Spanner 벡터 검색 시작하기

gcloud auth list

Credentialed accounts:
 - <myaccount>@<mydomain>.com (active)

gcloud config list project

[core]
project = <PROJECT_ID>

gcloud config set project <PROJECT_ID>

echo $GOOGLE_CLOUD_PROJECT

<PROJECT_ID>

gcloud services enable spanner.googleapis.com

export SPANNER_INSTANCE_ID=retail-demo
gcloud spanner instances create $SPANNER_INSTANCE_ID \
--config=regional-us-central1 \
--description="spanner AI retail demo" \
--nodes=1

$ gcloud spanner instances create $SPANNER_INSTANCE_ID \
--config=regional-us-central1 \
--description="spanner AI retail demo" \
--nodes=1
Creating instance...done.  

export SPANNER_DATABASE=cymbal-bikes
gcloud spanner databases create $SPANNER_DATABASE \
 --instance=$SPANNER_INSTANCE_ID

$ gcloud spanner databases create $SPANNER_DATABASE \
 --instance=$SPANNER_INSTANCE_ID
Creating database...done.

CREATE TABLE products (
categoryId INT64 NOT NULL,
productId INT64 NOT NULL,
productName STRING(MAX) NOT NULL,
productDescription STRING(MAX) NOT NULL,
productDescriptionEmbedding ARRAY<FLOAT32>,
createTime TIMESTAMP NOT NULL OPTIONS (
allow_commit_timestamp = true
),
inventoryCount INT64 NOT NULL,
priceInCents INT64,
) PRIMARY KEY(categoryId, productId);

CREATE MODEL EmbeddingsModel INPUT(
content STRING(MAX),
) OUTPUT(
embeddings STRUCT<statistics STRUCT<truncated BOOL, token_count FLOAT32>, values ARRAY<FLOAT32>>,
) REMOTE OPTIONS (
endpoint = '//aiplatform.googleapis.com/projects/<PROJECT_ID>/locations/us-central1/publishers/google/models/text-embedding-004'
);


CREATE MODEL LLMModel INPUT(
prompt STRING(MAX),
) OUTPUT(
content STRING(MAX),
) REMOTE OPTIONS (
endpoint = '//aiplatform.googleapis.com/projects/<PROJECT_ID>/locations/us-central1/publishers/google/models/gemini-pro',
default_batch_size = 1
);

INSERT INTO products (categoryId, productId, productName, productDescription, createTime, inventoryCount, priceInCents)
VALUES (1, 1, "Cymbal Helios Helmet", "Safety meets style with the Cymbal children's bike helmet. Its lightweight design, superior ventilation, and adjustable fit ensure comfort and protection on every ride. Stay bright and keep your child safe under the sun with Cymbal Helios!", PENDING_COMMIT_TIMESTAMP(), 100, 10999),
(1, 2, "Cymbal Sprout", "Let their cycling journey begin with the Cymbal Sprout, the ideal balance bike for beginning riders ages 2-4 years. Its lightweight frame, low seat height, and puncture-proof tires promote stability and confidence as little ones learn to balance and steer. Watch them sprout into cycling enthusiasts with Cymbal Sprout!", PENDING_COMMIT_TIMESTAMP(), 10, 13999),
(1, 3, "Cymbal Spark Jr.", "Light, vibrant, and ready for adventure, the Spark Jr. is the perfect first bike for young riders (ages 5-8). Its sturdy frame, easy-to-use brakes, and puncture-resistant tires inspire confidence and endless playtime. Let the spark of cycling ignite with Cymbal!", PENDING_COMMIT_TIMESTAMP(), 34, 13900),
(1, 4, "Cymbal Summit", "Conquering trails is a breeze with the Summit mountain bike. Its lightweight aluminum frame, responsive suspension, and powerful disc brakes provide exceptional control and comfort for experienced bikers navigating rocky climbs or shredding downhill. Reach new heights with Cymbal Summit!", PENDING_COMMIT_TIMESTAMP(), 0, 79999),
(1, 5, "Cymbal Breeze", "Cruise in style and embrace effortless pedaling with the Breeze electric bike. Its whisper-quiet motor and long-lasting battery let you conquer hills and distances with ease. Enjoy scenic rides, commutes, or errands with a boost of confidence from Cymbal Breeze!", PENDING_COMMIT_TIMESTAMP(), 72, 129999),
(1, 6, "Cymbal Trailblazer Backpack", "Carry all your essentials in style with the Trailblazer backpack. Its water-resistant material, multiple compartments, and comfortable straps keep your gear organized and accessible, allowing you to focus on the adventure. Blaze new trails with Cymbal Trailblazer!", PENDING_COMMIT_TIMESTAMP(), 24, 7999),
(1, 7, "Cymbal Phoenix Lights", "See and be seen with the Phoenix bike lights. Powerful LEDs and multiple light modes ensure superior visibility, enhancing your safety and enjoyment during day or night rides. Light up your journey with Cymbal Phoenix!", PENDING_COMMIT_TIMESTAMP(), 87, 3999),
(1, 8, "Cymbal Windstar Pump", "Flat tires are no match for the Windstar pump. Its compact design, lightweight construction, and high-pressure capacity make inflating tires quick and effortless. Get back on the road in no time with Cymbal Windstar!", PENDING_COMMIT_TIMESTAMP(), 36, 24999),
(1, 9,"Cymbal Odyssey Multi-Tool","Be prepared for anything with the Odyssey multi-tool. This handy gadget features essential tools like screwdrivers, hex wrenches, and tire levers, keeping you ready for minor repairs and adjustments on the go. Conquer your journey with Cymbal Odyssey!", PENDING_COMMIT_TIMESTAMP(), 52, 999),
(1, 10,"Cymbal Nomad Water Bottle","Stay hydrated on every ride with the Nomad water bottle. Its sleek design, BPA-free construction, and secure lock lid make it the perfect companion for staying refreshed and motivated throughout your adventures. Hydrate and explore with Cymbal Nomad!", PENDING_COMMIT_TIMESTAMP(), 42, 1299);

UPDATE products p1
SET productDescriptionEmbedding =
(SELECT embeddings.values from ML.PREDICT(MODEL EmbeddingsModel,
(SELECT productDescription as content FROM products p2 where p2.productId=p1.productId)))
WHERE categoryId=1;

-- Use Spanner's vector search, and integration with embedding and LLM models to
-- return items that are semantically relevant and available in inventory based on
-- real-time data.


SELECT productName, productDescription, inventoryCount, COSINE_DISTANCE(
productDescriptionEmbedding,
(   SELECT embeddings.values
FROM ML.PREDICT(
MODEL EmbeddingsModel,
(SELECT "I'd like to buy a starter bike for my 3 year old child" as content)
)
)
) as distance
FROM products
WHERE inventoryCount > 0
ORDER BY distance
LIMIT 5;

-- Use an LLM to analyze this list and provide a recommendation on whether each
-- product is a good fit for the user. We use the vector search and real time
-- inventory data to first filter the products to reduce the size of the prompt to
-- the LLM.
SELECT productName, productDescription, inventoryCount, content AS LLMResponse
FROM ML.PREDICT(
MODEL LLMModel,
(   SELECT
inventoryCount,
productName,
productDescription,
CONCAT(
"Answer with ‘Yes' or ‘No' and explain why: Is this a good fit for me?",
"I'd like to buy a starter bike for my 3 year old child \n",
"Product Name: ", productName, "\n",
"Product Description:", productDescription) AS prompt,
FROM products
WHERE inventoryCount > 0
ORDER by COSINE_DISTANCE(
productDescriptionEmbedding,
(   SELECT embeddings.values
FROM ML.PREDICT(
MODEL EmbeddingsModel,
( SELECT "I'd like to buy a starter bike for my 3 year old child" as content)
)
)
) LIMIT 5
),
STRUCT(256 AS maxOutputTokens)
);

ALTER TABLE `products` DROP COLUMN `productDescriptionEmbedding`;
ALTER TABLE
  `products` ADD COLUMN `productDescriptionEmbedding` ARRAY<FLOAT32>(vector_length=>768);

UPDATE products p1
SET productDescriptionEmbedding =
(SELECT embeddings.values from ML.PREDICT(MODEL EmbeddingsModel,
(SELECT productDescription as content FROM products p2 where p2.productId=p1.productId)))
WHERE categoryId=1;

CREATE VECTOR INDEX ProductDescriptionEmbeddingIndex
    ON products(productDescriptionEmbedding)
    WHERE productDescriptionEmbedding IS NOT NULL
OPTIONS (
 distance_type = 'COSINE'
);

SELECT productName, productDescription, inventoryCount, COSINE_DISTANCE(
productDescriptionEmbedding,
(   SELECT embeddings.values
FROM ML.PREDICT(
MODEL EmbeddingsModel,
(SELECT "I'd like to buy a starter bike for my 3 year old child" as content)
)
)
) as distance
FROM products
WHERE inventoryCount > 0
ORDER BY distance
LIMIT 5;

-- Generate the prompt embeddings
SELECT embeddings.values
FROM ML.PREDICT(
  MODEL EmbeddingsModel,
   (SELECT "I'd like to buy a starter bike for my 3 year old child" as content)
  )
)

-- Embedding query now using the vector index


SELECT productName, productDescription, inventoryCount, 
  APPROX_COSINE_DISTANCE(productDescriptionEmbedding, array<float32>[@VECTOR], options => JSON '{\"num_leaves_to_search\": 10}')
FROM products @{force_index=ProductDescriptionEmbeddingIndex}
WHERE productDescriptionEmbedding IS NOT NULL AND inventoryCount > 0
ORDER BY distance
LIMIT 5;