`langchain_community.vectorstores.tidb_vector`.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: Optional[Dict[str, Any]] = 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”, “inner_product”.
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)	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])	Add texts to TiDB Vector Store.
`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 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.
`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])	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: Optional[Dict[str, Any]] = 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”, “inner_product”.
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]¶

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

Parameters

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

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.

Parameters

texts (Iterable[str]) –
metadatas (Optional[List[dict]]) –
kwargs (Any) –

Return type

List[str]

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.
documents (List[Document]) –
kwargs (Any) –

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, **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: Optional[List[str]] = None, **kwargs: Any) → Optional[bool]¶

Delete by vector ID or other criteria.

Parameters

ids (Optional[List[str]]) – List of ids to delete.
**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¶

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, **kwargs: Any) → VST¶

Return VectorStore initialized from texts and embeddings.

Parameters

texts (List[str]) –
embedding (Embeddings) –
metadatas (Optional[List[dict]]) –
kwargs (Any) –

Return type

VST

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.

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.
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]¶

Return docs selected using the maximal marginal relevance.

Parameters

embedding (List[float]) –
k (int) –
fetch_k (int) –
lambda_mult (float) –
kwargs (Any) –

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, **kwargs: Any) → List[Document]¶

Return docs most similar to query.

Parameters

query (str) –
k (int) –
kwargs (Any) –

Return type

List[Document]

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

Return docs most similar to embedding vector.

Parameters

embedding (List[float]) –
k (int) –
kwargs (Any) –

Return type

List[Document]

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

Run similarity search with distance asynchronously.

Parameters

args (Any) –
kwargs (Any) –

Return type

List[Tuple[Document, float]]

delete(ids: Optional[List[str]] = 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 – 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]) –
embedding (Embeddings) –
kwargs (Any) –

Return type

VST

classmethod from_existing_vector_table(embedding: Embeddings, connection_string: str, table_name: str, distance_strategy: str = 'cosine', *, engine_args: Optional[Dict[str, Any]] = 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”, ‘inner_product’.
engine_args (Optional[Dict[str, Any]]) – 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: Optional[List[dict]] = 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 (Optional[List[dict]]) – 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”, “inner_product”.

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

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.
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]

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.
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]

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[dict] = 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 – 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) –

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: Optional[dict] = 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 – Additional keyword arguments.

Returns

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

Return type

List[Tuple[Document, float]]

Examples using TiDBVectorStore¶

langchain_community.vectorstores.tidb_vector.TiDBVectorStore¶

Examples using TiDBVectorStore¶

`langchain_community.vectorstores.tidb_vector`.TiDBVectorStore¶