TiDBVectorStore#

class langchain_community.vectorstores.tidb_vector.TiDBVectorStore(connection_string: str, embedding_function: Embeddings, table_name: str = 'langchain_vector', distance_strategy: str = 'cosine', *, engine_args: Dict[str, Any] | None = None, drop_existing_table: bool = False, **kwargs: Any)[source]#

TiDB Vector Store.

Initialize a TiDB Vector Store in Langchain with a flexible and standardized table structure for storing vector data which remains fixed regardless of the dynamic table name setting.

The vector table schema includes: - ‘id’: a UUID for each entry. - ‘embedding’: stores vector data in a VectorType column. - ‘document’: a Text column for the original data or additional information. - ‘meta’: a JSON column for flexible metadata storage. - ‘create_time’ and ‘update_time’: timestamp columns for tracking data changes.

This table structure caters to general use cases and complex scenarios where the table serves as a semantic layer for advanced data integration and analysis, leveraging SQL for join queries.

Parameters:

connection_string (str) – The connection string for the TiDB database, format: “mysql+pymysql://root@34.212.137.91:4000/test”.
embedding_function (Embeddings) – The embedding function used to generate embeddings.
table_name (str, optional) – The name of the table that will be used to store vector data. If you do not provide a table name, a default table named langchain_vector will be created automatically.
distance_strategy (str) – The strategy used for similarity search, defaults to “cosine”, valid values: “l2”, “cosine”.
engine_args (Optional[Dict]) – Additional arguments for the database engine, defaults to None.
drop_existing_table (bool) – Drop the existing TiDB table before initializing, defaults to False.
**kwargs (Any) – Additional keyword arguments.

Examples

from langchain_community.vectorstores import TiDBVectorStore from langchain_openai import OpenAIEmbeddings

embeddingFunc = OpenAIEmbeddings() CONNECTION_STRING = “mysql+pymysql://root@34.212.137.91:4000/test”

vs = TiDBVector.from_texts(: embedding=embeddingFunc, texts = […, …], connection_string=CONNECTION_STRING, distance_strategy=”l2”, table_name=”tidb_vector_langchain”,

)

query = “What did the president say about Ketanji Brown Jackson” docs = db.similarity_search_with_score(query)

Attributes

`distance_strategy`	Returns the current distance strategy.
`embeddings`	Return the function used to generate embeddings.
`tidb_vector_client`	Return the TiDB Vector Client.

Methods

`__init__`(connection_string, embedding_function)	Initialize a TiDB Vector Store in Langchain with a flexible and standardized table structure for storing vector data which remains fixed regardless of the dynamic table name setting.
`aadd_documents`(documents, **kwargs)	Async run more documents through the embeddings and add to the vectorstore.
`aadd_texts`(texts[, metadatas, ids])	Async run more texts through the embeddings and add to the vectorstore.
`add_documents`(documents, **kwargs)	Add or update documents in the vectorstore.
`add_texts`(texts[, metadatas, ids])	Add texts to TiDB Vector Store.
`adelete`([ids])	Async delete by vector ID or other criteria.
`afrom_documents`(documents, embedding, **kwargs)	Async return VectorStore initialized from documents and embeddings.
`afrom_texts`(texts, embedding[, metadatas, ids])	Async return VectorStore initialized from texts and embeddings.
`aget_by_ids`(ids, /)	Async get documents by their IDs.
`amax_marginal_relevance_search`(query[, k, ...])	Async return docs selected using the maximal marginal relevance.
`amax_marginal_relevance_search_by_vector`(...)	Async return docs selected using the maximal marginal relevance.
`as_retriever`(**kwargs)	Return VectorStoreRetriever initialized from this VectorStore.
`asearch`(query, search_type, **kwargs)	Async return docs most similar to query using a specified search type.
`asimilarity_search`(query[, k])	Async return docs most similar to query.
`asimilarity_search_by_vector`(embedding[, k])	Async return docs most similar to embedding vector.
`asimilarity_search_with_relevance_scores`(query)	Async return docs and relevance scores in the range [0, 1].
`asimilarity_search_with_score`(args, *kwargs)	Async run similarity search with distance.
`delete`([ids])	Delete vector data from the TiDB Vector Store.
`drop_vectorstore`()	Drop the Vector Store from the TiDB database.
`from_documents`(documents, embedding, **kwargs)	Return VectorStore initialized from documents and embeddings.
`from_existing_vector_table`(embedding, ...[, ...])	Create a VectorStore instance from an existing TiDB Vector Store in TiDB.
`from_texts`(texts, embedding[, metadatas])	Create a VectorStore from a list of texts.
`get_by_ids`(ids, /)	Get documents by their IDs.
`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 a specified search type.
`similarity_search`(query[, k, filter])	Perform a similarity search using the given query.
`similarity_search_by_vector`(embedding[, k])	Return docs most similar to embedding vector.
`similarity_search_with_relevance_scores`(query)	Return docs and relevance scores in the range [0, 1].
`similarity_search_with_score`(query[, k, filter])	Perform a similarity search with score based on the given query.

__init__(connection_string: str, embedding_function: Embeddings, table_name: str = 'langchain_vector', distance_strategy: str = 'cosine', *, engine_args: Dict[str, Any] | None = None, drop_existing_table: bool = False, **kwargs: Any) → None[source]#

Initialize a TiDB Vector Store in Langchain with a flexible and standardized table structure for storing vector data which remains fixed regardless of the dynamic table name setting.

The vector table schema includes: - ‘id’: a UUID for each entry. - ‘embedding’: stores vector data in a VectorType column. - ‘document’: a Text column for the original data or additional information. - ‘meta’: a JSON column for flexible metadata storage. - ‘create_time’ and ‘update_time’: timestamp columns for tracking data changes.

This table structure caters to general use cases and complex scenarios where the table serves as a semantic layer for advanced data integration and analysis, leveraging SQL for join queries.

Parameters:

connection_string (str) – The connection string for the TiDB database, format: “mysql+pymysql://root@34.212.137.91:4000/test”.
embedding_function (Embeddings) – The embedding function used to generate embeddings.
table_name (str, optional) – The name of the table that will be used to store vector data. If you do not provide a table name, a default table named langchain_vector will be created automatically.
distance_strategy (str) – The strategy used for similarity search, defaults to “cosine”, valid values: “l2”, “cosine”.
engine_args (Optional[Dict]) – Additional arguments for the database engine, defaults to None.
drop_existing_table (bool) – Drop the existing TiDB table before initializing, defaults to False.
**kwargs (Any) – Additional keyword arguments.

Return type:

None

Examples

from langchain_community.vectorstores import TiDBVectorStore from langchain_openai import OpenAIEmbeddings

embeddingFunc = OpenAIEmbeddings() CONNECTION_STRING = “mysql+pymysql://root@34.212.137.91:4000/test”

vs = TiDBVector.from_texts(: embedding=embeddingFunc, texts = […, …], connection_string=CONNECTION_STRING, distance_strategy=”l2”, table_name=”tidb_vector_langchain”,

)

query = “What did the president say about Ketanji Brown Jackson” docs = db.similarity_search_with_score(query)

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

Async run more documents through the embeddings and add to the vectorstore.

Parameters:

documents (list[Document]) – Documents to add to the vectorstore.
kwargs (Any) – Additional keyword arguments.

Returns:

List of IDs of the added texts.

Raises:

ValueError – If the number of IDs does not match the number of documents.

Return type:

list[str]

async aadd_texts(texts: Iterable[str], metadatas: list[dict] | None = None, *, ids: list[str] | None = None, **kwargs: Any) → list[str]#

Async run more texts through the embeddings and add to the vectorstore.

Parameters:

texts (Iterable[str]) – Iterable of strings to add to the vectorstore.
metadatas (list[dict] | None) – Optional list of metadatas associated with the texts. Default is None.
ids (list[str] | None) – Optional list
**kwargs (Any) – vectorstore specific parameters.

Returns:

List of ids from adding the texts into the vectorstore.

Raises:

ValueError – If the number of metadatas does not match the number of texts.
ValueError – If the number of ids does not match the number of texts.

Return type:

list[str]

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

Add or update documents in the vectorstore.

Parameters:

documents (list[Document]) – Documents to add to the vectorstore.
kwargs (Any) – Additional keyword arguments. if kwargs contains ids and documents contain ids, the ids in the kwargs will receive precedence.

Returns:

List of IDs of the added texts.

Raises:

ValueError – If the number of ids does not match the number of documents.

Return type:

list[str]

add_texts(texts: Iterable[str], metadatas: List[dict] | None = None, ids: List[str] | None = None, **kwargs: Any) → List[str][source]#

Add texts to TiDB Vector Store.

Parameters:

texts (Iterable[str]) – The texts to be added.
metadatas (Optional[List[dict]]) – The metadata associated with each text, Defaults to None.
ids (Optional[List[str]]) – The IDs to be assigned to each text, Defaults to None, will be generated if not provided.
kwargs (Any)

Returns:

The IDs assigned to the added texts.

Return type:

List[str]

async adelete(ids: list[str] | None = None, **kwargs: Any) → bool | None#

Async delete by vector ID or other criteria.

Parameters:

ids (list[str] | None) – List of ids to delete. If None, delete all. Default is None.
**kwargs (Any) – 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#

Async return VectorStore initialized from documents and embeddings.

Parameters:

documents (list[Document]) – List of Documents to add to the vectorstore.
embedding (Embeddings) – Embedding function to use.
kwargs (Any) – Additional keyword arguments.

Returns:

VectorStore initialized from documents and embeddings.

Return type:

VectorStore

async classmethod afrom_texts(texts: list[str], embedding: Embeddings, metadatas: list[dict] | None = None, *, ids: list[str] | None = None, **kwargs: Any) → VST#

Async return VectorStore initialized from texts and embeddings.

Parameters:

texts (list[str]) – Texts to add to the vectorstore.
embedding (Embeddings) – Embedding function to use.
metadatas (list[dict] | None) – Optional list of metadatas associated with the texts. Default is None.
ids (list[str] | None) – Optional list of IDs associated with the texts.
kwargs (Any) – Additional keyword arguments.

Returns:

VectorStore initialized from texts and embeddings.

Return type:

VectorStore

async aget_by_ids(ids: Sequence[str], /) → list[Document]#

Async get documents by their IDs.

The returned documents are expected to have the ID field set to the ID of the document in the vector store.

Fewer documents may be returned than requested if some IDs are not found or if there are duplicated IDs.

Users should not assume that the order of the returned documents matches the order of the input IDs. Instead, users should rely on the ID field of the returned documents.

This method should NOT raise exceptions if no documents are found for some IDs.

Parameters:: ids (Sequence[str]) – List of ids to retrieve.
Returns:: List of Documents.
Return type:: list[Document]

Added in version 0.2.11.

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

Async 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. Default is 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.
kwargs (Any)

Returns:

List of Documents selected by maximal marginal relevance.

Return type:

list[Document]

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]#

Async return docs selected using the maximal marginal relevance.

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

Parameters:

embedding (list[float]) – 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. Default is 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.
**kwargs (Any) – Arguments to pass to the search method.

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:

**kwargs (Any) –

Keyword arguments to pass to the search function. Can include: 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]#

Async return docs most similar to query using a specified search type.

Parameters:

query (str) – Input text.
search_type (str) – Type of search to perform. Can be “similarity”, “mmr”, or “similarity_score_threshold”.
**kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query.

Raises:

ValueError – If search_type is not one of “similarity”, “mmr”, or “similarity_score_threshold”.

Return type:

list[Document]

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

Async return docs most similar to query.

Parameters:

query (str) – Input text.
k (int) – Number of Documents to return. Defaults to 4.
**kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query.

Return type:

list[Document]

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

Async return docs most similar to embedding vector.

Parameters:

embedding (list[float]) – Embedding to look up documents similar to.
k (int) – Number of Documents to return. Defaults to 4.
**kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query vector.

Return type:

list[Document]

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

Async 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]]

async asimilarity_search_with_score(*args: Any, **kwargs: Any) → list[tuple[Document, float]]#

Async run similarity search with distance.

Parameters:

*args (Any) – Arguments to pass to the search method.
**kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Tuples of (doc, similarity_score).

Return type:

list[tuple[Document, float]]

delete(ids: List[str] | None = None, **kwargs: Any) → None[source]#

Delete vector data from the TiDB Vector Store.

Parameters:

ids (Optional[List[str]]) – A list of vector IDs to delete.
kwargs (Any) – Additional keyword arguments.

Return type:

None

drop_vectorstore() → None[source]#

Drop the Vector Store from the TiDB database.

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]) – List of Documents to add to the vectorstore.
embedding (Embeddings) – Embedding function to use.
kwargs (Any) – Additional keyword arguments.

Returns:

VectorStore initialized from documents and embeddings.

Return type:

VectorStore

classmethod from_existing_vector_table(embedding: Embeddings, connection_string: str, table_name: str, distance_strategy: str = 'cosine', *, engine_args: Dict[str, Any] | None = None, **kwargs: Any) → VectorStore[source]#

Create a VectorStore instance from an existing TiDB Vector Store in TiDB.

Parameters:

embedding (Embeddings) – The function to use for generating embeddings.
connection_string (str) – The connection string for the TiDB database, format: “mysql+pymysql://root@34.212.137.91:4000/test”.
table_name (str, optional) – The name of table used to store vector data, defaults to “langchain_vector”.
distance_strategy (str) – The distance strategy used for similarity search, defaults to “cosine”, allowed: “l2”, “cosine”.
engine_args (Dict[str, Any] | None) – Additional arguments for the underlying database engine, defaults to None.
**kwargs (Any) – Additional keyword arguments.

Returns:

The VectorStore instance.

Return type:

VectorStore

Raises:

NoSuchTableError – If the specified table does not exist in the TiDB.

classmethod from_texts(texts: List[str], embedding: Embeddings, metadatas: List[dict] | None = None, **kwargs: Any) → TiDBVectorStore[source]#

Create a VectorStore from a list of texts.

Parameters:

texts (List[str]) – The list of texts to be added to the TiDB Vector.
embedding (Embeddings) – The function to use for generating embeddings.
metadatas (List[dict] | None) – The list of metadata dictionaries corresponding to each text, defaults to None.
**kwargs (Any) –
Additional keyword arguments. connection_string (str): The connection string for the TiDB database,

format: “mysql+pymysql://root@34.212.137.91:4000/test”.

table_name (str, optional): The name of table used to store vector data,
defaults to “langchain_vector”.

distance_strategy: The distance strategy used for similarity search,
defaults to “cosine”, allowed: “l2”, “cosine”.

ids (Optional[List[str]]): The list of IDs corresponding to each text,
defaults to None.

engine_args: Additional arguments for the underlying database engine,
defaults to None.

drop_existing_table: Drop the existing TiDB table before initializing,
defaults to False.

Returns:

The created TiDB Vector Store.

Return type:

VectorStore

get_by_ids(ids: Sequence[str], /) → list[Document]#

Get documents by their IDs.

The returned documents are expected to have the ID field set to the ID of the document in the vector store.

Fewer documents may be returned than requested if some IDs are not found or if there are duplicated IDs.

Users should not assume that the order of the returned documents matches the order of the input IDs. Instead, users should rely on the ID field of the returned documents.

This method should NOT raise exceptions if no documents are found for some IDs.

Parameters:: ids (Sequence[str]) – List of ids to retrieve.
Returns:: List of Documents.
Return type:: list[Document]

Added in version 0.2.11.

max_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.

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. Default is 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.
**kwargs (Any) – Arguments to pass to the search method.

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, **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 (list[float]) – 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. Default is 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.
**kwargs (Any) – Arguments to pass to the search method.

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 a specified search type.

Parameters:

query (str) – Input text
search_type (str) – Type of search to perform. Can be “similarity”, “mmr”, or “similarity_score_threshold”.
**kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query.

Raises:

ValueError – If search_type is not one of “similarity”, “mmr”, or “similarity_score_threshold”.

Return type:

list[Document]

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

Perform a similarity search using the given query.

Parameters:

query (str) – The query string.
k (int, optional) – The number of results to retrieve. Defaults to 4.
filter (dict, optional) – A filter to apply to the search results. Defaults to None.
kwargs (Any) – Additional keyword arguments.

Returns:

A list of Document objects representing the search results.

Return type:

List[Document]

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

Return docs most similar to embedding vector.

Parameters:

embedding (list[float]) – Embedding to look up documents similar to.
k (int) – Number of Documents to return. Defaults to 4.
**kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query vector.

Return type:

list[Document]

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 = 5, filter: dict | None = None, **kwargs: Any) → List[Tuple[Document, float]][source]#

Perform a similarity search with score based on the given query.

Parameters:

query (str) – The query string.
k (int, optional) – The number of results to return. Defaults to 5.
filter (dict, optional) – A filter to apply to the search results. Defaults to None.
kwargs (Any) – Additional keyword arguments.

Returns:

A list of tuples containing relevant documents and their similarity scores.

Return type:

List[Tuple[Document, float]]

Examples using TiDBVectorStore