Implement semantic caching to avoid redundant LLM calls and reduce API costs.
Tag: ml
Tips and Tricks – Implement Prompt Templates for Consistent LLM Output
Use structured prompt templates to get reliable, formatted responses from LLMs.
Tips and Tricks – Use Embeddings for Semantic Search
Implement semantic search using text embeddings for more relevant results than keyword matching.
Tips and Tricks – Use dbt for Maintainable Data Transformations
Build modular, tested, documented data transformations with dbt.
Tips and Tricks – Use CQRS for Complex Domain Logic
Separate read and write operations for better scalability and simpler code.
Tips and Tricks – Use ValueTask for Hot Async Paths
Replace Task with ValueTask in frequently-called async methods that often complete synchronously.
Tips and Tricks – Implement Retry Logic for LLM API Calls
Handle rate limits and transient failures gracefully with exponential backoff.
Tips and Tricks – Implement Idempotent ETL with Merge Statements
Use MERGE (upsert) for safe, rerunnable data pipelines that handle duplicates gracefully.
Tips and Tricks – Implement Domain Events for Loose Coupling
Use domain events to decouple components and enable reactive architectures.