arize-phoenix

938 posts

arize-phoenix

@ArizePhoenix

Open-Source AI Observability and Evaluation

Notebook or Container

github.com/Arize-ai/phoen…

Joined February 2023

arize-phoenix
@ArizePhoenix
Aug 7
4 instrumentors shipped today thanks to our cracked OSS community. 🤖 AG2: multi-agent conversations, group chats, and tool calls ⚡ Together AI: fast inference across OSS models 🧠 Cohere: enterprise chat, search, and RAG 🦙 Ollama: local models galore
arize.com
Integrations - Phoenix
Connect Phoenix with your favorite AI frameworks, LLM providers, and tools
arize-phoenix
@ArizePhoenix
Aug 4
AI Queries and Browser AI Phoenix filters now understand English. Type "responses with apologies" and get a real filter expression back: ▎ 'sorry' in output.value or 'apolog' in output.value
00:00
arize-phoenix
@ArizePhoenix
Aug 3
The experiment said the fix works, but experiments aren't production. Trace → dataset → evaluator → experiment → verify in production. PXI helps you every step of the way!
00:00
arize-phoenix
@ArizePhoenix
Aug 1
Balancing cost, speed, and correctness can be a tricky balance. That's why we need good visuals to figure out the right sweet spot!
00:00
arize-phoenix
@ArizePhoenix
Jul 30
Customizable visualizations of your agent traces are here. Track cache hits, online eval degradations, tool call errors, all in real-time so you can quickly identify problems in production. What does your agent operations center look like?
00:00