_d
devops/ness
Blog
Reading ListAbout
Subscribe

Blog

Practical articles on AI, DevOps, Cloud, Linux, and infrastructure engineering.

Tag: #gptClear filters
Real-World RAG Incidents: Lessons from a Production Rollout
••6 months ago

Real-World RAG Incidents: Lessons from a Production Rollout

A field report from rolling out retrieval-augmented generation in production, including cache bugs, bad embeddings, and how we fixed them.

KU
Kiril urbonas
Read article
Real-World RAG Incidents: Lessons from a Production Rollout
••6 months ago

Real-World RAG Incidents: Lessons from a Production Rollout

A field report from rolling out retrieval-augmented generation in production, including cache bugs, bad embeddings, and how we fixed them.

KU
Kiril urbonas
Read article
Architecture Review: LLM Gateway Design for Multi-Provider Inference
••6 months ago

Architecture Review: LLM Gateway Design for Multi-Provider Inference

LLM Gateway Design for Multi-Provider Inference. Practical guidance for reliable, scalable platform operations.

KU
Kiril Urbonas
Read article
Real-World RAG Incidents: Lessons from a Production Rollout
••6 months ago

Real-World RAG Incidents: Lessons from a Production Rollout

A field report from rolling out retrieval-augmented generation in production, including cache bugs, bad embeddings, and how we fixed them.

KU
Kiril urbonas
Read article
Embedding Models Comparison: Choosing the Right Model for Your Use Case
••6 months ago

Embedding Models Comparison: Choosing the Right Model for Your Use Case

Compare popular embedding models including OpenAI, Sentence-BERT, and open-source alternatives. Learn which model fits your RAG, search, or similarity tasks.

KU
Kiril Urbonas
Read article
AI Cost Optimization: Reducing LLM Inference Costs by 80%
••7 months ago

AI Cost Optimization: Reducing LLM Inference Costs by 80%

Learn proven strategies to reduce AI inference costs including model quantization, caching, batching, and efficient prompt design. Real-world cost savings examples.

KU
Kiril Urbonas
Read article
Fine-tuning vs Few-Shot Learning: When to Use Each Approach
••7 months ago

Fine-tuning vs Few-Shot Learning: When to Use Each Approach

Compare fine-tuning and few-shot learning for adapting LLMs. Learn when to use each approach and their trade-offs in terms of cost, performance, and complexity.

KU
Kiril Urbonas
Read article
Real-World RAG Incidents: Lessons from a Production Rollout
••7 months ago

Real-World RAG Incidents: Lessons from a Production Rollout

A field report from rolling out retrieval-augmented generation in production, including cache bugs, bad embeddings, and how we fixed them.

KU
Kiril urbonas
Read article
Multi-Agent AI Systems: Building Collaborative AI Applications
••7 months ago

Multi-Agent AI Systems: Building Collaborative AI Applications

Learn how to build multi-agent AI systems where multiple AI agents collaborate to solve complex tasks. Architecture patterns and implementation guide.

KU
Kiril Urbonas
Read article
Real-World RAG Incidents: Lessons from a Production Rollout
••7 months ago

Real-World RAG Incidents: Lessons from a Production Rollout

A field report from rolling out retrieval-augmented generation in production, including cache bugs, bad embeddings, and how we fixed them.

KU
Kiril urbonas
Read article
Model Quantization Techniques: Reducing LLM Size and Cost
••7 months ago

Model Quantization Techniques: Reducing LLM Size and Cost

Learn how to reduce LLM model size and inference costs using quantization techniques like Q4, Q8, and GPTQ. Practical guide with benchmarks.

KU
Kiril Urbonas
Read article
Real-World RAG Incidents: Lessons from a Production Rollout
••7 months ago

Real-World RAG Incidents: Lessons from a Production Rollout

A field report from rolling out retrieval-augmented generation in production, including cache bugs, bad embeddings, and how we fixed them.

KU
Kiril urbonas
Read article
Page 3 of 6 · 71 posts
Previous
1234...6
Next