My 𝗢𝗽𝗲𝗻 𝗦𝗼𝘂𝗿𝗰𝗲 implementation of 𝗗𝗲𝗲𝗽 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗔𝗴𝗲𝗻𝘁 from scratch 👇

I have released the latest episode of my Newsletter and an update to my AI Engineers Handbook GitHub repository.

Walkthrough Blog: www.newsletter.swirlai.com/p/building-d...

Link to GitHub inside

#LLM #AI #MachineLearning

My 𝗢𝗽𝗲𝗻 𝗦𝗼𝘂𝗿𝗰𝗲 implementation of 𝗗𝗲𝗲𝗽 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗔𝗴𝗲𝗻𝘁 from scratch 👇

I have released the latest episode of my Newsletter and an update to my AI Engineers Handbook GitHub repository.

Walkthrough Blog: www.newsletter.swirlai.com/p/building-d...

Link to GitHub inside

#LLM #AI #MachineLearning

This is just the first part of the series. The ipynb or python code, runs an agent class that when asked will decide if a regular non-augmented answer should be returned or a tool that we define in the code should be used to get the right answer.

Last week I released the first article in my hands-on 𝗕𝘂𝗶𝗹𝗱𝗶𝗻𝗴 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁𝘀 𝗙𝗿𝗼𝗺 𝗦𝗰𝗿𝗮𝘁𝗰𝗵 series. It covers the tool use element of an Agent.

I wanted to do this for quite some time now and finally the time has arrived!

The article: www.newsletter.swirlai.com/p/building-a...

#LLM #AI #ML

👇

You can also find a Jupyter notebook and python scripts that complement the article in a GitHub repo (links in the article).

Youtube videos coming soon!If you’re looking for something to dig your hands into between holidays be sure to take a look!

➡️ How to think about constructing effective system prompts that can be used for Agents.
➡️ How to build an Agent class that is able to plan and execute actions using provided Tools.

👇

After finishing the project you will learn:

➡️ What AI Agents are.
➡️ How the Tool usage in AI Agents actually works.
➡️ How to build a decorator wrapper that extracts relevant details from a Python function to be passed to the LLM via system prompt.

👇

If you are using any orchestration frameworks for agentic applications, you might be abstracted away from what using a tool really means. I believe that understanding applications from the base building blocks is really important so we are implementing all of the abstractions from scratch.

👇

Last week I released the first article in my hands-on 𝗕𝘂𝗶𝗹𝗱𝗶𝗻𝗴 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁𝘀 𝗙𝗿𝗼𝗺 𝗦𝗰𝗿𝗮𝘁𝗰𝗵 series. It covers the tool use element of an Agent.

I wanted to do this for quite some time now and finally the time has arrived!

The article: www.newsletter.swirlai.com/p/building-a...

#LLM #AI #ML

👇

If you want to start learning Kubernetes, look no further 👇

Some time ago I created a 2 part series on the main concepts you should know when working with K8s. Examples and walkthroughs included!

Link to the article: www.newsletter.swirlai.com/p/a-guide-to...

#AI #MachineLearning #Kubernetes

Since I have resumed the newsletter, there will be many hands-on AI projects utilising Kubernetes for deployment. Be sure to sharpen your skills if you intend to follow! This resource is perfect for that.

In the two articles you will learn:

➡️ Why Kubernetes for AI and Data Engineering.
➡️ General Kubernetes Resources for application configuration.
➡️ How to deploy applications.
➡️ Different ways to deploy applications and when to use which.
➡️ Visual explanation for all of the above.

👇

If you want to start learning Kubernetes, look no further 👇

Some time ago I created a 2 part series on the main concepts you should know when working with K8s. Examples and walkthroughs included!

Link to the article: www.newsletter.swirlai.com/p/a-guide-to...

#AI #MachineLearning #Kubernetes

What is 𝗖𝗼𝗻𝘁𝗶𝗻𝘂𝗼𝘂𝘀 𝗧𝗿𝗮𝗶𝗻𝗶𝗻𝗴 (𝗖𝗧) in MLOps and what steps are needed to achieve it?

CT is the process of automated ML Model retraining in Production Environments on a specific trigger. Let’s look into some prerequisites for this:

👇

#LLM #MachineLearning #AI

- The need for Feature Store will wary on the types of Models you are deploying. I would prioritise it if you have Models that perform Online predictions as it will help with avoiding Training/Serving Skew.
- Don’t rush with Automated retraining. Ad-hoc and on-schedule will bring you a long way.

- Orchestration of ML Pipelines is always a good idea, there are many tools supporting this (Airflow, Kubeflow, VertexAI etc.). If you are not doing it yet - grab this next, also make the validation steps part of this goal.

👇

𝗠𝘆 𝘁𝗵𝗼𝘂𝗴𝗵𝘁𝘀 𝗼𝗻 𝗖𝗧:

➡️ Introduction of CT is not straightforward and you should approach it iteratively. The following could be good Quarterly Goals to set:

- Experiment Tracking is extremely important at any level of ML Maturity and the least invasive in the process of ML Model training.

👇

5) Introduction of Feature Store (Optional).

- Avoid work duplication when defining features.
- Reduce risk of Training/Serving Skew.

👇

4) Different Pipeline triggers in production.

- Ad-hoc.
- Cron.
- Reactive to Metrics produced in Model Monitoring System.
- Arrival of New Data.

✅ This is where the Continuous Training is actually triggered.

👇

3) Introduction of ML Metadata Store.

- Any Metadata related to ML artifact creation is tracked here.
- We also track performance of the ML Model.

✅ Experiments become reproducible and comparable between each other.
✅ Model Registry acts as glue between training and deployment pipelines.

👇

✅ Short circuits of the Pipeline allow for safe CT in production.

👇

2) Introduction of strict Data and Model Validation steps in the ML Pipeline.

- Data is validated before training the Model. If inconsistencies are found - Pipeline is aborted.
- Model is validated after training. Only after it passes the validation is it handed over for deployment.

👇

✅ You deploy Pipelines instead of Model Artifacts allowing Continuous Training In production.
✅ Reuse of components allows for rapid experimentation.

👇

1) Automation of ML Pipelines.

- Pipelines are orchestrated.
- Each pipeline step is developed independently and is able to run on different technology stacks.
- Pipelines are treated as a code artifact.

👇

What is 𝗖𝗼𝗻𝘁𝗶𝗻𝘂𝗼𝘂𝘀 𝗧𝗿𝗮𝗶𝗻𝗶𝗻𝗴 (𝗖𝗧) in MLOps and what steps are needed to achieve it?

CT is the process of automated ML Model retraining in Production Environments on a specific trigger. Let’s look into some prerequisites for this:

👇

#LLM #MachineLearning #AI

And let’s not forget the less popular part:

𝘏) Observing, Evaluating, Monitoring and Securing your application in production!

What other pieces of the system am I missing? Let me know in the comments 👇

#LLM #AI #MachineLearning

𝘉 ) Prompt Engineering - having context available for usage in your prompts does not free you from the hard work of engineering the prompts. You will still need to align the system to produce outputs that you desire and prevent jailbreak scenarios.

👇

𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻:

𝘈 ) LLM - Choosing the right Large Language Model to power your application.

✅ It is becoming less of a headache the further we are into the LLM craze. The performance of available LLMs are converging, both open source and proprietary.

👇

𝘎 ) Heuristics - business rules applied to your retrieval procedure.

- Time importance.
- Reranking.
- Duplicate context (diversity ranking).
- Source retrieval.
- Conditional document preprocessing.

👇

𝘌 ) Vector Search

- Choice of similarity measure.
- Choosing the query path - metadata first vs. ANN first.
- Hybrid search.

👇