Google Cloud SQL for MySQL 集成

pip install -qU langchain-google-cloud-sql-mysql langchain-google-vertexai

# # Automatically restart kernel after installs so that your environment can access the new packages
# import IPython

# app = IPython.Application.instance()
# app.kernel.do_shutdown(True)

from google.colab import auth

auth.authenticate_user()

# @markdown Please fill in the value below with your Google Cloud project ID and then run the cell.

PROJECT_ID = "my-project-id"  # @param {type:"string"}

# Set the project id
!gcloud config set project {PROJECT_ID}

# @title Set Your Values Here { display-mode: "form" }
REGION = "us-central1"  # @param {type: "string"}
INSTANCE = "my-mysql-instance"  # @param {type: "string"}
DATABASE = "my-database"  # @param {type: "string"}
TABLE_NAME = "vector_store"  # @param {type: "string"}

from langchain_google_cloud_sql_mysql import MySQLEngine

engine = MySQLEngine.from_instance(
    project_id=PROJECT_ID, region=REGION, instance=INSTANCE, database=DATABASE
)

engine.init_vectorstore_table(
    table_name=TABLE_NAME,
    vector_size=768,  # Vector size for VertexAI model(textembedding-gecko@latest)
)

# enable Vertex AI API
!gcloud services enable aiplatform.googleapis.com

from langchain_google_vertexai import VertexAIEmbeddings

embedding = VertexAIEmbeddings(
    model_name="textembedding-gecko@latest", project=PROJECT_ID
)

from langchain_google_cloud_sql_mysql import MySQLVectorStore

store = MySQLVectorStore(
    engine=engine,
    embedding_service=embedding,
    table_name=TABLE_NAME,
)

import uuid

all_texts = ["Apples and oranges", "Cars and airplanes", "Pineapple", "Train", "Banana"]
metadatas = [{"len": len(t)} for t in all_texts]
ids = [str(uuid.uuid4()) for _ in all_texts]

store.add_texts(all_texts, metadatas=metadatas, ids=ids)

store.delete([ids[1]])

query = "I'd like a fruit."
docs = store.similarity_search(query)
print(docs[0].page_content)

Pineapple

query_vector = embedding.embed_query(query)
docs = store.similarity_search_by_vector(query_vector, k=2)
print(docs)

[Document(page_content='Pineapple', metadata={'len': 9}), Document(page_content='Banana', metadata={'len': 6})]

GRANT EXECUTE ON PROCEDURE mysql.create_vector_index TO '<IAM_DB_USER>'@'%';
GRANT EXECUTE ON PROCEDURE mysql.alter_vector_index TO '<IAM_DB_USER>'@'%';
GRANT EXECUTE ON PROCEDURE mysql.drop_vector_index TO '<IAM_DB_USER>'@'%';
GRANT SELECT ON mysql.vector_indexes TO '<IAM_DB_USER>'@'%';

from langchain_google_cloud_sql_mysql import VectorIndex

store.apply_vector_index(VectorIndex())

store.drop_vector_index()

from langchain_google_cloud_sql_mysql import Column

# set table name
CUSTOM_TABLE_NAME = "vector_store_custom"

engine.init_vectorstore_table(
    table_name=CUSTOM_TABLE_NAME,
    vector_size=768,  # VertexAI model: textembedding-gecko@latest
    metadata_columns=[Column("len", "INTEGER")],
)


# initialize MySQLVectorStore with custom metadata columns
custom_store = MySQLVectorStore(
    engine=engine,
    embedding_service=embedding,
    table_name=CUSTOM_TABLE_NAME,
    metadata_columns=["len"],
    # connect to an existing VectorStore by customizing the table schema:
    # id_column="uuid",
    # content_column="documents",
    # embedding_column="vectors",
)

import uuid

# add texts to the vector store
all_texts = ["Apples and oranges", "Cars and airplanes", "Pineapple", "Train", "Banana"]
metadatas = [{"len": len(t)} for t in all_texts]
ids = [str(uuid.uuid4()) for _ in all_texts]
custom_store.add_texts(all_texts, metadatas=metadatas, ids=ids)

# use filter on search
query_vector = embedding.embed_query("I'd like a fruit.")
docs = custom_store.similarity_search_by_vector(query_vector, filter="len >= 6")

print(docs)

[Document(page_content='Pineapple', metadata={'len': 9}), Document(page_content='Banana', metadata={'len': 6}), Document(page_content='Apples and oranges', metadata={'len': 18}), Document(page_content='Cars and airplanes', metadata={'len': 18})]