DEV Community

The Modern Data Engineering AI Roadmap: Mastering the Fundamentals That Drive ROI Series' Articles

Back to Vinicius Fagundes's Series
Temperature, Tokens, and Context Windows: The Three Pillars of LLM Control
qvfagundes profile

Temperature, Tokens, and Context Windows: The Three Pillars of LLM Control

#ai #dataengineering #data #product
2
Comments
13 min read
Transformers and Attention: How LLMs Actually Process Text
qvfagundes profile

Transformers and Attention: How LLMs Actually Process Text

#ai #architecture #llm #deeplearning
5
Comments
19 min read
Embeddings and Vector Similarity: How Machines Understand Meaning
qvfagundes profile

Embeddings and Vector Similarity: How Machines Understand Meaning

#ai #datascience #dataengineering #llm
1
Comments
19 min read
Positional Encodings and Context Window Engineering: Why Token Order Matters
qvfagundes profile

Positional Encodings and Context Window Engineering: Why Token Order Matters

#dataengineering #ai #software
3
Comments
12 min read
Function Calling and Tool Use: Turning LLMs into Action-Taking Agents
qvfagundes profile

Function Calling and Tool Use: Turning LLMs into Action-Taking Agents

#ai #llm #mcp #dataengineering
Comments
18 min read
Prompt Engineering Patterns: From Zero-Shot to Chain-of-Thought Reasoning
qvfagundes profile

Prompt Engineering Patterns: From Zero-Shot to Chain-of-Thought Reasoning

#ai #mcp #llm #dataengineering
1
Comments
14 min read
Retrieval-Augmented Generation: Connecting LLMs to Your Data
qvfagundes profile

Retrieval-Augmented Generation: Connecting LLMs to Your Data

#ai #datascience #llm #rag
Comments
10 min read
Chunking Strategies: The Art of Slicing Documents for Optimal RAG Performance
qvfagundes profile

Chunking Strategies: The Art of Slicing Documents for Optimal RAG Performance

#ai #llm #data
Comments
10 min read
Dense vs Sparse Retrieval: Mastering FAISS, BM25, and Hybrid Search
qvfagundes profile

Dense vs Sparse Retrieval: Mastering FAISS, BM25, and Hybrid Search

#ai #llm #vectordatabase
1
Comments
15 min read
Reranking and Two-Stage Retrieval: Precision When It Matters Most
qvfagundes profile

Reranking and Two-Stage Retrieval: Precision When It Matters Most

#ai #llm #rag
Comments
2 min read
Multi-Step Reasoning and Agentic Workflows: Building AI That Plans and Executes
qvfagundes profile

Multi-Step Reasoning and Agentic Workflows: Building AI That Plans and Executes

#ai #rag #programming #webdev
Comments
16 min read
Human-in-the-Loop Systems: Building AI That Knows When to Ask for Help
qvfagundes profile

Human-in-the-Loop Systems: Building AI That Knows When to Ask for Help

#ai #rag #programming #data
Comments
17 min read
RAG Evaluation Metrics: Measuring What Actually Matters
qvfagundes profile

RAG Evaluation Metrics: Measuring What Actually Matters

#llm #rag #dataengineering #ai
1
Comments
10 min read