ci(dspy): Add Ruff linting workflow (stanfordnlp#538)

* Add Ruff linting workflow

* Update GitHub Actions workflows

* Make ruff apply but not fail

* Style fixes by Ruff

* Combine Workflows

* Add caching

* Add import related rules

* Automatic Style fixes

* Try and fix caching

* Fix import

* Use natve python dep caching

* Update actions/checkout to v4

* Use autofix in tests

* Try to cache "install poetry"

* Empty-Commit to test caching

* Remove workflow deps

* Rename action

* Update workflow name

* Fix Docker stop command and subprocess run check

* Fix functional imports

---------

Co-authored-by: isaacbmiller <[email protected]>

.github/workflows/run_tests.yml

@@ -1,4 +1,4 @@
-name: Build and Run Tests
+name: Fix, Test, and Build
 
 on:
   push:
@@ -10,38 +10,78 @@ env:
   POETRY_VERSION: "1.6.1"
 
 jobs:
+  fix:
+    name: Apply Ruff Fix
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v5
+      - uses: chartboost/ruff-action@v1
+        with:
+          args: --fix-only
+      - uses: stefanzweifel/git-auto-commit-action@v5
+        with:
+          commit_message: "Automatic Style fixes"
+
   test:
-    name: Test
+    name: Run Tests
     runs-on: ubuntu-latest
     strategy:
       matrix:
         python-version: ["3.9"]
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ github.head_ref }}
+      - name: Load cached Poetry installation
+        id: cached-poetry
+        uses: actions/cache@v3
+        with:
+          path: ~/.local
+          key: poetry-${{ env.POETRY_VERSION }}-${{ hashFiles('**/poetry.lock') }}
+      - name: Install Poetry
+        if: steps.cached-poetry.outputs.cache-hit != 'true'
+        uses: snok/install-poetry@v1
       - name: Set up python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-      - name: Install Poetry
-        uses: snok/install-poetry@v1
+          cache: "poetry"
       - name: Install dependencies
-        run: poetry install
+        run: poetry install --no-interaction --no-root
+      - name: Run lint with tests
+        uses: chartboost/ruff-action@v1
+        with:
+          args: --fix-only
       - name: Run tests with pytest
         run: poetry run pytest tests/
+
   build_poetry:
     name: Build Poetry
     runs-on: ubuntu-latest
     strategy:
       matrix:
         python-version: ["3.9"]
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ github.head_ref }}
+      - name: Load cached Poetry installation
+        id: cached-poetry
+        uses: actions/cache@v3
+        with:
+          path: ~/.local
+          key: poetry-${{ env.POETRY_VERSION }}-${{ hashFiles('**/poetry.lock') }}
+      - name: Install Poetry
+        if: steps.cached-poetry.outputs.cache-hit != 'true'
+        uses: snok/install-poetry@v1
       - name: Set up python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-      - name: Install Poetry
-        uses: snok/install-poetry@v1
+          cache: "poetry"
       - name: Build
         run: poetry build
       - name: Install built package
@@ -50,17 +90,30 @@ jobs:
         run: python -c "import dspy"
       - name: Test import dsp
         run: python -c "import dsp"
+
   build_setup:
     name: Build Setup
     runs-on: ubuntu-latest
     strategy:
       matrix:
         python-version: ["3.9"]
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ github.head_ref }}
+      - name: Load cached Poetry installation
+        id: cached-poetry
+        uses: actions/cache@v3
+        with:
+          path: ~/.local
+          key: poetry-${{ env.POETRY_VERSION }}-${{ hashFiles('**/poetry.lock') }}
+      - name: Install Poetry
+        if: steps.cached-poetry.outputs.cache-hit != 'true'
+        uses: snok/install-poetry@v1
       - name: Set up python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+          cache: "poetry"
       - name: Run setup.py build
         run: python setup.py build

dsp/__init__.py

@@ -3,7 +3,6 @@
 from .templates import *
 from .utils import settings
 
-
 """
 TODO:
 

dsp/evaluation/utils.py

@@ -1,7 +1,8 @@
 
-import dsp
-import tqdm
 import pandas as pd
+import tqdm
+
+import dsp
 
 try:
     from IPython.display import display as ipython_display

dsp/modules/__init__.py

@@ -1,19 +1,15 @@
-from .cache_utils import *
 from .azure_openai import AzureOpenAI
-from .gpt3 import *
+from .bedrock import *
+from .cache_utils import *
+from .clarifai import *
+from .cohere import *
+from .colbertv2 import ColBERTv2
 from .databricks import *
+from .google import *
+from .gpt3 import *
 from .hf import HFModel
-from .colbertv2 import ColBERTv2
-from .sentence_vectorizer import *
-from .cohere import *
-from .sbert import *
-from .pyserini import *
+from .hf_client import Anyscale, HFClientTGI, Together
 from .ollama import *
-from .clarifai import *
-from .bedrock import *
-from .google import *
-
-
-from .hf_client import HFClientTGI
-from .hf_client import Anyscale
-from .hf_client import Together
+from .pyserini import *
+from .sbert import *
+from .sentence_vectorizer import *

dsp/modules/aws_lm.py

@@ -4,10 +4,11 @@
 
 from __future__ import annotations
 
-from abc import abstractmethod
+import json
 import logging
+from abc import abstractmethod
 from typing import Any, Literal
-import json
+
 from dsp.modules.lm import LM
 
 # Heuristic translating number of chars to tokens

dsp/modules/azurecognitivesearch.py

@@ -1,6 +1,7 @@
-from typing import Union, Any
+from typing import Any, Union
 
 from dsp.utils import dotdict
+
 try:
     from azure.core.credentials import AzureKeyCredential
     from azure.search.documents import SearchClient

dsp/modules/bedrock.py

@@ -1,7 +1,8 @@
 from __future__ import annotations
 
-from typing import Any
 import json
+from typing import Any
+
 from dsp.modules.aws_lm import AWSLM
 
 

dsp/modules/cache_utils.py

@@ -1,12 +1,11 @@
 import os
-
+from functools import wraps
 from pathlib import Path
+
 from joblib import Memory
-from functools import wraps
 
 from dsp.utils import dotdict
 
-
 cache_turn_on = True
 
 

dsp/modules/clarifai.py

@@ -3,6 +3,7 @@
 
 from dsp.modules.lm import LM
 
+
 class ClarifaiLLM(LM):
     """Integration to call models hosted in clarifai platform.
 

dsp/modules/cohere.py

@@ -1,5 +1,6 @@
 import math
 from typing import Any, Optional
+
 import backoff
 
 from dsp.modules.lm import LM

dsp/modules/colbertv2.py

@@ -1,11 +1,11 @@
 import functools
-from typing import Optional, Union, Any
+from typing import Any, Optional, Union
+
 import requests
 
 from dsp.modules.cache_utils import CacheMemory, NotebookCacheMemory
 from dsp.utils import dotdict
 
-
 # TODO: Ideally, this takes the name of the index and looks up its port.
 
 

dsp/modules/databricks.py

@@ -19,8 +19,8 @@
 from dsp.modules.gpt3 import GPT3
 
 try:
-    from openai.openai_object import OpenAIObject
     import openai.error
+    from openai.openai_object import OpenAIObject
     ERRORS = (openai.error.RateLimitError, openai.error.ServiceUnavailableError, openai.error.APIError)
 except Exception:
     ERRORS = (openai.RateLimitError, openai.APIError)

dsp/modules/finetuning/finetune_hf.py

@@ -1,28 +1,30 @@
 # Adapted from: https://www.philschmid.de/fine-tune-flan-t5#3-fine-tune-and-evaluate-flan-t5
 
-import os
-import json
 import copy
 import glob
-import torch
+import json
+import os
 import warnings
+from dataclasses import dataclass
+
 import evaluate
 import numpy as np
+import torch
 from datasets import Dataset
-from dataclasses import dataclass
 from transformers import (
-    set_seed,
     AutoConfig,
-    AutoModelForSeq2SeqLM,
     AutoModelForCausalLM,
+    AutoModelForSeq2SeqLM,
     AutoTokenizer,
+    DataCollatorForSeq2Seq,
     PreTrainedTokenizer,
-    Trainer,
     Seq2SeqTrainer,
-    TrainingArguments,
     Seq2SeqTrainingArguments,
-    DataCollatorForSeq2Seq,
+    Trainer,
+    TrainingArguments,
+    set_seed,
 )
+
 # from peft import get_peft_model, LoraConfig, TaskType
 from transformers.trainer_callback import TrainerCallback
 

dsp/modules/google.py

@@ -1,6 +1,7 @@
 import os
-from typing import Any, Optional
 from collections.abc import Iterable
+from typing import Any, Optional
+
 import backoff
 
 from dsp.modules.lm import LM

dsp/modules/gpt3.py

@@ -11,10 +11,10 @@
 import json
 from typing import Any, Literal, Optional, cast
 
-import dsp
 import backoff
 import openai
 
+import dsp
 from dsp.modules.cache_utils import CacheMemory, NotebookCacheMemory, cache_turn_on
 from dsp.modules.lm import LM
 
@@ -24,8 +24,8 @@
     OPENAI_LEGACY = True
 
 try:
-    from openai.openai_object import OpenAIObject
     import openai.error
+    from openai.openai_object import OpenAIObject
 
     ERRORS = (
         openai.error.RateLimitError,

dsp/modules/hf.py

@@ -1,8 +1,9 @@
 # from peft import PeftConfig, PeftModel
 # from transformers import AutoModelForSeq2SeqLM, AutoModelForCausalLM, AutoTokenizer, AutoConfig
-from typing import Optional, Literal
+from typing import Literal, Optional
 
 from dsp.modules.lm import LM
+
 # from dsp.modules.finetuning.finetune_hf import preprocess_prompt
 
 def openai_to_hf(**kwargs):
@@ -43,8 +44,8 @@ def __init__(self, model: str, checkpoint: Optional[str] = None, is_client: bool
         self.device_map = hf_device_map
         if not self.is_client:
             try:
-                from transformers import AutoModelForSeq2SeqLM, AutoModelForCausalLM, AutoTokenizer, AutoConfig
                 import torch
+                from transformers import AutoConfig, AutoModelForCausalLM, AutoModelForSeq2SeqLM, AutoTokenizer
             except ImportError as exc:
                 raise ModuleNotFoundError(
                     "You need to install Hugging Face transformers library to use HF models.",

dsp/modules/hf_client.py

@@ -1,15 +1,15 @@
 import os
 import random
-import requests
-from dsp.modules.hf import HFModel, openai_to_hf
-from dsp.modules.cache_utils import CacheMemory, NotebookCacheMemory
-import subprocess
 import re
 import shutil
+import subprocess
 
 # from dsp.modules.adapter import TurboAdapter, DavinciAdapter, LlamaAdapter
-
 import backoff
+import requests
+
+from dsp.modules.cache_utils import CacheMemory, NotebookCacheMemory
+from dsp.modules.hf import HFModel, openai_to_hf
 
 ERRORS = (Exception)
 
@@ -173,7 +173,7 @@ def close_server(self, port):
                     container_id = match.group(1)
                     port_mapping = subprocess.check_output(['docker', 'port', container_id]).decode().strip()
                     if f'0.0.0.0:{port}' in port_mapping:
-                        subprocess.run(['docker', 'stop', container_id])
+                        subprocess.run(['docker', 'stop', container_id], check=False)
 
     def run_server(self, port, model_name=None, model_path=None, env_variable=None, gpus="all", num_shard=1, max_input_length=4000, max_total_tokens=4096, max_best_of=100):        
         self.close_server(port)
@@ -355,8 +355,7 @@ class ChatModuleClient(HFModel):
     def __init__(self, model, model_path):
         super().__init__(model=model, is_client=True)
 
-        from mlc_chat import ChatModule
-        from mlc_chat import ChatConfig
+        from mlc_chat import ChatConfig, ChatModule
 
         self.cm = ChatModule(
             model=model, lib_path=model_path, chat_config=ChatConfig(conv_template="LM"),