Python

Phoenix

Trace, evaluate and debug LLM apps

by Arize-ai · Elastic-2.0

pip install arize-phoenix
phoenix serve

What is Phoenix?

Phoenix from Arize traces LLM applications, surfaces failure clusters and runs evaluations, all runnable locally in a notebook or as a server.

Why people choose Phoenix

• Runs locally, even in a notebook
• Clusters failures to find patterns
• Built-in LLM evaluators

Phoenix at a glance

Open-source alternatives to Phoenix

Other open-source llm / rag framework tools worth comparing:

LangChainCompose chains, tools and agentsLlamaIndexThe data framework for RAGHaystackProduction pipelines for search and RAGDSPyProgram — not prompt — language modelstxtaiAll-in-one embeddings databaseRAGFlowDeep-document-understanding RAGSemantic KernelMicrosoft's enterprise agent frameworkGraphRAGRAG that builds a knowledge graph firstLiteLLMOne API for 100+ LLM providersInstructorReliable structured outputs from LLMsOutlinesGuarantee valid JSON and grammarsGuidanceInterleave control and generationLLMWareEnterprise RAG with small specialised modelsFlashRankUltra-light reranking for better RAGSentence TransformersThe standard way to make embeddingsRagasMeasure whether your RAG is any goodPromptfooUnit tests for your promptsLangfuseSee what your LLM app actually did

Phoenix head-to-head

FAQ