Features
Unified search across multiple data sources
Real-time incremental syncing
SDKs for Python and Node.js
Collection-based knowledge base management
Source connection management with authentication
Semantic search with temporal relevance scoring
LLM-friendly context retrieval via REST API
Open-source self-hosting option
Structured and unstructured data support
Developer-focused documentation and quickstart
Trace visibility for agent steps (prompts, retrievals, tool calls, outputs)
LLM-as-judge evaluation for relevance, toxicity, quality scoring
Dataset creation from traces for reproducible testing
Experiment management and regression benchmarking
Built-in Prompt IDE for iterative prompt optimization
Self-hosted deployment on local, Docker, Kubernetes
Phoenix Cloud managed hosting option
Vendor-agnostic support for any model/framework
Native OpenTelemetry integration
OpenInference specification for LLM telemetry
Human annotation and automated labeling
Ghost trajectories to simulate alternative agent paths
Eval-as-you-test for early quality feedback
One-click integration with LlamaIndex
