Skip to content

Commit

Permalink
Updates the future-looking docs to account for what we've already don…
Browse files Browse the repository at this point in the history
…e/shifting priorites
  • Loading branch information
elijahbenizzy committed Sep 18, 2024
1 parent 9587699 commit e88128f
Show file tree
Hide file tree
Showing 2 changed files with 25 additions and 55 deletions.
34 changes: 20 additions & 14 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,11 +1,13 @@
# <img src="https://github.com/user-attachments/assets/2ab9b499-7ca2-4ae9-af72-ccc775f30b4e" width=25 height=25/> Burr

<div>

[![Discord](https://img.shields.io/badge/Join-Burr_Discord-7289DA?logo=discord)](https://discord.gg/6Zy2DwP4f3)
[![Downloads](https://static.pepy.tech/badge/burr/month)](https://pepy.tech/project/burr)
[![GitHub Last Commit](https://img.shields.io/github/last-commit/dagworks-inc/burr)](https://github.com/dagworks-inc/burr/pulse)
[![X](https://img.shields.io/badge/follow-%40burr_framework-1DA1F2?logo=x&style=social)](https://twitter.com/burr_framework)
<a href="https://app.commanddash.io/agent/github_DAGWorks-Inc_burr"><img src="https://img.shields.io/badge/AI-Code%20Agent-EB9FDA"></a>

</div>

Burr makes it easy to develop applications that make decisions (chatbots, agents, simulations, etc...) from simple python building blocks.
Expand All @@ -31,6 +33,7 @@ Then run the UI server:
```bash
burr
```

This will open up Burr's telemetry UI. It comes loaded with some default data so you can click around.
It also has a demo chat application to help demonstrate what the UI captures enabling you too see things changing in
real-time. Hit the "Demos" side bar on the left and select `chatbot`. To chat it requires the `OPENAI_API_KEY`
Expand All @@ -42,6 +45,7 @@ Next, start coding / running examples:
git clone https://github.com/dagworks-inc/burr && cd burr/examples/hello-world-counter
python application.py
```

You'll see the counter example running in the terminal, along with the trace being tracked in the UI.
See if you can find it.

Expand Down Expand Up @@ -119,14 +123,14 @@ Then read through some of the concepts and write your own application!

While Burr is attempting something (somewhat) unique, there are a variety of tools that occupy similar spaces:

| Criteria | Burr | Langgraph | temporal | Langchain | Superagent | Hamilton |
|-------------------------------------------|:---:|:----------:|:--------:|:---------:|:----------:|:--------:|
| Explicitly models a state machine || || || |
| Framework-agnostic || || || |
| Asynchronous event-based orchestration || || || |
| Built for core web-service logic || || || |
| Open-source user-interface for monitoring/tracing || || || |
| Works with non-LLM use-cases || || || |
| Criteria | Burr | Langgraph | temporal | Langchain | Superagent | Hamilton |
| ------------------------------------------------- | :--: | :-------: | :------: | :-------: | :--------: | :------: |
| Explicitly models a state machine | | || || |
| Framework-agnostic | | || || |
| Asynchronous event-based orchestration | | || || |
| Built for core web-service logic | | || || |
| Open-source user-interface for monitoring/tracing | | || || |
| Works with non-LLM use-cases | | || || |

## 🌯 Why the name Burr?

Expand All @@ -140,19 +144,18 @@ but realized that it has a wide array of applications and decided to release it

While Burr is stable and well-tested, we have quite a few tools/features on our roadmap!

1. Recursive state machines. Run Burr within Burr to get hierarchical agents/parallelism + track through to the UI.
1. Parallelism -- support for recursive "sub-agents" through an ergonomic API (not: this is already feasible, see [recursive applications](http://localhost:8000/concepts/recursion/)).
2. Testing & eval curation. Curating data with annotations and being able to export these annotations to create unit & integration tests.
3. Various efficiency/usability improvements for the core library (see [planned capabilities](https://burr.dagworks.io/concepts/planned-capabilities/) for more details). This includes:
1. Fully typed state with validation
2. First-class support for retries + exception management
3. More integration with popular frameworks (LCEL, LLamaIndex, Hamilton, etc...)
4. Capturing & surfacing extra metadata, e.g. annotations for particular point in time, that you can then pull out for fine-tuning, etc.
1. First-class support for retries + exception management
2. More integration with popular frameworks (LCEL, LLamaIndex, Hamilton, etc...)
3. Capturing & surfacing extra metadata, e.g. annotations for particular point in time, that you can then pull out for fine-tuning, etc.
4. Tooling for hosted execution of state machines, integrating with your infrastructure (Ray, modal, FastAPI + EC2, etc...)
5. Storage integrations. More integrations with technologies like Redis, MongoDB, MySQL, etc. so you can run Burr on top of what you have available.
6. More out of the box plugins for fine-grained tracing, e.g. decorators for your functions, LLM clients, etc.

If you want to avoid self-hosting the above solutions we're building Burr Cloud. To let us know you're interested
sign up [here](https://forms.gle/w9u2QKcPrztApRedA) for the waitlist to get access.
sign up [here](https://forms.gle/w9u2QKcPrztApRedA) for the waitlist to get access.

## 🤲 Contributing

Expand All @@ -163,6 +166,7 @@ We welcome contributors! To get started on developing, see the [developer-facing
### Code contributions

Users who have contributed core functionality, integrations, or examples.

- [Elijah ben Izzy](https://github.com/elijahbenizzy)
- [Stefan Krawczyk](https://github.com/skrawcz)
- [Joseph Booth](https://github.com/jombooth)
Expand All @@ -172,7 +176,9 @@ Users who have contributed core functionality, integrations, or examples.
- [Abdul Rafay](https://github.com/proftorch)

### Bug hunters/special mentions

Users who have contributed small docs fixes, design suggestions, and found bugs

- [Luke Chadwick](https://github.com/vertis)
- [Evans](https://github.com/sudoevans)
- [Sasmitha Manathunga](https://github.com/mmz-001)
46 changes: 5 additions & 41 deletions docs/concepts/planned-capabilities.rst
Original file line number Diff line number Diff line change
Expand Up @@ -6,41 +6,13 @@ These are on the roadmap (and will be part of Burr in the imminent future), but

We build fast though, so let us know which ones you need and they'll be in there before you know it!

-----------
Typed State
-----------

We plan to add the ability to type-check state with some (or all) of the following:

- Pydantic
- dataclasses
- TypedDict
- Custom state schemas (through the ``reads``/``writes`` parameters)

The idea is you would define state at the function level, parameterized by the state type, and Burr would be able to validate
against that state.

.. code-block:: python
class InputState(TypedDict):
foo: int
bar: str
class OutputState(TypedDict):
baz: int
qux: str
@action(reads=["foo", "bar"], writes=["baz"])
def my_action(state: State[InputState]) -> State[OutputState]:
result = {"baz": state["foo"] + 1, "qux": state["bar"] + "!"}
return state.update(**result)
The above could also be dataclasses/pydantic models. We could also add something as simple as:

.. code-block:: python
--------------------
UI-based annotations
--------------------

@action(reads={"foo": int, "bar": str}, writes={"baz": int, "qux": str})
...
We're adding the ability to annotate actions/states in the UI and download later for
analysis, debugging, etc... Please reach out if this is something you'd like to test!

-----------------------------
State Management/Immutability
Expand Down Expand Up @@ -114,14 +86,6 @@ One could imagine adding it as a condition (a few possibilities)
Will have to come up with ergonomic APIs -- the above are just some ideas.
-----------------
Streaming results
-----------------
Results should be able to stream in, but we'll want to store the final output in state.
Still thinking through the UX.
------------
Integrations
------------
Expand Down

0 comments on commit e88128f

Please sign in to comment.