feat: add MySQLVectorStore initialization methods

[jackwotherspoon]

Adding MySQLVectorStore and all the different class methods to initialize it.

Example usage:

from langchain_google_cloud_sql_mysql import  MySQLEngine, MySQLVectorStore

# create connection pool engine
engine = MySQLEngine.from_instance("my-project-id", "us-central1", "my-instance", "my-database")

# initialize vector store table
engine.init_vectorstore_table(table_name="vector_store", vector_size=768)

# base constructor
vector_store = MySQLVectorStore(
    engine,
    embedding_service=embeddings_service,
    table_name="vector_store",
)

# create VectorStore from LangChain Documents
vector_store = MySQLVectorStore.from_documents(
    docs,
    embedding=embeddings_service,
    engine=engine,
    table_name="vector_store",
    ids=ids,
)

# create VectorStore from texts
vector_store = MySQLVectorStore.from_texts(
    texts,
    embedding=embeddings_service,
    engine=engine,
    table_name="vector_store",
    metadatas=metadatas,
    ids=ids,
)

[jackwotherspoon]

Need to swap test instance over to instance that has MySQL vector support enabled.

[totoleon]

Better to name it "query_options" instead of index_query_options. In PG QueryOptions is a sub attribute of index, though in Mysql it will be separate. There will be something more than than the index itself such as whether to use KNN query or ANN query, which we call "search_type"

[jackwotherspoon]

good idea, done

[averikitsch]

Did we want to update to query_options?

[jackwotherspoon]

it is updated to query_options, this comment is pinned on out of date code

[averikitsch]

Did we want to update to query_options?