burr
burr copied to clipboard
Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.
**Is your feature request related to a problem? Please describe.** There are some inputs that everyone might want. Tracers, etc... We should be able to inject it. **Describe the solution...
**Is your feature request related to a problem? Please describe.** We should be able to handle iteractions such as step/iterate/run/stream). These would be hooks called before and after user-facing stuff....
**Is your feature request related to a problem? Please describe.** The graphviz viz could be styled better. **Describe the solution you'd like** Something that looks nice like https://github.com/dagworks-inc/hamilton 's output....
[Short description explaining the high-level reason for the pull request] api.localhost will direct to api on port 7242 and telemetry.localhost will open the Burr UI ## Changes - add Docker...
For getting typed-state up to parity with standard state. Currently a list but these should be individual issues. Please comment with more! - [ ] Documentation on differences between using...
I'm building an application with `burr.integrations.pydantic` and building the graph + application fails. The following error message isn't helpful because it exposes internal implementation (i.e., the key `"state"` is nowhere...
[Short description explaining the high-level reason for the pull request] ## Changes ## How I tested this ## Notes ## Checklist - [ ] PR has an informative and human-readable...
Allows to load traces from tracked Burr application with OpenLLMetry traces. You can load previous chat interactions and try new prompts with multiple LLM providers via LiteLLM.  To launch...
[Short description explaining the high-level reason for the pull request] ## Changes ## How I tested this ## Notes ## Checklist - [ ] PR has an informative and human-readable...
**Is your feature request related to a problem? Please describe.** Small typos in an `expr` can be easy to miss. We should have a way to test & verify these...