# Phoenix

## Docs

- [Authentication](https://mintlify.wiki/Arize-ai/phoenix/api/authentication.md): API authentication methods for Phoenix
- [Datasets API](https://mintlify.wiki/Arize-ai/phoenix/api/datasets.md): API endpoints for managing datasets and examples
- [Evaluations API](https://mintlify.wiki/Arize-ai/phoenix/api/evaluations.md): API endpoints for submitting and retrieving evaluations
- [API Overview](https://mintlify.wiki/Arize-ai/phoenix/api/overview.md): REST API overview for Arize Phoenix
- [Traces API](https://mintlify.wiki/Arize-ai/phoenix/api/traces.md): API endpoints for managing traces and trace annotations
- [Creating Datasets](https://mintlify.wiki/Arize-ai/phoenix/datasets/creating-datasets.md): Learn how to create datasets from traces, uploads, and various data sources
- [Running Experiments](https://mintlify.wiki/Arize-ai/phoenix/datasets/experiments.md): Learn how to run experiments, track runs, compare results, and evaluate your AI applications
- [Datasets & Experiments Overview](https://mintlify.wiki/Arize-ai/phoenix/datasets/overview.md): Learn how datasets enable experimentation, evaluation, and fine-tuning in Phoenix
- [Dataset Versioning](https://mintlify.wiki/Arize-ai/phoenix/datasets/versioning.md): Learn how to manage dataset versions, tags, and exports in Phoenix
- [Deployment](https://mintlify.wiki/Arize-ai/phoenix/deployment.md): Deploy Phoenix for local development, production, or use Phoenix Cloud
- [API Key Management](https://mintlify.wiki/Arize-ai/phoenix/deployment/api-keys.md): Create and manage API keys for programmatic access to Phoenix
- [Authentication Setup](https://mintlify.wiki/Arize-ai/phoenix/deployment/authentication.md): Configure user management, SSO, and access control for Phoenix Cloud
- [Configuration Reference](https://mintlify.wiki/Arize-ai/phoenix/deployment/configuration.md): Complete reference for Phoenix environment variables and settings
- [Docker Deployment](https://mintlify.wiki/Arize-ai/phoenix/deployment/docker.md): Deploy Phoenix using Docker and Docker Compose
- [Kubernetes Deployment](https://mintlify.wiki/Arize-ai/phoenix/deployment/kubernetes.md): Deploy Phoenix on Kubernetes using Helm charts
- [Phoenix Cloud](https://mintlify.wiki/Arize-ai/phoenix/deployment/phoenix-cloud.md): Managed Phoenix hosting with enterprise features and security
- [Security Configuration](https://mintlify.wiki/Arize-ai/phoenix/deployment/security.md): Configure authentication, encryption, and network security for Phoenix
- [Batch Evaluation](https://mintlify.wiki/Arize-ai/phoenix/evaluation/batch-evaluation.md): Run evaluations at scale on datasets, traces, and experiments
- [Custom Evaluators](https://mintlify.wiki/Arize-ai/phoenix/evaluation/custom-evaluators.md): Create custom evaluation logic for your specific use cases
- [LLM-as-a-Judge](https://mintlify.wiki/Arize-ai/phoenix/evaluation/llm-as-judge.md): Use LLMs to evaluate model outputs with structured judgments
- [Evaluation Overview](https://mintlify.wiki/Arize-ai/phoenix/evaluation/overview.md): Learn how to evaluate LLM applications with Phoenix
- [Pre-built Metrics](https://mintlify.wiki/Arize-ai/phoenix/evaluation/pre-built-metrics.md): Ready-to-use evaluation metrics for common LLM tasks
- [Datasets](https://mintlify.wiki/Arize-ai/phoenix/features/datasets.md): Version-controlled datasets for experiments, evaluation, and fine-tuning with support for creating from production traces
- [Evaluation](https://mintlify.wiki/Arize-ai/phoenix/features/evaluation.md): LLM-as-a-judge evaluation with pre-built metrics and custom evaluators for systematic quality assessment
- [Experiments](https://mintlify.wiki/Arize-ai/phoenix/features/experiments.md): Systematic experiment tracking for testing prompts, models, and retrieval configurations with comprehensive comparison tools
- [Playground](https://mintlify.wiki/Arize-ai/phoenix/features/playground.md): Interactive playground for prompt optimization with model comparison, parameter tuning, and trace replay capabilities
- [Prompt Management](https://mintlify.wiki/Arize-ai/phoenix/features/prompt-management.md): Centralized prompt management with version control, tagging, and systematic testing for production LLM applications
- [Tracing](https://mintlify.wiki/Arize-ai/phoenix/features/tracing.md): OpenTelemetry-based tracing for LLM applications with automatic instrumentation and span hierarchy
- [Installation](https://mintlify.wiki/Arize-ai/phoenix/installation.md): Install Phoenix using pip, conda, Docker, or from source
- [Anthropic Integration](https://mintlify.wiki/Arize-ai/phoenix/integrations/anthropic.md): Instrument Anthropic Claude API calls with Phoenix for complete observability including streaming and tool use
- [LangChain Integration](https://mintlify.wiki/Arize-ai/phoenix/integrations/langchain.md): Auto-instrument LangChain applications in Python and JavaScript for complete observability of chains, agents, and retrievers
- [LlamaIndex Integration](https://mintlify.wiki/Arize-ai/phoenix/integrations/llamaindex.md): Auto-instrument LlamaIndex applications for complete observability of queries, retrievals, and agent workflows
- [OpenAI Integration](https://mintlify.wiki/Arize-ai/phoenix/integrations/openai.md): Auto-instrument OpenAI SDK calls with Phoenix for complete observability of GPT models, embeddings, and function calling
- [OpenTelemetry Integration](https://mintlify.wiki/Arize-ai/phoenix/integrations/opentelemetry.md): Use OpenTelemetry primitives to build custom instrumentation for your LLM applications
- [Integrations Overview](https://mintlify.wiki/Arize-ai/phoenix/integrations/overview.md): Phoenix integrates with popular LLM frameworks and providers through OpenTelemetry-based instrumentation
- [Introduction to Phoenix](https://mintlify.wiki/Arize-ai/phoenix/introduction.md): Open-source AI observability platform for experimentation, evaluation, and troubleshooting
- [Quickstart](https://mintlify.wiki/Arize-ai/phoenix/quickstart.md): Get Phoenix up and running in 5 minutes
- [Python Client Reference](https://mintlify.wiki/Arize-ai/phoenix/sdk/python/client.md): Complete reference for the Phoenix Python client library
- [Python Evals Reference](https://mintlify.wiki/Arize-ai/phoenix/sdk/python/evals.md): Complete reference for Phoenix evaluation framework
- [Python OTEL Reference](https://mintlify.wiki/Arize-ai/phoenix/sdk/python/otel.md): Complete reference for Phoenix OpenTelemetry integration
- [Python SDK Overview](https://mintlify.wiki/Arize-ai/phoenix/sdk/python/overview.md): Overview of the Phoenix Python SDK packages and components
- [TypeScript Client Reference](https://mintlify.wiki/Arize-ai/phoenix/sdk/typescript/client.md): Complete reference for the Phoenix TypeScript client library
- [TypeScript Evals Reference](https://mintlify.wiki/Arize-ai/phoenix/sdk/typescript/evals.md): Complete reference for Phoenix evaluation framework in TypeScript/JavaScript
- [TypeScript OTEL Reference](https://mintlify.wiki/Arize-ai/phoenix/sdk/typescript/otel.md): Complete reference for Phoenix OpenTelemetry integration in TypeScript/JavaScript
- [TypeScript SDK Overview](https://mintlify.wiki/Arize-ai/phoenix/sdk/typescript/overview.md): Overview of the Phoenix TypeScript/JavaScript SDK packages
- [Annotations](https://mintlify.wiki/Arize-ai/phoenix/tracing/annotations.md): Add human feedback and automated evaluations to traces
- [Cost Tracking](https://mintlify.wiki/Arize-ai/phoenix/tracing/cost-tracking.md): Monitor and analyze LLM costs across providers
- [Instrumentation](https://mintlify.wiki/Arize-ai/phoenix/tracing/instrumentation.md): Instrument your LLM applications to send traces to Phoenix
- [Tracing Overview](https://mintlify.wiki/Arize-ai/phoenix/tracing/overview.md): Understand distributed tracing in Phoenix with OpenTelemetry and OpenInference
- [Projects](https://mintlify.wiki/Arize-ai/phoenix/tracing/projects.md): Organize and isolate traces using projects in Phoenix
- [Sessions](https://mintlify.wiki/Arize-ai/phoenix/tracing/sessions.md): Group related traces into sessions for better analysis and debugging