🔌 Platform Integrations
Integrations
Connect your evaluation platform with leading observability tools, LLM providers, frameworks, and alerting systems. Seamlessly integrate LangFuse, Arize, and other platforms to build comprehensive AI evaluation pipelines.
Featured Observability Platforms
LF
ConfiguredLangFuse
Open-source LLM observability and tracing platform with comprehensive evaluation capabilities
Trace ManagementCost TrackingA/B ExperimentsScore Attribution
AX
ConfiguredArize AX Enterprise
Full enterprise SaaS platform for LLM observability and evaluation with multi-cloud support
Advanced TracingSession EvaluationAgent Workflow GraphsLLM-as-Judge Templates
PX
AvailableArize Phoenix
Open-source LLM tracing and evaluation platform built on OpenTelemetry for total visibility, prompt playground, and streamlined evaluations
OpenTelemetry TracingInteractive Prompt PlaygroundStreamlined EvaluationsDataset Clustering
LLM Providers
AI
ConfiguredOpenAI
GPT-4, GPT-3.5, and other OpenAI models for LLM-as-judge and agent capabilities
GPT-4GPT-3.5-turboEmbeddings
AC
Anthropic Claude
High-quality reasoning and safety-focused LLM for evaluation judging
Claude 3Advanced ReasoningLong Context
GV
Google Vertex AI
Gemini models with multimodal capabilities for comprehensive evaluation
Gemini ProMultimodal AnalysisCode Understanding
AB
AWS Bedrock
Access to multiple foundation models through AWS managed service
ClaudeLlama 2Titan
Frameworks
LC
ConfiguredLangChain
Modular framework for building LLM applications with chains, agents, and evaluators
Chain CompositionAgent FrameworksDocument Loaders
LG
ConfiguredLangGraph
Stateful agent orchestration framework with graph-based workflows
Graph WorkflowsState ManagementCheckpointing
LI
ConfiguredLlamaIndex
Data framework for connecting custom data sources to LLMs with built-in evaluators
Semantic ParsingRetrieversEvaluators
Alerting
PD
PagerDuty
Incident response and alerting for evaluation threshold breaches
Incident ResponseOn-Call ManagementAlerting
OG
Opsgenie
On-call management and alerting for production evaluation systems
On-Call ManagementAlert RoutingIncident Response
SL
ConfiguredSlack
Real-time notifications for evaluation results and threshold breaches
Channel NotificationsDirect MessagesRich Formatting
Phoenix Integration Examples
Arize Phoenix Integration Examples
Explore comprehensive integration examples for Phoenix, organized by complexity level. From simple SDK integrations to complex multi-agent systems.
Beginner Integrations
BeginnerSimple SDK and framework integrations with Phoenix for LLM observability
Agno
Agno agent examples
OpenAI SDK
OpenAI Python SDK, including chat completions and embeddings
MistralAI SDK
MistralAI Python SDK
VertexAI SDK
VertexAI Python SDK
LlamaIndex
LlamaIndex query engines
DSPy
DSPy primitives and custom RAG modules
Boto3 Bedrock Client
Boto3 Bedrock client
LangChain
LangChain primitives and simple chains
LiteLLM
A lightweight LiteLLM framework
LiteLLM Proxy
LiteLLM Proxy to log OpenAI, Azure, Vertex, Bedrock
Groq
Groq and AsyncGroq chat completions
Anthropic
Anthropic Messages client
BeeAI
Agentic instrumentation in the BeeAI framework
Intermediate Integrations
IntermediateAdvanced integration examples with full applications and multi-component systems
LlamaIndex + Next.js Chatbot
A fully functional chatbot using Next.js and a LlamaIndex FastAPI backend
LangServe
A LangChain application deployed with LangServe using custom metadata on a per-request basis
DSPy
A DSPy RAG application using FastAPI, Weaviate, and Cohere
Haystack
A Haystack QA RAG application
OpenAI Agents
OpenAI Agents with handoffs
Autogen AgentChat
Microsoft Autogen Assistant Agent and Team Chat
PydanticAI
PydanticAI agent examples
Ready to Integrate?
Start building your evaluation pipeline with LangFuse and Arize. Explore our implementation guides and get started today.