Data anonymization is the process of protecting private or sensitive information
by erasing or encrypting identifiers that link an individual to stored data.
This method is often used in situations where privacy is necessary,
such as when sharing data or making it publicly available.
The goal of data anonymization is to make it impossible (or at least very difficult) to
identify individuals from the data, while still allowing the data to be useful for analysis and research purposes.
Before you will continue reading please watch short introduction:
I have decided to create a library which will help to simply anonymize data with high-performance.
That’s why I have used Rust to code it.
The library will use three algorithms which will anonymize data.
Named Entity Recognition method enables the library to identify
and anonymize sensitive named entities in your data,
like names, organizations, locations, and other personal identifiers.
Here you can use existing models from HuggingFace for different languages for example:
The models are based on external libraries like pytorch. To avoid external dependencies
I have used rust tract library which is a rust onnx implementation.
To use models we need to convert them to onnx format using the transformers library.
docker run -it-v$(pwd):/app/ -p 8080:8080 qooba/anonymize-rs server --host 0.0.0.0 --port 8080 --config config.yaml
For the NER algorithm we can configure if the predicted entity will be replaced or not.
For the example request we will receive an anonymized response and replace items.
curl -X GET "http://localhost:8080/api/anonymize?text=I like to eat apples and bananas and plums"-H"accept: application/json"-H"Content-Type: application/json"
Response:
{"text":"I like to eat FRUIT_FLASH0 and FRUIT_FLASH1 and FRUIT_REGEX0","items":{"FRUIT_FLASH0":"apples","FRUIT_FLASH1":"banans","FRUIT_REGEX0":"plums"}}
If needed we can deanonymize the data using a separate endpoint.
curl -X POST "http://localhost:8080/api/deanonymize"-H"accept: application/json"-H"Content-Type: application/json"-d'{
"text": "I like to eat FRUIT_FLASH0 and FRUIT_FLASH1 and FRUIT_REGEX0",
"items": {
"FRUIT_FLASH0": "apples",
"FRUIT_FLASH1": "banans",
"FRUIT_REGEX0": "plums"
}
}'
Response:
{"text":"I like to eat apples and bananas and plums"}
If we prefer we can use the library from python code in this case we simply install the library.
And we can use it in python.
We have discussed the first anonymization algorithm but what if it is not enough ?
There are two additional methods. First is Flush Text algorithm which is
a fast method for searching and replacing words in large datasets,
used to anonymize predefined sensitive information.
For flush text we can define configuration where we can read keywords in separate file
where each line is a keyword or in the keyword configuration section.
The last method is simple Regex where we can define patterns which will be replaced.
We can combine several methods and build an anonymization pipeline:
Remember that it
uses automated detection mechanisms, and there is no guarantee that it will find all sensitive information.
You should always ensure that your data protection measures are comprehensive and multi-layered.
Currently large language models gain popularity due to their impressive capabilities.
However, running these models often requires powerful GPUs,
which can be a barrier for many developers. LLM a Rust library developed
by the Rustformers GitHub organization is designed to run several
large language models on CPU, making these powerful tools more accessible than ever.
Before you will continue reading please watch short introduction:
Currently GGML a tensor library written in C that provides a foundation for machine learning applications
is used as a LLM backend.
GGML library uses a technique called model quantization.
Model quantization is a process that reduces the precision
of the numbers used in a machine learning model.
For instance, a model might use 32-bit floating-point numbers in its calculations.
Through quantization, these can be reduced to lower-precision formats,
such as 16-bit integers or even 8-bit integers.
The GGML library, which Rustformers is built upon, supports
a number of different quantization strategies.
These include 4-bit, 5-bit, and 8-bit quantization.
Each of these offers different trade-offs between efficiency and performance.
For instance, 4-bit quantization will be more efficient in terms of memory
and computational requirements, but it might lead to a larger decrease
in model performance compared to 8-bit quantization.
LLM supports a variety of large language models, including:
Bloom
GPT-2
GPT-J
GPT-NeoX
Llama
MPT
The models needs to be converted into form readable by GGML library
but thanks to the authors you can find ready to use models on huggingface.
To test it you can install llm-cli packge. Then you can chat with the model in the console.
cargo install llm-cli --git https://github.com/rustformers/llm
llm gptj infer -m ./gpt4all-j-q4_0-ggjt.bin -p"Rust is a cool programming language because"
To be able to talk with the model using http I have used actix server and built Rest API.
Api expose endpoint which returns response asyncronously.
The solution is acomplished with simple UI interface.
The world of artificial intelligence (AI) has seen significant advancements in recent years,
with OpenAI’s GPT-4 being one of the most groundbreaking language models to date.
However, harnessing the full potential of GPT-4 often requires high-end GPUs and
expensive hardware, making it inaccessible for many users. That’s where GPT-4All comes into play!
In this comprehensive guide, we’ll introduce you to GPT-4All, an optimized AI model
that runs smoothly on your laptop using just your CPU.
Before you will continue reading please watch short introduction:
GPT-4All was trained on a massive, curated corpus of assistant interactions,
covering a diverse range of tasks and scenarios.
This includes word problems, story descriptions, multi-turn dialogues, and even code.
At the first stage the authors collected one million prompt-response pairs using the GPT OpenAI
API. Then they have cleaned and curated the data using Atlas project.
Finally the released model was trained using Low-Rank Adaptation approach which reduce the number of trainable parameters
and required resources.
The authors have shared awesome library which automatially downloads the model and expose simple python API and additionally expose console
interface.
Delta lake is an open source storage framework for building lake house architectures
on top of data lakes.
Additionally it brings reliability to data lakes with features like:
ACID transactions, scalable metadata handling, schema enforcement, time travel and many more.
Before you will continue reading please watch short introduction:
Delta lake can be used with compute engines like Spark, Flink, Presto, Trino and Hive. It also
has API for Scala, Java, Rust , Ruby and Python.
To simplify integrations with delta lake I have built a REST API layer called Yummy Delta.
Which abstracts multiple delta lake tables providing operations like: creating new delta table,
writing and querying, but also optimizing and vacuuming.
I have coded an overall solution in rust based on the delta-rs project.
Delta lake keeps the data in parquet files which is an open source,
column-oriented data file format.
Additionally it writes the metadata in the transaction log,
json files containing information about all performed operations.
The transaction log is stored in the delta lake _delta_log subdirectory.
For example, every data write will create a new parquet file.
After data write is done a new transaction log file will be created which finishes the transaction.
Update and delete operations will be conducted in a similar way.
On the other hand when we read data from delta lake at the first stage transaction
files are read and then according to the transaction data appropriate parquet files are loaded.
Thanks to this mechanism the delta lake guarantees ACID transactions.
There are several delta lake integrations and one of them is delta-rs rust library.
To be able to manage multiple delta tables on multiple stores I have built Yummy delta server which expose Rest API.
Using API we can: list and create delta tables, inspect delta tables schema, append or override data in delta tables and additional operations like optimize or vacuum.
Realtime models deployment is a stage where performance is critical.
In this article I will show how to speedup MLflow
models serving and decrease resource consumption.
Additionally benchmark results will be presented.
Before you will continue reading please watch short introduction:
The Mlflow is opensource platform which covers end to end
machine learning lifecycle
Including: Tracking experiments, Organizing code into reusable projects,
Models versioning and finally models deployment.
With Mlflow we can easily serve versioned models.
Moreover it supports multiple ML frameworks and abstracts
them with consistent Rest API.
Thanks to this we can experiment with multiple models flavors
without affecting existing integration.
Mlflow is written in python and uses python to serve real-time models.
This simplifies the integration with ML frameworks which expose python API.
On the other hand real-time models serving is a stage where
prediction latency and resource consumption is critical.
Additionally serving robustness is required even for higher load.
To check how the rust implementation will perform I have implemented
the ML models server which can read Mlflow models and expose the same Rest API.
For test purposes I have implemented integration with LightGBM
and Catboost models flavors.
Where I have used Rust bindings to the native libraries.
I have used Vegeta attack to perform load tests and measure p99 response time for
a different number of requests per seconds.
Additionally I have measured the CPU and memory usage of the model serving container.
All tests have been performed on my local machine.
The performance tests show that rust implementation is very promising.
For all models even for 1000 requests per second the response time is low.
CPU usage increases linearly as traffic increases.
And memory usage is constant.
On the other hand Mlflow serving python implementation performs much worse and for higher traffic
the response times are higher than 5 seconds which exceeds timeout value.
CPU usage quickly consumes available machine resources.
The memory usage is stable for all cases.
The Rust implementation is wrapped with the python api and available in yummy.
Thus you can simply install and run it through the command line or using python code.
pip install yummy-mlflow
importyummy_mlflow# yummy_mlflow.model_serve(MODEL_PATH, HOST, POST, LOG_LEVEL)
yummy_mlflow.model_serve(model_path,'0.0.0.0',8080,'error')
We use cookies to ensure that we give you the best experience on our website. If you continue to use this site we will assume that you are happy with it.Ok
