llm agents rag ai agent-loop

The seven layers under your LLM agent

Tracing the LLM agent stack back to the model API call to show where the seams are, from completion and chat templating to structured output, instruction-tuning, RAG, the agent loop, and the frameworks that grew on top of it.

Read More

Kafka KRaft on macOS without Docker

Running docker on apple silicon is still somehow a struggle, here are some notes about how to set native kafka with KRaft on macos docker-free and suitable for development.

Read More

Running t5x on macos

Background If you are in language model space, you cannot avoid 🤗 transformers and other libraries from that ecosystem. From my experience, those libraries are top-quality, they provide invaluable service to the community, and the whole 🤗 story is a great example of how open-source has to be. Also, if you are into reading source...

Read More

A weekend of ops'ing (a rant)

Some wrap up of experience of past two days. I tried to automate deployment of kubeflow on to a self-built kubernetes cluster with ansible. 5/7 experience with partial success so far. I generally like the idea of kubeflow, which on contrary to Sagemaker lets me work and test small things out while not being constantly...

Read More

Things to consider while doing a linear regression

Main assumptions Validity Additivity Linearity Independence and equal variance of errors (we’re talking about OLS) Normality of errors (might not be present, but its distribution has to be understood) Checklist before modeling Distribution of the target variable Distributions and correlations between exogenous variables

Read More