feat(dev): pre-commit

Author: Daniele Briggi

.pre-commit-config.yaml

@@ -0,0 +1,27 @@
+# Use the same version of tools installed in the IDE
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
+    hooks:
+    - id: end-of-file-fixer
+    - id: trailing-whitespace
+    - id: detect-private-key
+    - id: check-merge-conflict
+-   repo: https://github.com/psf/black
+    rev: 25.1.0
+    hooks:
+    -   id: black
+- repo: https://github.com/pycqa/isort
+  rev: 6.0.1
+  hooks:
+    - id: isort
+      args: ["--profile", "black", "--filter-files"]
+- repo: https://github.com/pycqa/flake8
+  rev: 7.3.0
+  hooks:
+    - id: flake8
+- repo: https://github.com/PyCQA/bandit
+  rev: 1.8.6
+  hooks:
+    - id: bandit
+      args: ["--configfile", "bandit.yaml"]

README.md

@@ -1 +1 @@
-# sqlite-rag
+# sqlite-rag

bandit.yaml

@@ -0,0 +1,3 @@
+# https://bndit.readthedocs.io/en/latest/config.html
+skips: ['B101']
+exclude_dirs: ['tests']

pyproject.toml

@@ -21,6 +21,9 @@ dev = [
     "pytest-cov",
     "black",
     "flake8",
+    "bandit",
+    "isort",
+    "pre-commit"
 ]
 
 [project.scripts]
@@ -41,4 +44,4 @@ testpaths = [
 ]
 pythonpath = [
     "src"
-]
+]

src/sqlite_rag/__init__.py

@@ -1,19 +1,19 @@
 """
 SQLite RAG - Hybrid search with SQLite AI and SQLite Vector
 
-This package provides both a library interface and CLI for document 
+This package provides both a library interface and CLI for document
 indexing and semantic search using SQLite with AI and vector extensions.
 """
 
-from .sqliterag import SQLiteRag
-from .models.document import Document
 from .models.chunk import Chunk
+from .models.document import Document
 from .settings import Settings
+from .sqliterag import SQLiteRag
 
 __version__ = "0.1.0"
 __all__ = [
     "SQLiteRag",
-    "Document", 
+    "Document",
     "Chunk",
     "Settings",
-]
+]

src/sqlite_rag/chunker.py

@@ -1,9 +1,9 @@
+import math
 import sqlite3
 from typing import List
 
 from .models.chunk import Chunk
 from .settings import Settings
-import math
 
 
 class Chunker:
@@ -23,7 +23,7 @@ def _get_token_count(self, text: str) -> int:
         if text == "":
             return 0
         cursor = self._conn.execute("SELECT llm_token_count(?) AS count", (text,))
-        return cursor.fetchone()['count']
+        return cursor.fetchone()["count"]
 
     def _estimate_tokens_count(self, text: str) -> int:
         """Estimate token count more conservatively."""

src/sqlite_rag/models/chunk.py

@@ -5,5 +5,5 @@
 class Chunk:
     id: int | None = None
     document_id: int | None = None
-    content: str = ''
-    embedding: str | bytes = b''
+    content: str = ""
+    embedding: str | bytes = b""

src/sqlite_rag/models/document.py

@@ -1,5 +1,5 @@
-from datetime import datetime
 import hashlib
+from datetime import datetime
 
 from attr import dataclass
 

src/sqlite_rag/reader.py

@@ -48,7 +48,9 @@ def is_supported(path: Path) -> bool:
     def parse_file(path: Path) -> str:
         try:
             converter = MarkItDown()
-            return converter.convert(path, stream_info=StreamInfo(charset='utf8')).text_content
+            return converter.convert(
+                path, stream_info=StreamInfo(charset="utf8")
+            ).text_content
         except Exception as exc:
             raise ValueError(f"Failed to parse file {path}") from exc
 

src/sqlite_rag/settings.py

@@ -12,4 +12,3 @@ def __init__(self, model_path_or_name: str, db_path: str = "sqliterag.db"):
         self.chunk_overlap = 32  # Token overlap between chunks
 
         self.quantize_scan = True  # Whether to quantize the vector for faster search
-