add lint and format check action

.github/workflows/lint.yaml

@@ -0,0 +1,28 @@
+name: Lint and format checks
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install tools
+        run: |
+          pip install black isort ruff
+
+      - name: Run Black
+        run: black --check .
+
+      - name: Run Isort
+        run: isort --check-only .
+
+      - name: Run Ruff
+        run: ruff check .

loaders/pdf.py

@@ -1,12 +1,12 @@
+import logging
 from pathlib import Path
 from typing import List
 
-from config import Config
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_core.documents import Document
 from langchain_community.document_loaders import PyPDFLoader
+from langchain_core.documents import Document
 
-import logging
+from config import Config
 
 logger = logging.getLogger(__name__)
 

loaders/web.py

@@ -1,12 +1,11 @@
+import logging
 from typing import List
 
-from pathlib import Path
-from langchain_core.documents import Document
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.document_loaders import WebBaseLoader
+from langchain_core.documents import Document
 
 from config import Config
-import logging
 
 logger = logging.getLogger(__name__)
 
@@ -55,7 +54,7 @@ def load(self, urls: List[str]) -> List[Document]:
         try:
             loader = WebBaseLoader(urls)
             docs = loader.load()
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to load URLs via WebBaseLoader")
             raise
 

vector_db/db_provider.py

@@ -1,9 +1,9 @@
 from abc import ABC, abstractmethod
 from typing import List
 
-from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_core.documents import Document
 from langchain_core.embeddings import Embeddings
+from langchain_huggingface import HuggingFaceEmbeddings
 
 
 class DBProvider(ABC):

vector_db/dryrun_provider.py

@@ -1,5 +1,7 @@
 from typing import List
+
 from langchain_core.documents import Document
+
 from vector_db.db_provider import DBProvider
 
 

vector_db/elastic_provider.py

@@ -1,4 +1,5 @@
 from typing import List
+
 from langchain_core.documents import Document
 from langchain_elasticsearch.vectorstores import ElasticsearchStore
 

vector_db/pgvector_provider.py

@@ -1,6 +1,8 @@
 from typing import List
-from langchain_postgres import PGVector
+
 from langchain_core.documents import Document
+from langchain_postgres import PGVector
+
 from vector_db.db_provider import DBProvider
 
 

vector_db/redis_provider.py

@@ -41,7 +41,7 @@ def __init__(self, url: str, index: str, schema: str):
         try:
             self.redis_client = redis.from_url(self.url)
             self.redis_client.ping()
-        except Exception as e:
+        except Exception:
             logger.exception("Failed to connect to Redis at %s", self.url)
             raise
 

vector_db/sqlserver_provider.py

@@ -107,6 +107,6 @@ def add_documents(self, docs: List[Document]) -> None:
             batch = docs[i : i + batch_size]
             try:
                 self.db.add_documents(batch)
-            except Exception as e:
+            except Exception:
                 logger.exception("Failed to insert batch starting at index %s", i)
                 raise