-
MorphingDB is a postgreSQL extension for supporting deep learning model inference within the database and vector storage.
-
MorphingDB allows users to import the libtorch model and make inferences using data from within the database.
-
MorphingDB allows users to store vector data with dimensional information, allowing libtorch to work directly with vector data in the database, users can store data preprocessed into vectors in the database to speed up inference.
-
MorphingDB supports model centric and task centric inference.
dowload zip to morphingdb project path
unzip model
unzip models.zip -d ./model/use docker image from docker hub
sudo docker pull morphingdb/morphingdb:1.0or build docker image
sudo docker build -t morphingdb .create docker contanier
# abs_morphingdb_test_dir is the absolute path of the morphingdb project directory from https://github.com/MorphingDB/Morphingdb_test/
sudo docker run -d
--name MorphingDB_test
-e POSTGRES_PASSWORD=123456
-v [abs_morphingdb_test_dir]:[abs_morphingdb_test_dir]
-v [data_dir]:/var/lib/postgresql/data
-p [port]:5432
morphingdbenter docker
sudo docker exec -it [contanier id] /bin/bashConnect to server
psql -p 5432 -d postgres -U postgres -h localhostEnable the extension
CREATE EXTENSION pgdl;SELECT create_model(model_name, model_path, base_model, model description);You need to write the corresponding input and output handlers for the created model in src/external_process, and rebuild extension, make install.
SELECT register_process();SELECT predict_float([model_name], ['cpu'/'gpu'], [variable_input_column]) from [table];
SELECT predict_text([model_name], ['cpu'/'gpu'], [variable_input_column]) from [table];
Use window functions to speed up predictions with variable window sizes.
SELECT comment,predict_batch_text([model_name], ['cpu'/'gpu'], [variable_input_column]) over (rows between current row and [window_size] following)
AS result
FROM [table];
SELECT comment,predict_batch_float8([model_name], ['cpu'/'gpu'], [variable_input_column]) over (rows between current row and [window_size] following)
AS result
FROM [table];SELECT image_classification(<column_name>) as task_result
FROM <table_name>
WHERE <conditions>;After the model is imported, the user can view the model information through the model_info table.
SELECT * from model_info;
MorphingDB supports vector storage, including storage of vector dimension information. In morphingdb, the vector type is mvec.
create table vec_test(id integer, vec mvec);insert into vec_test values(1, '[1.0,2.2,3.123,4.2]{4}');
insert into vec_test values(1, '[1.0,2.2,3.123,4.2]');
insert into vec_test values(1, '[1.0,2.2,3.123,4.2]{2,2}');
insert into vec_test values(1, ARRAY[1.0,2.0,3.0,1.2345]::float4[]::mvec);select get_mvec_shape(vec) from vec_test;
select get_mvec_data(vec) from vec_test;update vec_test set vec=vec+vec;
update vec_test set vec=vec-text_to_mvec('[1,2,3,4]');
select * from vec_test where vec=='[1,2.2,3.123,4.2]';A Comparative Study of in-Database Inference Approaches
Learning a Data-Driven Policy Network for Pre-Training Automated Feature Engineering
Pre-Trained Model Recommendation for Downstream Fine-tuning
SmartLite: A DBMS-based Serving System for DNN Inference in Resource-constrained Environments