weco 0.2.6__py3-none-any.whl → 0.2.8__py3-none-any.whl

weco/__init__.py

@@ -1,4 +1,4 @@
 # DO NOT EDIT
-__pkg_version__ = "0.2.6"
+__pkg_version__ = "0.2.8"
 __api_version__ = "v1"
 __base_url__ = f"https://api.aide.weco.ai/{__api_version__}"

weco/api.py

@@ -6,14 +6,9 @@ import sys
 
 
 def handle_api_error(e: requests.exceptions.HTTPError, console: rich.console.Console) -> None:
-    """Extract and display error messages from API responses."""
-    try:
-        error_data = e.response.json()
-        error_message = error_data.get("detail", str(e))
-        console.print(f"[bold red]Server Error:[/] {error_message}")
-    except Exception:
-        # If we can't parse the JSON, just show the original error
-        console.print(f"[bold red]Server Error:[/] {str(e)}")
+    """Extract and display error messages from API responses in a structured format."""
+    error_message = str(e)  # Default message
+    console.print(f"[bold red]Error:[/] {error_message}")
     sys.exit(1)
 
 

weco/cli.py

@@ -36,7 +36,7 @@ def main() -> None:
     parser = argparse.ArgumentParser(
         description="[bold cyan]Weco CLI[/]", formatter_class=argparse.RawDescriptionHelpFormatter
     )
-    parser.add_argument("--source", type=str, required=True, help="Path to the Python source code (e.g. optimize.py)")
+    parser.add_argument("--source", type=str, required=True, help="Path to the source code (e.g. optimize.py)")
     parser.add_argument(
         "--eval-command", type=str, required=True, help="Command to run for evaluation (e.g. 'python eval.py --arg1=val1')"
     )
@@ -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,
@@ -83,9 +84,11 @@ 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)
+        solution_panels = SolutionPanels(metric_name=metric_name, source_fp=source_fp)
         eval_output_panel = EvaluationOutputPanel()
         tree_panel = MetricTreePanel(maximize=maximize)
         layout = create_optimization_layout()
@@ -112,11 +115,11 @@ 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)
-            runs_copy_source_fp = runs_dir / "original.py"
+            # Save the original code (.runs/<session-id>/original.<extension>)
+            runs_copy_source_fp = runs_dir / f"original.{source_fp.suffix}"
             write_to_path(fp=runs_copy_source_fp, content=source_code)
 
             # Write the code string to the source file path
@@ -197,8 +200,8 @@ def main() -> None:
                     api_keys=api_keys,
                     timeout=timeout,
                 )
-                # Save next solution (.runs/<session-id>/step_<step>.py)
-                write_to_path(fp=runs_dir / f"step_{step}.py", content=eval_and_next_solution_response["code"])
+                # Save next solution (.runs/<session-id>/step_<step>.<extension>)
+                write_to_path(fp=runs_dir / f"step_{step}.{source_fp.suffix}", content=eval_and_next_solution_response["code"])
 
                 # Write the next solution to the source file
                 write_to_path(fp=source_fp, content=eval_and_next_solution_response["code"])
@@ -348,8 +351,8 @@ def main() -> None:
                 )
                 best_solution_content = f"# Best solution from Weco with a score of {best_score_str}\n\n{best_solution_code}"
 
-            # Save best solution to .runs/<session-id>/best.py
-            write_to_path(fp=runs_dir / "best.py", content=best_solution_content)
+            # Save best solution to .runs/<session-id>/best.<extension>
+            write_to_path(fp=runs_dir / f"best.{source_fp.suffix}", content=best_solution_content)
 
             # write the best solution to the source file
             write_to_path(fp=source_fp, content=best_solution_content)

weco/panels.py

@@ -6,12 +6,13 @@ from rich.panel import Panel
 from rich.syntax import Syntax
 from typing import Dict, List, Optional, Union, Tuple
 from .utils import format_number
+import pathlib
 
 
 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 +20,8 @@ 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),
@@ -45,6 +47,8 @@ class SummaryPanel:
         """Create a summary panel with the relevant information."""
         layout = Layout(name="summary")
         summary_table = Table(show_header=False, box=None, padding=(0, 1))
+
+        summary_table.add_row("")
         # Goal
         if final_message is not None:
             summary_table.add_row(f"[bold cyan]Result:[/] {final_message}")
@@ -55,8 +59,7 @@ 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(
@@ -256,13 +259,19 @@ class EvaluationOutputPanel:
 class SolutionPanels:
     """Displays the current and best solutions side by side."""
 
-    def __init__(self, metric_name: str):
+    def __init__(self, metric_name: str, source_fp: pathlib.Path):
         # Current solution
         self.current_node = None
         # Best solution
         self.best_node = None
         # Metric name
         self.metric_name = metric_name.capitalize()
+        # Determine the lexer for the source file
+        self.lexer = self._determine_lexer(source_fp)
+
+    def _determine_lexer(self, source_fp: pathlib.Path) -> str:
+        """Determine the lexer for the source file."""
+        return Syntax.from_path(source_fp).lexer
 
     def update(self, current_node: Union[Node, None], best_node: Union[Node, None]):
         """Update the current and best solutions."""
@@ -280,7 +289,7 @@ class SolutionPanels:
         # Current solution (without score)
         current_title = f"[bold]💡 Current Solution (Step {current_step})"
         current_panel = Panel(
-            Syntax(str(current_code), "python", theme="monokai", line_numbers=True, word_wrap=False),
+            Syntax(str(current_code), self.lexer, theme="monokai", line_numbers=True, word_wrap=False),
             title=current_title,
             border_style="yellow",
             expand=True,
@@ -290,7 +299,7 @@ class SolutionPanels:
         # Best solution
         best_title = f"[bold]🏆 Best Solution ([green]{self.metric_name}: {f'{best_score:.4f}' if best_score is not None else 'N/A'}[/])"
         best_panel = Panel(
-            Syntax(str(best_code), "python", theme="monokai", line_numbers=True, word_wrap=False),
+            Syntax(str(best_code), self.lexer, theme="monokai", line_numbers=True, word_wrap=False),
             title=best_title,
             border_style="green",
             expand=True,

{weco-0.2.6.dist-info → weco-0.2.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: weco
-Version: 0.2.6
+Version: 0.2.8
 Summary: Documentation for `weco`, a CLI for using Weco AI's code optimizer.
 Author-email: Weco AI Team <contact@weco.ai>
 License: MIT
@@ -9,7 +9,7 @@ Keywords: AI,Code Optimization,Code Generation
 Classifier: Programming Language :: Python :: 3
 Classifier: Operating System :: OS Independent
 Classifier: License :: OSI Approved :: MIT License
-Requires-Python: >=3.12
+Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: requests
@@ -20,13 +20,19 @@ Requires-Dist: build; extra == "dev"
 Requires-Dist: setuptools_scm; extra == "dev"
 Dynamic: license-file
 
-# Weco CLI – Code Optimizer for Machine Learning Engineers
+# Weco: The Evaluation-Driven AI Code Optimizer
 
 [![Python](https://img.shields.io/badge/Python-3.12.0-blue)](https://www.python.org)
-[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
 [![PyPI version](https://badge.fury.io/py/weco.svg)](https://badge.fury.io/py/weco)
+[![AIDE](https://img.shields.io/badge/AI--Driven_Exploration-arXiv-orange?style=flat-square&logo=arxiv)](https://arxiv.org/abs/2502.13138)
 
-`weco` is a command-line interface for interacting with Weco AI's code optimizer, powered by [AI-Driven Exploration](https://arxiv.org/abs/2502.13138). It helps you automate the improvement of your code for tasks like GPU kernel optimization, feature engineering, model development, and prompt engineering.
+Weco systematically optimizes your code, guided directly by your evaluation metrics.
+
+Example applications include:
+
+- **GPU Kernel Optimization**: Reimplement PyTorch functions using CUDA, Triton or Metal, optimizing for `latency`, `throughput`, or `memory_bandwidth`.
+- **Model Development**: Tune feature transformations or architectures, optimizing for `validation_accuracy`, `AUC`, or `Sharpe Ratio`.
+- **Prompt Engineering**: Refine prompts for LLMs, optimizing for  `win_rate`, `relevance`, or `format_adherence`
 
 https://github.com/user-attachments/assets/cb724ef1-bff6-4757-b457-d3b2201ede81
 
@@ -40,37 +46,6 @@ The `weco` CLI leverages a tree search approach guided by Large Language Models
 
 ---
 
-## Example Use Cases
-
-Here's how `weco` can be applied to common ML engineering tasks:
-
-*   **GPU Kernel Optimization:**
-    *   **Goal:** Improve the speed or efficiency of low-level GPU code.
-    *   **How:** `weco` iteratively refines CUDA, Triton, Metal, or other kernel code specified in your `--source` file.
-    *   **`--eval-command`:** Typically runs a script that compiles the kernel, executes it, and benchmarks performance (e.g., latency, throughput).
-    *   **`--metric`:** Examples include `latency`, `throughput`, `TFLOPS`, `memory_bandwidth`. Optimize to `minimize` latency or `maximize` throughput.
-
-*   **Feature Engineering:**
-    *   **Goal:** Discover better data transformations or feature combinations for your machine learning models.
-    *   **How:** `weco` explores different processing steps or parameters within your feature transformation code (`--source`).
-    *   **`--eval-command`:** Executes a script that applies the features, trains/validates a model using those features, and prints a performance score.
-    *   **`--metric`:** Examples include `accuracy`, `AUC`, `F1-score`, `validation_loss`. Usually optimized to `maximize` accuracy/AUC/F1 or `minimize` loss.
-
-*   **Model Development:**
-    *   **Goal:** Tune hyperparameters or experiment with small architectural changes directly within your model's code.
-    *   **How:** `weco` modifies hyperparameter values (like learning rate, layer sizes if defined in the code) or structural elements in your model definition (`--source`).
-    *   **`--eval-command`:** Runs your model training and evaluation script, printing the key performance indicator.
-    *   **`--metric`:** Examples include `validation_accuracy`, `test_loss`, `inference_time`, `perplexity`. Optimize according to the metric's nature (e.g., `maximize` accuracy, `minimize` loss).
-
-*   **Prompt Engineering:**
-    *   **Goal:** Refine prompts used within larger systems (e.g., for LLM interactions) to achieve better or more consistent outputs.
-    *   **How:** `weco` modifies prompt templates, examples, or instructions stored in the `--source` file.
-    *   **`--eval-command`:** Executes a script that uses the prompt, generates an output, evaluates that output against desired criteria (e.g., using another LLM, checking for keywords, format validation), and prints a score.
-    *   **`--metric`:** Examples include `quality_score`, `relevance`, `task_success_rate`, `format_adherence`. Usually optimized to `maximize`.
-
----
-
-
 ## Setup
 
 1.  **Install the Package:**
@@ -97,70 +72,30 @@ Here's how `weco` can be applied to common ML engineering tasks:
 
 ---
 
-### Examples
+### Example: Optimizing Simple PyTorch Operations
+
+This basic example shows how to optimize a simple PyTorch function for speedup.
 
-**Example 1: Optimizing PyTorch simple operations**
+For more advanced examples, including **[Metal/MLX](/examples/metal/README.md), [Triton](/examples/triton/README.md), [CUDA kernel optimization](/examples/cuda/README.md)**, and **[ML model optimization](/examples/spaceship-titanic/README.md)t**, please see the `README.md` files within the corresponding subdirectories under the [`examples/`](./examples/) folder.
 
 ```bash
+# Navigate to the example directory
 cd examples/hello-kernel-world
-pip install torch 
+
+# Install dependencies
+pip install torch
+
+# Run Weco
 weco --source optimize.py \
      --eval-command "python evaluate.py --solution-path optimize.py --device cpu" \
      --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."
 ```
 
-Note that if you have an NVIDIA gpu, change the device to `cuda`. If you are running this on Apple Silicon, set it to `mps`.
-
-**Example 2: Optimizing MLX operations with instructions from a file**
-
-Lets optimize a 2D convolution operation in [`mlx`](https://github.com/ml-explore/mlx) using [Metal](https://developer.apple.com/documentation/metal/). Sometimes, additional context or instructions are too complex for a single command-line string. You can provide a path to a file containing these instructions.
-
-```bash
-cd examples/metal
-pip install mlx
-weco --source optimize.py \
-     --eval-command "python evaluate.py --solution-path optimize.py" \
-     --metric speedup \
-     --maximize true \
-     --steps 30 \
-     --model o3-mini \
-     --additional-instructions examples.rst
-```
-
-**Example 3: Level Agnostic Optimization: Causal Self Attention with Triton & CUDA**
-
-Given how useful causal multihead self attention is to transformers, we've seen its wide adoption across ML engineering and AI research. Its great to keep things at a high-level (in PyTorch) when doing research, but when moving to production you often need to write highly customized low-level kernels to make things run as fast as they can. The `weco` CLI can optimize kernels across a variety of different abstraction levels and frameworks. Example 2 uses Metal but lets explore two more frameworks:
-
-1. [Triton](https://github.com/triton-lang/triton)
-    ```bash
-   cd examples/triton
-   pip install torch triton
-   weco --source optimize.py \
-        --eval-command "python evaluate.py --solution-path optimize.py" \
-        --metric speedup \
-        --maximize true \
-        --steps 30 \
-        --model gemini-2.5-pro-preview-03-25 \
-        --additional-instructions "Use triton to optimize the code while ensuring a small max float diff. Maintain the same code format."
-   ```
-
-2. [CUDA](https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html)
-   ```bash
-   cd examples/cuda
-   pip install torch
-   weco --source optimize.py \
-        --eval-command "python evaluate.py --solution-path optimize.py" \
-        --metric speedup \
-        --maximize true \
-        --steps 30 \
-        --model gemini-2.5-pro-preview-03-25 \
-        --additional-instructions guide.md
-   ```
-
+**Note:** If you have an NVIDIA GPU, change the device in the `--eval-command` to `cuda`. If you are running this on Apple Silicon, set it to `mps`.
 
 ---
 
@@ -169,16 +104,28 @@ 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-0.2.8.dist-info/RECORD

@@ -0,0 +1,11 @@
+weco/__init__.py,sha256=VUGnYC55MzHzmhg_IT0RRJ3QJDE3D2QFmvwGhhJ8hwA,124
+weco/api.py,sha256=89lB2572jApAxkA0DDppDnJKBwvZTa3kH9jFpC0LFDQ,3313
+weco/cli.py,sha256=8WotHdSRGP5GwLucEQltiMRH8zVrGB84n8o2mhUaCco,17408
+weco/panels.py,sha256=R_df-VAbWyLoqCA9A6UzbIGZ9sm2IgJO4idnyjmrHQk,12701
+weco/utils.py,sha256=hhIebUPnetFMfNSFfcsKVw1TSpeu_Zw3rBPPnxDie0U,3911
+weco-0.2.8.dist-info/licenses/LICENSE,sha256=p_GQqJBvuZgkLNboYKyH-5dhpTDlKs2wq2TVM55WrWE,1065
+weco-0.2.8.dist-info/METADATA,sha256=5KLO8utu8ItVkPmJ6uLy3NHCUpLsRit_OvyT70Sp7XI,9179
+weco-0.2.8.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+weco-0.2.8.dist-info/entry_points.txt,sha256=ixJ2uClALbCpBvnIR6BXMNck8SHAab8eVkM9pIUowcs,39
+weco-0.2.8.dist-info/top_level.txt,sha256=F0N7v6e2zBSlsorFv-arAq2yDxQbzX3KVO8GxYhPUeE,5
+weco-0.2.8.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,,