You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+9-10Lines changed: 9 additions & 10 deletions
Original file line number
Diff line number
Diff line change
@@ -31,14 +31,13 @@ Or for development, clone the repo and run the following.
31
31
32
32
pip install -e .
33
33
34
-
The library requires Python >= 3.9. The installation script will git
35
-
clone [AutoGen](https://github.com/microsoft/autogen). You may require [Git Large File Storage](https://git-lfs.com/) if
36
-
git is unable to clone the repository otherwise.
34
+
The library requires Python >= 3.9. By default (starting with v0.1.3.5), we use [LiteLLM](https://github.com/BerriAI/litellm) as the backend of LLMs. For backward compatibility, we provide backend-support with [AutoGen](https://github.com/microsoft/autogen); when installing, users can add `[autogen]` tag to install a compatible AutoGen version (e.g., `pip install trace-opt[autogen]`). You may require [Git Large File Storage](https://git-lfs.com/) if
35
+
git is unable to clone the repository.
37
36
38
37
## Updates
39
38
-**2025.2.7** Trace was featured in the [G-Research NeurIPS highlight](https://www.gresearch.com/news/neurips-paper-reviews-2024-8/) by the Science Director Hugh Salimbeni.
40
39
-**2024.12.10** Trace was demoed in person at NeurIPS 2024 Expo.
41
-
-**2024.11.05** Ching-An Cheng gave a talk at UW Robotics Colloquium on Trace: [video](https://www.youtube.com/watch?v=T2g1Vo3u_9g).
40
+
-**2024.11.05** Ching-An Cheng gave a talk at UW Robotics Colloquium on Trace: [video](https://www.youtube.com/watch?v=T2g1Vo3u_9g).
42
41
-**2024.10.21** New [paper](https://arxiv.org/abs/2410.15625) by Nvidia, Stanford, Visa, & Intel applies Trace to
43
42
optimize for mapper code of parallel programming (for scientific computing and matrix multiplication). Trace (OptoPrime) learns code achieving 1.3X speed up under 10
44
43
minutes, compared to the code optimized by a system engineer expert.
@@ -215,16 +214,16 @@ def train():
215
214
agent = train()
216
215
```
217
216
218
-
Defining and training an agent through Trace will give you more flexibility and control over what the agent learns.
217
+
Defining and training an agent through Trace will give you more flexibility and control over what the agent learns.
219
218
220
219
## Tutorials
221
220
222
221
|**Level**|**Tutorial**|**Run in Colab**|**Description**|
| Beginner |[Getting Started](https://microsoft.github.io/Trace/quickstart/quick_start.html)|[](https://colab.research.google.com/github/microsoft/Trace/blob/website/docs/quickstart/quick_start.ipynb)| Introduces basic primitives like `node` and `bundle`. Showcases a code optimization pipeline. |
225
-
| Beginner | [Adaptive AI Agent](https://microsoft.github.io/Trace/quickstart/quick_start_2.html) | [](https://colab.research.google.com/github/microsoft/Trace/blob/website/docs/quickstart/quick_start_2.ipynb) | Introduce primitive `model` that allows anyone to build self-improving agents that react to environment feedback. Shows how an LLM agent learns to place a shot in a Battleship game.
226
-
| Intermediate | [Multi-Agent Collaboration](https://microsoft.github.io/Trace/quickstart/virtualhome.html) | N/A | Demonstrates how Trace can be used for multi-agent collaboration environment in Virtualhome.
227
-
| Intermediate | [NLP Prompt Optimization](https://microsoft.github.io/Trace/examples/nlp/bigbench_hard.html) | [](https://colab.research.google.com/github/microsoft/Trace/blob/website/docs/examples/nlp/bigbench_hard.ipynb) | Shows how Trace can optimizes prompt and code together jointly for BigBench-Hard 23 tasks.
224
+
| Beginner | [Adaptive AI Agent](https://microsoft.github.io/Trace/quickstart/quick_start_2.html) | [](https://colab.research.google.com/github/microsoft/Trace/blob/website/docs/quickstart/quick_start_2.ipynb) | Introduce primitive `model` that allows anyone to build self-improving agents that react to environment feedback. Shows how an LLM agent learns to place a shot in a Battleship game.
225
+
| Intermediate | [Multi-Agent Collaboration](https://microsoft.github.io/Trace/quickstart/virtualhome.html) | N/A | Demonstrates how Trace can be used for multi-agent collaboration environment in Virtualhome.
226
+
| Intermediate | [NLP Prompt Optimization](https://microsoft.github.io/Trace/examples/nlp/bigbench_hard.html) | [](https://colab.research.google.com/github/microsoft/Trace/blob/website/docs/examples/nlp/bigbench_hard.ipynb) | Shows how Trace can optimizes prompt and code together jointly for BigBench-Hard 23 tasks.
228
227
| Advanced |[Robotic Arm Control](https://microsoft.github.io/Trace/examples/robotics/metaworld.html)|[](https://colab.research.google.com/github/microsoft/Trace/blob/website/docs/examples/robotics/metaworld.ipynb)| Trace can optimize code to control a robotic arm after observing a full trajectory of interactions. |
229
228
230
229
@@ -276,7 +275,7 @@ with TraceGraph coming soon).
276
275
277
276
## LLM API Setup
278
277
279
-
Currently we rely on AutoGen for LLM caching and API-Key management.
278
+
Currently we rely on AutoGen for LLM caching and API-Key management.
280
279
AutoGen relies on `OAI_CONFIG_LIST`, which is a file you put in your working directory. It has the format of:
0 commit comments