Mikyo King

Right now if you use `using_project` via: ``` from phoenix.trace import using_project with using_project("foo"): chain.invoke() # works px.Client().log_evaluations() # falls back to the non-context specific project ```

Use-cases for more complex RAG include - Multiple Retrievers - Re-rankers - Hybrid search @mikeldking - knowledge Graph - Multi-modal - Forward RAG / Hyde

- [ ] Move to vite - [ ] #2580 - [ ] #2579

[ENHANCEMENT] Move to Pytest 8

2

WISITT

[BUG] LlamaIndex Tracing for llama.cpp advertised as gpt3.5 turbo

5

Question 1: Our LLM is always erroneously called “gpt-3.5-turbo” as the model name in the Phoenix trace. Is there a parameter we can override to change it to an arbitrary...

[Feature Request]: Support metadata on queryEngine, invocations - make them available to the callback system

1

### Feature Description As a user of LlamaIndex in a production setting, I may want to tag or add metadata to a queryEngine or invocation. E.x. I have a queryEngine...

feat(datasets): datasets page

1

resolves #3165