“Complex production tracing and evaluation: LangSmith.”
+ tracing, datasets, experiment tracking
“LangSmith | Tracing, datasets, experiment tracking”
“Langfuse Production tracing and evaluation observability”
+ production tracing and evaluation observability
“Langfuse Production tracing and evaluation observability”
“General-purpose LLM applications: DeepEval.”
+ LLM unit testing and CI integration
“DeepEval | LLM unit testing and CI integration”
+ pytest integration
“DeepEval integrates with pytest, so failing evaluation metrics can fail the test run.”
“RAG applications: Ragas.”
+ RAG evaluation
“Ragas | RAG evaluation”
“Prompt engineering and model comparisons: promptfoo.”
+ prompt testing, model comparisons, red teaming
“promptfoo | Prompt testing, model comparisons, red teaming”
“GitHub Actions CI/CD orchestration and merge protection”
+ CI/CD orchestration and merge protection
“GitHub Actions CI/CD orchestration and merge protection”
“Here's a practical architecture you can implement with GitHub Actions, GitLab CI, or Jenkins.”
“Here's a practical architecture you can implement with GitHub Actions, GitLab CI, or Jenkins.”
“OpenAI Evals | Custom model evaluation workflows”
“pytest Test execution and failure reporting”
+ test execution and failure reporting
“pytest Test execution and failure reporting”