Summary of entries of Methods for langchain-google-cloud-sql-mysql.
langchain_google_cloud_sql_mysql.engine._get_iam_principal_email
_get_iam_principal_email(credentials: google.auth.credentials.Credentials) -> str
Get email address associated with current authenticated IAM principal.
See more: langchain_google_cloud_sql_mysql.engine._get_iam_principal_email
langchain_google_cloud_sql_mysql.vectorstore.cosine_similarity
cosine_similarity(
X: typing.Union[
typing.List[typing.List[float]], typing.List[numpy.ndarray], numpy.ndarray
],
Y: typing.Union[
typing.List[typing.List[float]], typing.List[numpy.ndarray], numpy.ndarray
],
) -> numpy.ndarray
Row-wise cosine similarity between two equal-width matrices.
See more: langchain_google_cloud_sql_mysql.vectorstore.cosine_similarity
langchain_google_cloud_sql_mysql.vectorstore.maximal_marginal_relevance
maximal_marginal_relevance(
query_embedding: numpy.ndarray,
embedding_list: list,
lambda_mult: float = 0.5,
k: int = 4,
) -> typing.List[int]
Calculate maximal marginal relevance.
See more: langchain_google_cloud_sql_mysql.vectorstore.maximal_marginal_relevance
langchain_google_cloud_sql_mysql.chat_message_history.MySQLChatMessageHistory._verify_schema
_verify_schema() -> None
Verify table exists with required schema for MySQLChatMessageHistory class.
See more: langchain_google_cloud_sql_mysql.chat_message_history.MySQLChatMessageHistory._verify_schema
langchain_google_cloud_sql_mysql.chat_message_history.MySQLChatMessageHistory.add_message
add_message(message: langchain_core.messages.base.BaseMessage) -> None
Append the message to the record in Cloud SQL.
See more: langchain_google_cloud_sql_mysql.chat_message_history.MySQLChatMessageHistory.add_message
langchain_google_cloud_sql_mysql.chat_message_history.MySQLChatMessageHistory.clear
clear() -> None
Clear session memory from Cloud SQL.
See more: langchain_google_cloud_sql_mysql.chat_message_history.MySQLChatMessageHistory.clear
langchain_google_cloud_sql_mysql.engine.MySQLEngine._create_connector_engine
_create_connector_engine(
instance_connection_name: str,
database: str,
user: typing.Optional[str],
password: typing.Optional[str],
) -> sqlalchemy.engine.base.Engine
Create a SQLAlchemy engine using the Cloud SQL Python Connector.
See more: langchain_google_cloud_sql_mysql.engine.MySQLEngine._create_connector_engine
langchain_google_cloud_sql_mysql.engine.MySQLEngine._execute
_execute(query: str, params: typing.Optional[dict] = None) -> None
Executes a SQL query within a transaction.
See more: langchain_google_cloud_sql_mysql.engine.MySQLEngine._execute
langchain_google_cloud_sql_mysql.engine.MySQLEngine._execute_outside_tx
_execute_outside_tx(query: str, params: typing.Optional[dict] = None) -> None
Executes a SQL query with autocommit (outside of transaction).
See more: langchain_google_cloud_sql_mysql.engine.MySQLEngine._execute_outside_tx
langchain_google_cloud_sql_mysql.engine.MySQLEngine._fetch
_fetch(query: str, params: typing.Optional[dict] = None)
Fetch results from a SQL query.
See more: langchain_google_cloud_sql_mysql.engine.MySQLEngine._fetch
langchain_google_cloud_sql_mysql.engine.MySQLEngine._fetch_rows
_fetch_rows(query: str, params: typing.Optional[dict] = None)
Fetch results from a SQL query as rows.
See more: langchain_google_cloud_sql_mysql.engine.MySQLEngine._fetch_rows
langchain_google_cloud_sql_mysql.engine.MySQLEngine._load_document_table
_load_document_table(table_name: str) -> sqlalchemy.sql.schema.Table
Load table schema from existing table in MySQL database.
See more: langchain_google_cloud_sql_mysql.engine.MySQLEngine._load_document_table
langchain_google_cloud_sql_mysql.engine.MySQLEngine.connect
connect() -> sqlalchemy.engine.base.Connection
Create a connection from SQLAlchemy connection pool.
See more: langchain_google_cloud_sql_mysql.engine.MySQLEngine.connect
langchain_google_cloud_sql_mysql.engine.MySQLEngine.from_instance
from_instance(
project_id: str,
region: str,
instance: str,
database: str,
user: typing.Optional[str] = None,
password: typing.Optional[str] = None,
) -> langchain_google_cloud_sql_mysql.engine.MySQLEngine
Create an instance of MySQLEngine from Cloud SQL instance details.
See more: langchain_google_cloud_sql_mysql.engine.MySQLEngine.from_instance
langchain_google_cloud_sql_mysql.engine.MySQLEngine.init_chat_history_table
init_chat_history_table(table_name: str) -> None
Create table with schema required for MySQLChatMessageHistory class.
See more: langchain_google_cloud_sql_mysql.engine.MySQLEngine.init_chat_history_table
langchain_google_cloud_sql_mysql.engine.MySQLEngine.init_document_table
init_document_table(
table_name: str,
metadata_columns: typing.List[sqlalchemy.sql.schema.Column] = [],
content_column: str = "page_content",
metadata_json_column: typing.Optional[str] = "langchain_metadata",
overwrite_existing: bool = False,
) -> None
Create a table for saving of langchain documents.
See more: langchain_google_cloud_sql_mysql.engine.MySQLEngine.init_document_table
langchain_google_cloud_sql_mysql.engine.MySQLEngine.init_vectorstore_table
init_vectorstore_table(
table_name: str,
vector_size: int,
content_column: str = "content",
embedding_column: str = "embedding",
metadata_columns: typing.List[langchain_google_cloud_sql_mysql.engine.Column] = [],
metadata_json_column: str = "langchain_metadata",
id_column: str = "langchain_id",
overwrite_existing: bool = False,
store_metadata: bool = True,
) -> None
Create a table for saving of vectors to be used with MySQLVectorStore.
See more: langchain_google_cloud_sql_mysql.engine.MySQLEngine.init_vectorstore_table
langchain_google_cloud_sql_mysql.indexes.VectorIndex
VectorIndex(
name: typing.Optional[str] = None,
index_type: typing.Optional[
langchain_google_cloud_sql_mysql.indexes.IndexType
] = None,
distance_measure: typing.Optional[
langchain_google_cloud_sql_mysql.indexes.DistanceMeasure
] = None,
num_partitions: typing.Optional[int] = None,
num_neighbors: typing.Optional[int] = None,
)
Initializes a new instance of the VectorIndex class.
See more: langchain_google_cloud_sql_mysql.indexes.VectorIndex
langchain_google_cloud_sql_mysql.loader.MySQLDocumentSaver
MySQLDocumentSaver(
engine: langchain_google_cloud_sql_mysql.engine.MySQLEngine,
table_name: str,
content_column: typing.Optional[str] = None,
metadata_json_column: typing.Optional[str] = None,
)
MySQLDocumentSaver allows for saving of langchain documents in a database.
See more: langchain_google_cloud_sql_mysql.loader.MySQLDocumentSaver
langchain_google_cloud_sql_mysql.loader.MySQLDocumentSaver.add_documents
add_documents(docs: typing.List[langchain_core.documents.base.Document]) -> None
Save documents in the DocumentSaver table.
See more: langchain_google_cloud_sql_mysql.loader.MySQLDocumentSaver.add_documents
langchain_google_cloud_sql_mysql.loader.MySQLDocumentSaver.delete
delete(docs: typing.List[langchain_core.documents.base.Document]) -> None
Delete all instances of a document from the DocumentSaver table by matching the entire Document object.
See more: langchain_google_cloud_sql_mysql.loader.MySQLDocumentSaver.delete
langchain_google_cloud_sql_mysql.loader.MySQLLoader
MySQLLoader(
engine: langchain_google_cloud_sql_mysql.engine.MySQLEngine,
table_name: str = "",
query: str = "",
content_columns: typing.Optional[typing.List[str]] = None,
metadata_columns: typing.Optional[typing.List[str]] = None,
metadata_json_column: typing.Optional[str] = None,
)
Document page content defaults to the first column present in the query or table and metadata defaults to all other columns.
See more: langchain_google_cloud_sql_mysql.loader.MySQLLoader
langchain_google_cloud_sql_mysql.loader.MySQLLoader.lazy_load
lazy_load() -> typing.Iterator[langchain_core.documents.base.Document]
Lazy Load langchain documents from a Cloud SQL MySQL database.
See more: langchain_google_cloud_sql_mysql.loader.MySQLLoader.lazy_load
langchain_google_cloud_sql_mysql.loader.MySQLLoader.load
load() -> typing.List[langchain_core.documents.base.Document]
Load langchain documents from a Cloud SQL MySQL database.
See more: langchain_google_cloud_sql_mysql.loader.MySQLLoader.load
langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.add_documents
add_documents(
documents: typing.List[langchain_core.documents.base.Document],
ids: typing.Optional[typing.List[str]] = None,
**kwargs: typing.Any
) -> typing.List[str]
Run more documents through the embeddings and add to the vectorstore.
See more: langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.add_documents
langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.add_texts
add_texts(
texts: typing.Iterable[str],
metadatas: typing.Optional[typing.List[dict]] = None,
ids: typing.Optional[typing.List[str]] = None,
**kwargs: typing.Any
) -> typing.List[str]
Run more texts through the embeddings and add to the vectorstore.
See more: langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.add_texts
langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.delete
delete(ids: typing.Optional[typing.List[str]] = None, **kwargs: typing.Any) -> bool
Delete by vector ID or other criteria.
See more: langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.delete
langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.from_documents
from_documents(documents: typing.List[langchain_core.documents.base.Document], embedding: langchain_core.embeddings.embeddings.Embeddings, engine: langchain_google_cloud_sql_mysql.engine.MySQLEngine, table_name: str, ids: typing.Optional[typing.List[str]] = None, content_column: str = 'content', embedding_column: str = 'embedding', metadata_columns: typing.List[str] = [], ignore_metadata_columns: typing.Optional[typing.List[str]] = None, id_column: str = 'langchain_id', metadata_json_column: str = 'langchain_metadata', query_options: langchain_google_cloud_sql_mysql.indexes.QueryOptions = QueryOptions(num_partitions=None, num_neighbors=10, distance_measure=
Return VectorStore initialized from documents and embeddings.
See more: langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.from_documents
langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.from_texts
from_texts(texts: typing.List[str], embedding: langchain_core.embeddings.embeddings.Embeddings, engine: langchain_google_cloud_sql_mysql.engine.MySQLEngine, table_name: str, metadatas: typing.Optional[typing.List[dict]] = None, ids: typing.Optional[typing.List[str]] = None, content_column: str = 'content', embedding_column: str = 'embedding', metadata_columns: typing.List[str] = [], ignore_metadata_columns: typing.Optional[typing.List[str]] = None, id_column: str = 'langchain_id', metadata_json_column: str = 'langchain_metadata', query_options: langchain_google_cloud_sql_mysql.indexes.QueryOptions = QueryOptions(num_partitions=None, num_neighbors=10, distance_measure=
Return VectorStore initialized from texts and embeddings.
See more: langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.from_texts
langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.max_marginal_relevance_search
max_marginal_relevance_search(
query: str,
k: typing.Optional[int] = None,
fetch_k: typing.Optional[int] = None,
lambda_mult: typing.Optional[float] = None,
filter: typing.Optional[str] = None,
query_options: typing.Optional[
langchain_google_cloud_sql_mysql.indexes.QueryOptions
] = None,
**kwargs: typing.Any
) -> typing.List[langchain_core.documents.base.Document]
Performs Maximal Marginal Relevance (MMR) search based on a text query.
See more: langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.max_marginal_relevance_search
langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.max_marginal_relevance_search_by_vector
max_marginal_relevance_search_by_vector(
embedding: typing.List[float],
k: typing.Optional[int] = None,
fetch_k: typing.Optional[int] = None,
lambda_mult: typing.Optional[float] = None,
filter: typing.Optional[str] = None,
query_options: typing.Optional[
langchain_google_cloud_sql_mysql.indexes.QueryOptions
] = None,
**kwargs: typing.Any
) -> typing.List[langchain_core.documents.base.Document]
Performs Maximal Marginal Relevance (MMR) search based on a vector embedding.
langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.max_marginal_relevance_search_with_score_by_vector
max_marginal_relevance_search_with_score_by_vector(
embedding: typing.List[float],
k: typing.Optional[int] = None,
fetch_k: typing.Optional[int] = None,
lambda_mult: typing.Optional[float] = None,
filter: typing.Optional[str] = None,
query_options: typing.Optional[
langchain_google_cloud_sql_mysql.indexes.QueryOptions
] = None,
**kwargs: typing.Any
) -> typing.List[typing.Tuple[langchain_core.documents.base.Document, float]]
Performs Maximal Marginal Relevance (MMR) search based on a vector embedding and returns documents with scores.
langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.similarity_search
similarity_search(
query: str,
k: typing.Optional[int] = None,
filter: typing.Optional[str] = None,
**kwargs: typing.Any
) -> typing.List[langchain_core.documents.base.Document]
Searches for similar documents based on a text query.
See more: langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.similarity_search
langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.similarity_search_by_vector
similarity_search_by_vector(
embedding: typing.List[float],
k: typing.Optional[int] = None,
filter: typing.Optional[str] = None,
query_options: typing.Optional[
langchain_google_cloud_sql_mysql.indexes.QueryOptions
] = None,
**kwargs: typing.Any
) -> typing.List[langchain_core.documents.base.Document]
Searches for similar documents based on a vector embedding.
See more: langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.similarity_search_by_vector
langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.similarity_search_with_score
similarity_search_with_score(
query: str,
k: typing.Optional[int] = None,
filter: typing.Optional[str] = None,
query_options: typing.Optional[
langchain_google_cloud_sql_mysql.indexes.QueryOptions
] = None,
**kwargs: typing.Any
) -> typing.List[typing.Tuple[langchain_core.documents.base.Document, float]]
Searches for similar documents based on a text query and returns their scores.
See more: langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.similarity_search_with_score
langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.similarity_search_with_score_by_vector
similarity_search_with_score_by_vector(
embedding: typing.List[float],
k: typing.Optional[int] = None,
filter: typing.Optional[str] = None,
query_options: typing.Optional[
langchain_google_cloud_sql_mysql.indexes.QueryOptions
] = None,
**kwargs: typing.Any
) -> typing.List[typing.Tuple[langchain_core.documents.base.Document, float]]
Searches for similar documents based on a vector embedding and returns their scores.
See more: langchain_google_cloud_sql_mysql.vectorstore.MySQLVectorStore.similarity_search_with_score_by_vector