Resources
Table of Contents
Most of what I’ve learned during my career has been through on-the-job learning or self-study. The internet has a wealth of valuable content, one just needs to know where to find it.
Here I’ve collected the resources to which I refer the most.
Data analysis
Packages:
Data engineering
Documentation:
- dbt’s best practices
- GoogleSQL reference for BigQuery
Machine learning/AI
Courses:
- Azure AI Fundamentals
- Azure AI Engineer
- Machine Learning Engineer learning path with Google Cloud
Documentation:
Packages:
- scikit-learn for machine learning
- TensorFlow for machine learning and deep learning
LLMs
Articles:
- 58 prompting techniques by Jason Liu.
- What We’ve Learned From A Year of Building with LLMs – A practical guide to building successful LLM products (Yan et al.).
Blogs:
- AI Snake Oil – What artificial intelligence can do, what it can’t, and how to tell the difference (Narayanan & Kapoor).
Packages:
- DSPy for optimizing LLM prompts.
- Instructor for structuring LLM output.
- LangChain for developing LLM-powered applications.
- Langfuse for monitoring and evaluating LLM-powered applications.
- LangSmith for monitoring and evaluating LLM-powered applications.
- Semantic Kernel is Microsoft’s LLM SDK.
Sites:
- The Prompt engineering guide introduces prompt engineering and goes into depth on various techniques.
Tools:
- Pinecone is a vector database, it also has a lot of great courses about building LLM-powered apps.
- Weaviate is a vector database.
Python
Packages: