chore: ruff CI (should fail) (AnswerDotAI#42)

chore: ruff CI (should pass) chore: use action for format chore: better ruff format chore: import linting too, move ruff to pyproject
adharm · Jan 13, 2024 · 2e5060e · 2e5060e
1 parent d71bcdc
commit 2e5060e
Show file tree

Hide file tree

Showing 16 changed files with 104 additions and 80 deletions.
diff --git a/.github/workflows/ruff.yml b/.github/workflows/ruff.yml
@@ -0,0 +1,13 @@
+name: Ruff
+on: pull_request
+jobs:
+  ruff:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: "Linting & Flaking"
+        uses: chartboost/ruff-action@v1
+      - name: "Formatting"
+        uses: chartboost/ruff-action@v1
+        with:
+          args: format --check
diff --git a/.ruff.toml b/.ruff.toml
diff --git a/pyproject.toml b/pyproject.toml
@@ -32,3 +32,61 @@ ruff = "^0.1.9"
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
+
+[tool.ruff]
+# Exclude a variety of commonly ignored directories.
+exclude = [
+    ".bzr",
+    ".direnv",
+    ".eggs",
+    ".git",
+    ".git-rewrite",
+    ".hg",
+    ".mypy_cache",
+    ".nox",
+    ".pants.d",
+    ".pytype",
+    ".ruff_cache",
+    ".svn",
+    ".tox",
+    ".venv",
+    "__pypackages__",
+    "_build",
+    "buck-out",
+    "build",
+    "dist",
+    "node_modules",
+    "venv",
+]
+
+# Same as Black.
+line-length = 88
+output-format = "grouped"
+
+target-version = "py39"
+
+[tool.ruff.lint]
+select = [
+  # bugbear rules
+  "B",
+  "I",
+  # remove unused imports
+  "F401",
+  # bare except statements
+  "E722",
+  # unused arguments
+  "ARG",
+]
+ignore = [
+  "B006",
+  "B018",
+]
+
+unfixable = [
+  "T201",
+  "T203",
+]
+ignore-init-module-imports = true
+
+[tool.ruff.lint.isort]
+section-order = ["future", "standard-library", "third-party", "first-party", "local-folder"]
diff --git a/ragatouille/RAGPretrainedModel.py b/ragatouille/RAGPretrainedModel.py
@@ -1,14 +1,16 @@
-from typing import Callable, Optional, Union, Any
 from pathlib import Path
-from langchain_core.retrievers import BaseRetriever
+from typing import Any, Callable, Optional, Union
+
 from langchain.retrievers.document_compressors.base import BaseDocumentCompressor
+from langchain_core.retrievers import BaseRetriever
+
 from ragatouille.data.corpus_processor import CorpusProcessor
 from ragatouille.data.preprocessors import llama_index_sentence_splitter
-from ragatouille.models import LateInteractionModel, ColBERT
 from ragatouille.integrations import (
-    RAGatouilleLangChainRetriever,
     RAGatouilleLangChainCompressor,
+    RAGatouilleLangChainRetriever,
 )
+from ragatouille.models import ColBERT, LateInteractionModel
 
 
 class RAGPretrainedModel:

diff --git a/ragatouille/RAGTrainer.py b/ragatouille/RAGTrainer.py
@@ -1,12 +1,12 @@
 from pathlib import Path
-from typing import Union, Literal, Optional
+from typing import Literal, Optional, Union
 
 from colbert.infra import ColBERTConfig
 
-from ragatouille.models import LateInteractionModel, ColBERT
+from ragatouille.data import TrainingDataProcessor
+from ragatouille.models import ColBERT, LateInteractionModel
 from ragatouille.negative_miners import HardNegativeMiner, SimpleMiner
 from ragatouille.utils import seeded_shuffle
-from ragatouille.data import TrainingDataProcessor
 
 
 class RAGTrainer:

diff --git a/ragatouille/data/__init__.py b/ragatouille/data/__init__.py
@@ -5,5 +5,5 @@
 __all__ = [
     "TrainingDataProcessor",
     "CorpusProcessor",
-    "llama_index_sentence_splitter"
+    "llama_index_sentence_splitter",
 ]
diff --git a/ragatouille/data/corpus_processor.py b/ragatouille/data/corpus_processor.py
@@ -1,4 +1,5 @@
 from typing import Callable, Optional, Union
+
 from ragatouille.data.preprocessors import llama_index_sentence_splitter
 
 

diff --git a/ragatouille/data/training_data_processor.py b/ragatouille/data/training_data_processor.py
@@ -1,8 +1,9 @@
 import os
+import random
 from collections import defaultdict
 from pathlib import Path
 from typing import Literal, Union
-import random
+
 import srsly
 
 

diff --git a/ragatouille/integrations/__init__.py b/ragatouille/integrations/__init__.py
@@ -1,6 +1,6 @@
 from ragatouille.integrations._langchain import (
-    RAGatouilleLangChainRetriever,
     RAGatouilleLangChainCompressor,
+    RAGatouilleLangChainRetriever,
 )
 
 __all__ = ["RAGatouilleLangChainRetriever", "RAGatouilleLangChainCompressor"]
diff --git a/ragatouille/integrations/_langchain.py b/ragatouille/integrations/_langchain.py
@@ -1,8 +1,9 @@
-from typing import Any, Optional, List, Sequence
+from typing import Any, List, Optional, Sequence
+
+from langchain.retrievers.document_compressors.base import BaseDocumentCompressor
 from langchain_core.callbacks.manager import CallbackManagerForRetrieverRun, Callbacks
 from langchain_core.documents import Document
 from langchain_core.retrievers import BaseRetriever
-from langchain.retrievers.document_compressors.base import BaseDocumentCompressor
 
 
 class RAGatouilleLangChainRetriever(BaseRetriever):
@@ -13,7 +14,7 @@ def _get_relevant_documents(
         self,
         query: str,
         *,
-        run_manager: CallbackManagerForRetrieverRun,
+        run_manager: CallbackManagerForRetrieverRun,  # noqa
     ) -> List[Document]:
         """Get documents relevant to a query."""
         docs = self.model.search(query, **self.kwargs)
@@ -34,7 +35,7 @@ def compress_documents(
         self,
         documents: Sequence[Document],
         query: str,
-        callbacks: Optional[Callbacks] = None,
+        callbacks: Optional[Callbacks] = None,  # noqa
         **kwargs,
     ) -> Any:
         """Rerank a list of documents relevant to a query."""

diff --git a/ragatouille/models/base.py b/ragatouille/models/base.py
@@ -1,5 +1,3 @@
-from typing import Union
-from pathlib import Path
 from abc import ABC, abstractmethod
 from pathlib import Path
 from typing import Union

diff --git a/ragatouille/models/colbert.py b/ragatouille/models/colbert.py
@@ -1,14 +1,14 @@
 import math
-from typing import Union, Optional, Literal
-import os
 import time
 from pathlib import Path
-from colbert.infra import Run, ColBERTConfig, RunConfig
-from colbert import Indexer, Searcher, Trainer, IndexUpdater
-from colbert.modeling.checkpoint import Checkpoint
-import torch
-import srsly
+from typing import Literal, Optional, Union
+
 import numpy as np
+import srsly
+import torch
+from colbert import Indexer, IndexUpdater, Searcher, Trainer
+from colbert.infra import ColBERTConfig, Run, RunConfig
+from colbert.modeling.checkpoint import Checkpoint
 
 from ragatouille.models.base import LateInteractionModel
 

diff --git a/ragatouille/models/utils.py b/ragatouille/models/utils.py
@@ -10,7 +10,7 @@
 from colbert.modeling.colbert import ColBERT
 from huggingface_hub import HfApi
 from huggingface_hub.utils import HfHubHTTPError
-from transformers import BertPreTrainedModel, AutoModel
+from transformers import AutoModel, BertPreTrainedModel
 
 
 def seeded_shuffle(collection: list, seed: int = 42):

diff --git a/ragatouille/negative_miners/simpleminer.py b/ragatouille/negative_miners/simpleminer.py
@@ -1,10 +1,11 @@
 from enum import Enum
 from pathlib import Path
-from typing import Literal, Union, Optional
-from sentence_transformers import SentenceTransformer
+from typing import Literal, Optional, Union
+
 import torch
-from voyager import Index, Space, StorageDataType
+from sentence_transformers import SentenceTransformer
 from tqdm import tqdm
+from voyager import Index, Space, StorageDataType
 
 from .base import HardNegativeMiner
 

diff --git a/ragatouille/utils.py b/ragatouille/utils.py
@@ -1,4 +1,5 @@
 import random
+
 import requests
 
 

diff --git a/tests/__init__.py b/tests/__init__.py
@@ -1,2 +1,2 @@
 # TODO
-# Tests in v0.0.2
+# Tests in v0.0.2
Original file line number	Diff line number	Diff line change
		@@ -1,4 +1,5 @@
		from typing import Callable, Optional, Union

		from ragatouille.data.preprocessors import llama_index_sentence_splitter


Expand Down