right permissions to create tables.
ids row ids to insert into collection.
- pre_delete_collection if True, will delete the collection if it exists.
(default: False) - Useful for testing.
- distance_strategy is the distance strategy to use. (default: EUCLIDEAN)
EUCLIDEAN is the euclidean distance.
COSINE is the cosine distance.
HAMMING is the hamming distance.
- classmethod from_texts(texts: List[str], embedding: Embeddings, metadatas: Optional[List[dict]] = None, collection_name: str = 'langchain', distance_strategy: DistanceStrategy = DistanceStrategy.COSINE, ids: Optional[List[str]] = None, pre_delete_collection: bool = False, **kwargs: Any) Lantern [source]¶
Initialize Lantern vectorstore from list of texts. The embeddings will be generated using embedding class provided.
Order of elements for lists ids, texts, metadatas should match, so each row will be associated with correct values.
Postgres connection string is required “Either pass it as connection_string parameter or set the LANTERN_CONNECTION_STRING environment variable.
connection_string is fully populated connection string for postgres database
texts texts to insert into collection.
- embedding is
Embeddings
that will be used for embedding the text sent. If none is sent, then the multilingual Tensorflow Universal Sentence Encoder will be used.
- embedding is
metadatas row metadata to insert into collection.
- collection_name is the name of the collection to use. (default: langchain)
- NOTE: This is the name of the table in which embedding data will be stored
The table will be created when initializing the store (if not exists) So, make sure the user has the right permissions to create tables.
- distance_strategy is the distance strategy to use. (default: EUCLIDEAN)
EUCLIDEAN is the euclidean distance.
COSINE is the cosine distance.
HAMMING is the hamming distance.
ids row ids to insert into collection.
- pre_delete_collection if True, will delete the collection if it exists.
(default: False) - Useful for testing.
- max_marginal_relevance_search(query: str, k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, filter: Optional[Dict[str, 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. Defaults to 20.
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[Dict[str, str]]) – Filter by metadata. Defaults to None.
- Returns
List of Documents selected by maximal marginal relevance.
- Return type
List[Document]
- max_marginal_relevance_search_by_vector(embedding: List[float], k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, filter: Optional[Dict[str, str]] = None, **kwargs: Any) List[Document] [source]¶
- Return docs selected using the maximal marginal relevance
to embedding vector.
- Maximal marginal relevance optimizes for similarity to query AND diversity
among selected documents.
- Parameters
embedding (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. Defaults to 20.
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[Dict[str, str]]) – Filter by metadata. Defaults to None.
- Returns
List of Documents selected by maximal marginal relevance.
- Return type
List[Document]
- max_marginal_relevance_search_with_score(query: str, k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, filter: Optional[dict] = None, **kwargs: Any) List[Tuple[Document, float]] [source]¶
Return docs selected using the maximal marginal relevance with score.
- 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. Defaults to 20.
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[Dict[str, str]]) – Filter by metadata. Defaults to None.
- Returns
- List of Documents selected by maximal marginal
relevance to the query and score for each.
- Return type
List[Tuple[Document, float]]
- max_marginal_relevance_search_with_score_by_vector(embedding: List[float], k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, filter: Optional[Dict[str, str]] = None, **kwargs: Any) List[Tuple[Document, float]] [source]¶
- Return docs selected using the maximal marginal relevance with score
to embedding vector.
- Maximal marginal relevance optimizes for similarity to query AND diversity
among selected documents.
- Parameters
embedding – 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. Defaults to 20.
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[Dict[str, str]]) – Filter by metadata. Defaults to None.
- Returns
- List of Documents selected by maximal marginal
relevance to the query and score for each.
- Return type
List[Tuple[Document, float]]
- 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, **kwargs: Any) List[Document] [source]¶
Return docs most similar to query.
- similarity_search_by_vector(embedding: List[float], k: int = 4, filter: Optional[dict] = None, **kwargs: Any) List[Document] [source]¶
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_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)