burr
burr copied to clipboard
apache
Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.
You want to +1 or -1 a response for later evaluation. We need to expose a way to do that. # idea ```python # annotated current returned state app.annotate({"value": 1,...
# Problem Large state objects will (a) kill the UI, and (b) make looking at data difficult. # Context I have a large list of objects 1K+, that I am...
- [x] Add Mongodb support - [ ] Add snowflake support (this will likely be restrictive) - [ ] Add deltalake support (this will likely be restrictive) - [ ]...
Got lazy and decided not to implement. Should be pretty straightforward, follow the GPT-like example.
We should be able to validate the DAG. Specific things we can check for: 1. For all nodes that read state item X, given an initial state, does there exist...
If someone is building an agent, an agent can go do stuff, but then might need help. Frame that example using `run(halt_before=["human_step"])`... TODO: - [ ] write up documentation to...
Take the following: ```python @action(reads=['input_var'], writes=['output_var']) def simple_action(state: State) -> tuple[dict, State]: output_var = _compute(state["input_var"]) result = {"output_var" : output_var} return result, state.update(**result) # or return result, state.append(**result) ``` This...
## Overview We should be able to launch a whole bunch of actions in parallel. Walking the state machine in parallel is tricky, so this proposes the following: 1. A...
This is me playing around -- parking it here for now, might pick up later. Current work: If anyone wants to pick this up, you'll need to: 1. Fix the...
Problems with Hamilton integration: - [ ] We can't modify inputs from state - [ ] We can't modify outputs to state Idea: ```python h = Hamilton( inputs={"most_recent_item": from_state("all_items", process=lambda...