Phoenix is an open-source AI observability platform designed for experimentation, evaluation, and troubleshooting. It provides:
- Tracing - Trace your LLM application's runtime using OpenTelemetry-based instrumentation.
- Evaluation - Leverage LLMs to benchmark your application's performance using response and retrieval evals.
- Datasets - Create versioned datasets of examples for experimentation, evaluation, and fine-tuning.
- Experiments - Track and evaluate changes to prompts, LLMs, and retrieval.
Phoenix is vendor and language agnostic with out-of-the-box support for popular frameworks (π¦LlamaIndex, π¦βLangChain, Haystack, π§©DSPy) and LLM providers (OpenAI, Bedrock, MistralAI, VertexAI, LiteLLM, and more). For details on auto-instrumentation, check out the OpenInference project.
Phoenix runs practically anywhere, including your Jupyter notebook, local machine, containerized deployment, or in the cloud.
Installation
Install Phoenix via pip or conda
pip install arize-phoenixPhoenix container images are available via Docker Hub and can be deployed using Docker or Kubernetes.
Features
| Key Features | Availability |
|---|---|
| Tracing | β |
| Evaluation | β |
| Retrieval (RAG) Analysis | β |
| Datasets | β |
| Fine-Tuning Export | β |
| Annotations | β |
| Human Feedback | β |
| Experiments | β |
| Embeddings Analysis | β |
| Data Export | β |
| REST API | β |
| GraphQL API | β |
| Data Retention | Customizable |
| Authentication | β |
| Social Login | β |
| RBAC | β |
| Projects | β |
| Self-Hosting | β |
| Jupyter Notebooks | β |
| Sessions | In Progress π§ |
| Prompt Playground | In Progress π§ |
| Prompt Management | Coming soon β±οΈ |
Tracing Integrations
Phoenix is built on top of OpenTelemetry and is vendor, language, and framework agnostic.
| Python | Integration | Package | Version Badge |
|---|---|---|---|
| OpenAI | openinference-instrumentation-openai |
 |
|
| LlamaIndex | openinference-instrumentation-llama-index |
 |
|
| DSPy | openinference-instrumentation-dspy |
 |
|
| AWS Bedrock | openinference-instrumentation-bedrock |
 |
|
| LangChain | openinference-instrumentation-langchain |
 |
|
| MistralAI | openinference-instrumentation-mistralai |
 |
|
| Guardrails | openinference-instrumentation-guardrails |
 |
|
| VertexAI | openinference-instrumentation-vertexai |
 |
|
| CrewAI | openinference-instrumentation-crewai |
 |
|
| Haystack | openinference-instrumentation-haystack |
 |
|
| LiteLLM | openinference-instrumentation-litellm |
 |
|
| Groq | openinference-instrumentation-groq |
 |
|
| Instructor | openinference-instrumentation-instructor |
 |
|
| Anthropic | openinference-instrumentation-anthropic |
 |
JavaScript
| Integration | Package | Version Badge |
|---|---|---|
| OpenAI | @arizeai/openinference-instrumentation-openai |
 |
| LangChain.js | @arizeai/openinference-instrumentation-langchain |
 |
| Vercel AI SDK | @arizeai/openinference-vercel |
 |
For details about tracing integrations and example applications, see the OpenInference project.
Community
Join our community to connect with thousands of AI builders.
- π Join our Slack community.
- π Read our documentation.
- π‘ Ask questions and provide feedback in the #phoenix-support channel.
- π Leave a star on our GitHub.
- π Report bugs with GitHub Issues.
- π Follow us on π.
- ποΈ Sign up for our mailing list.
- πΊοΈ Check out our roadmap to see where we're heading next.
Breaking Changes
See the migration guide for a list of breaking changes.
Copyright, Patent, and License
Copyright 2024 Arize AI, Inc. All Rights Reserved.
Portions of this code are patent protected by one or more U.S. Patents. See IP_NOTICE.
This software is licensed under the terms of the Elastic License 2.0 (ELv2). See LICENSE.