weco 0.2.6__py3-none-any.whl → 0.2.7__py3-none-any.whl

weco/__init__.py

@@ -1,4 +1,4 @@
 # DO NOT EDIT
-__pkg_version__ = "0.2.6"
+__pkg_version__ = "0.2.7"
 __api_version__ = "v1"
 __base_url__ = f"https://api.aide.weco.ai/{__api_version__}"

weco/cli.py

@@ -50,6 +50,7 @@ def main() -> None:
     )
     parser.add_argument("--steps", type=int, required=True, help="Number of steps to run")
     parser.add_argument("--model", type=str, required=True, help="Model to use for optimization")
+    parser.add_argument("--log-dir", type=str, default=".runs", help="Directory to store logs and results")
     parser.add_argument(
         "--additional-instructions",
         default=None,
@@ -83,7 +84,9 @@ def main() -> None:
             timeout = 800
 
         # Initialize panels
-        summary_panel = SummaryPanel(maximize=maximize, metric_name=metric_name, total_steps=steps, model=args.model)
+        summary_panel = SummaryPanel(
+            maximize=maximize, metric_name=metric_name, total_steps=steps, model=args.model, runs_dir=args.log_dir
+        )
         plan_panel = PlanPanel()
         solution_panels = SolutionPanels(metric_name=metric_name)
         eval_output_panel = EvaluationOutputPanel()
@@ -112,7 +115,7 @@ def main() -> None:
         with Live(layout, refresh_per_second=refresh_rate, screen=True) as live:
             # Define the runs directory (.runs/<session-id>)
             session_id = session_response["session_id"]
-            runs_dir = pathlib.Path(".runs") / session_id
+            runs_dir = pathlib.Path(args.log_dir) / session_id
             runs_dir.mkdir(parents=True, exist_ok=True)
 
             # Save the original code (.runs/<session-id>/original.py)

weco/panels.py

@@ -11,7 +11,7 @@ from .utils import format_number
 class SummaryPanel:
     """Holds a summary of the optimization session."""
 
-    def __init__(self, maximize: bool, metric_name: str, total_steps: int, model: str, session_id: str = None):
+    def __init__(self, maximize: bool, metric_name: str, total_steps: int, model: str, runs_dir: str, session_id: str = None):
         self.maximize = maximize
         self.metric_name = metric_name
         self.goal = ("Maximizing" if self.maximize else "Minimizing") + f" {self.metric_name}..."
@@ -19,7 +19,8 @@ class SummaryPanel:
         self.total_output_tokens = 0
         self.total_steps = total_steps
         self.model = model
-        self.session_id = session_id or "N/A"
+        self.runs_dir = runs_dir
+        self.session_id = session_id if session_id is not None else "N/A"
         self.progress = Progress(
             TextColumn("[progress.description]{task.description}"),
             BarColumn(bar_width=20),
@@ -55,8 +56,7 @@ class SummaryPanel:
         summary_table.add_row(f"[bold cyan]Model:[/] {self.model}")
         summary_table.add_row("")
         # Log directory
-        runs_dir = f".runs/{self.session_id}"
-        summary_table.add_row(f"[bold cyan]Logs:[/] [blue underline]{runs_dir}[/]")
+        summary_table.add_row(f"[bold cyan]Logs:[/] [blue underline]{self.runs_dir}/{self.session_id}[/]")
         summary_table.add_row("")
         # Token counts
         summary_table.add_row(

{weco-0.2.6.dist-info → weco-0.2.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: weco
-Version: 0.2.6
+Version: 0.2.7
 Summary: Documentation for `weco`, a CLI for using Weco AI's code optimizer.
 Author-email: Weco AI Team <contact@weco.ai>
 License: MIT
@@ -109,7 +109,7 @@ weco --source optimize.py \
      --metric speedup \
      --maximize true \
      --steps 15 \
-     --model claude-3-7-sonnet-20250219 \
+     --model gemini-2.5-pro-exp-03-25 \
      --additional-instructions "Fuse operations in the forward method while ensuring the max float deviation remains small. Maintain the same format of the code."
 ```
 
@@ -127,7 +127,7 @@ weco --source optimize.py \
      --metric speedup \
      --maximize true \
      --steps 30 \
-     --model o3-mini \
+     --model gemini-2.5-pro-exp-03-25 \
      --additional-instructions examples.rst
 ```
 
@@ -144,7 +144,7 @@ Given how useful causal multihead self attention is to transformers, we've seen
         --metric speedup \
         --maximize true \
         --steps 30 \
-        --model gemini-2.5-pro-preview-03-25 \
+        --model gemini-2.5-pro-exp-03-25 \
         --additional-instructions "Use triton to optimize the code while ensuring a small max float diff. Maintain the same code format."
    ```
 
@@ -157,10 +157,52 @@ Given how useful causal multihead self attention is to transformers, we've seen
         --metric speedup \
         --maximize true \
         --steps 30 \
-        --model gemini-2.5-pro-preview-03-25 \
+        --model gemini-2.5-pro-exp-03-25 \
         --additional-instructions guide.md
    ```
 
+**Example 4: Optimizing a Classification Model**
+
+This example demonstrates optimizing a script for a Kaggle competition ([Spaceship Titanic](https://www.kaggle.com/competitions/spaceship-titanic/overview)) to improve classification accuracy. The additional instructions are provided via a separate file (`examples/spaceship-titanic/README.md`).
+
+First, install the requirements for the example environment:
+```bash
+pip install -r examples/spaceship-titanic/requirements-test.txt
+```
+And run utility function once to prepare the dataset
+```bash
+python examples/spaceship-titanic/utils.py
+```
+
+You should see the following structure at `examples/spaceship-titanic`. You need to prepare the kaggle credentials for downloading the dataset.
+```
+.
+├── baseline.py
+├── evaluate.py
+├── optimize.py
+├── private
+│   └── test.csv
+├── public
+│   ├── sample_submission.csv
+│   ├── test.csv
+│   └── train.csv
+├── README.md
+├── requirements-test.txt
+└── utils.py
+```
+
+Then, execute the optimization command:
+```bash
+weco --source examples/spaceship-titanic/optimize.py \
+     --eval-command "python examples/spaceship-titanic/optimize.py && python examples/spaceship-titanic/evaluate.py" \
+     --metric accuracy \
+     --maximize true \
+     --steps 10 \
+     --model gemini-2.5-pro-exp-03-25 \
+     --additional-instructions examples/spaceship-titanic/README.md
+```
+
+*The [baseline.py](examples/spaceship-titanic/baseline.py) is provided as a start point for optimization*
 
 ---
 
@@ -169,16 +211,28 @@ Given how useful causal multihead self attention is to transformers, we've seen
 | Argument                    | Description                                                                                                                                                              | Required |
 | :-------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------- |
 | `--source`                  | Path to the source code file that will be optimized (e.g., `optimize.py`).                                                                                               | Yes      |
-| `--eval-command`            | Command to run for evaluating the code in `--source`. This command should print the target `--metric` and its value to the terminal (stdout/stderr). See note below. | Yes      |
-| `--metric`                  | The name of the metric you want to optimize (e.g., 'accuracy', 'speedup', 'loss'). This metric name should match what's printed by your `--eval-command`.            | Yes      |
+| `--eval-command`            | Command to run for evaluating the code in `--source`. This command should print the target `--metric` and its value to the terminal (stdout/stderr). See note below.     | Yes      |
+| `--metric`                  | The name of the metric you want to optimize (e.g., 'accuracy', 'speedup', 'loss'). This metric name should match what's printed by your `--eval-command`.                | Yes      |
 | `--maximize`                | Whether to maximize (`true`) or minimize (`false`) the metric.                                                                                                           | Yes      |
 | `--steps`                   | Number of optimization steps (LLM iterations) to run.                                                                                                                    | Yes      |
-| `--model`                   | Model identifier for the LLM to use (e.g., `gpt-4o`, `claude-3.5-sonnet`). Recommended models to try include `o3-mini`, `claude-3-haiku`, and `gemini-2.5-pro-exp-03-25`.        | Yes      |
-| `--additional-instructions` | (Optional) Natural language description of specific instructions OR path to a file containing detailed instructions to guide the LLM.                                       | No       |
+| `--model`                   | Model identifier for the LLM to use (e.g., `gpt-4o`, `claude-3.5-sonnet`). Recommended models to try include `o3-mini`, `claude-3-haiku`, and `gemini-2.5-pro-exp-03-25`.| Yes      |
+| `--additional-instructions` | (Optional) Natural language description of specific instructions OR path to a file containing detailed instructions to guide the LLM.                                    | No       |
+| `--log-dir`                 | (Optional) Path to the directory to log intermediate steps and final optimization result. Defaults to `.runs/`.                                                          | No       |
 
 ---
 
+### Performance & Expectations
 
+Weco, powered by the AIDE algorithm, optimizes code iteratively based on your evaluation results. Achieving significant improvements, especially on complex research-level tasks, often requires substantial exploration time.
+
+The following plot from the independent [Research Engineering Benchmark (RE-Bench)](https://metr.org/AI_R_D_Evaluation_Report.pdf) report shows the performance of AIDE (the algorithm behind Weco) on challenging ML research engineering tasks over different time budgets.
+<p align="center">
+<img src="https://github.com/user-attachments/assets/ff0e471d-2f50-4e2d-b718-874862f533df" alt="RE-Bench Performance Across Time" width="60%"/>
+</p>
+
+As shown, AIDE demonstrates strong performance gains over time, surpassing lower human expert percentiles within hours and continuing to improve. This highlights the potential of evaluation-driven optimization but also indicates that reaching high levels of performance comparable to human experts on difficult benchmarks can take considerable time (tens of hours in this specific benchmark, corresponding to many `--steps` in the Weco CLI). Factor this into your planning when setting the number of `--steps` for your optimization runs.
+
+---
 
 ### Important Note on Evaluation
 

weco-0.2.7.dist-info/RECORD

@@ -0,0 +1,11 @@
+weco/__init__.py,sha256=6ZYuD51wx6bytYdLFMvzihYrpBlSxiFbmuiEl0z_AFo,124
+weco/api.py,sha256=8rIf2Fy3tN6GW7BG1CaggtfE9pW56I1erzwLCgawcVE,3511
+weco/cli.py,sha256=h8FevpztBob7OziDTIKh4y9CSnehkHJp2ydts6V6DhM,17317
+weco/panels.py,sha256=HHWmrnc2EJBJ8AEHb8mxlq30m-3q0j_4axc0r17sTnE,12349
+weco/utils.py,sha256=hhIebUPnetFMfNSFfcsKVw1TSpeu_Zw3rBPPnxDie0U,3911
+weco-0.2.7.dist-info/licenses/LICENSE,sha256=p_GQqJBvuZgkLNboYKyH-5dhpTDlKs2wq2TVM55WrWE,1065
+weco-0.2.7.dist-info/METADATA,sha256=AlBfVky2jZ6C2MnB8k_WkSMyucTeTE1Ias3y3_4bVsE,14577
+weco-0.2.7.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+weco-0.2.7.dist-info/entry_points.txt,sha256=ixJ2uClALbCpBvnIR6BXMNck8SHAab8eVkM9pIUowcs,39
+weco-0.2.7.dist-info/top_level.txt,sha256=F0N7v6e2zBSlsorFv-arAq2yDxQbzX3KVO8GxYhPUeE,5
+weco-0.2.7.dist-info/RECORD,,

weco-0.2.6.dist-info/RECORD

@@ -1,11 +0,0 @@
-weco/__init__.py,sha256=a3RxrwZhsuinalG_NtT0maKLFXFbgmgXFahpFgcEtZQ,124
-weco/api.py,sha256=8rIf2Fy3tN6GW7BG1CaggtfE9pW56I1erzwLCgawcVE,3511
-weco/cli.py,sha256=6rGEm_L-WSkJIT-jgfFmf2i_DXkQn6ILhqYQlptLFew,17159
-weco/panels.py,sha256=9gq5C43hgUmQgl6tW-f2dBbDjlsBKBatSaUVKeGm4Zw,12296
-weco/utils.py,sha256=hhIebUPnetFMfNSFfcsKVw1TSpeu_Zw3rBPPnxDie0U,3911
-weco-0.2.6.dist-info/licenses/LICENSE,sha256=p_GQqJBvuZgkLNboYKyH-5dhpTDlKs2wq2TVM55WrWE,1065
-weco-0.2.6.dist-info/METADATA,sha256=Ih-nkHxq_SJKccYXoVHmxytElqG75BSU1DGAAC9ipkk,11581
-weco-0.2.6.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-weco-0.2.6.dist-info/entry_points.txt,sha256=ixJ2uClALbCpBvnIR6BXMNck8SHAab8eVkM9pIUowcs,39
-weco-0.2.6.dist-info/top_level.txt,sha256=F0N7v6e2zBSlsorFv-arAq2yDxQbzX3KVO8GxYhPUeE,5
-weco-0.2.6.dist-info/RECORD,,