fix(metadata): passed by reference

chore(dependencies): remove attrs

Author: Daniele Briggi

README.md

@@ -2,7 +2,7 @@
 
 # SQLite RAG
 
-[![Run Tests](https://github.com/sqliteai/sqlite-rag/actions/workflows/test.yaml/badge.svg?branch=main&event=release)](https://github.com/sqliteai/sqlite-rag/actions/workflows/test.yaml)
+[![Run Tests](https://github.com/sqliteai/sqlite-rag/actions/workflows/test.yaml/badge.svg)](https://github.com/sqliteai/sqlite-rag/actions/workflows/test.yaml)
 [![codecov](https://codecov.io/github/sqliteai/sqlite-rag/graph/badge.svg?token=30KYPY7864)](https://codecov.io/github/sqliteai/sqlite-rag)
 ![PyPI - Version](https://img.shields.io/pypi/v/sqlite-rag?link=https%3A%2F%2Fpypi.org%2Fproject%2Fsqlite-rag%2F)
 ![PyPI - Python Version](https://img.shields.io/pypi/pyversions/sqlite-rag?link=https%3A%2F%2Fpypi.org%2Fproject%2Fsqlite-rag)

pyproject.toml

@@ -17,7 +17,6 @@ classifiers = [
     "Operating System :: OS Independent",
 ]
 dependencies = [
-    "attrs",
     "typer",
     "huggingface_hub[hf_transfer]",
     "markitdown[docx]",

src/sqlite_rag/models/chunk.py

@@ -1,4 +1,4 @@
-from attr import dataclass
+from dataclasses import dataclass
 
 
 @dataclass

src/sqlite_rag/models/document.py

@@ -1,10 +1,9 @@
 import hashlib
 import re
+from dataclasses import dataclass, field
 from datetime import datetime
 from typing import Optional
 
-from attr import dataclass
-
 from .chunk import Chunk
 
 
@@ -15,11 +14,11 @@ class Document:
     id: str | None = None
     content: str = ""
     uri: str | None = None
-    metadata: dict = {}
+    metadata: dict = field(default_factory=dict)
     created_at: datetime | None = None
     updated_at: datetime | None = None
 
-    chunks: list["Chunk"] = []
+    chunks: list["Chunk"] = field(default_factory=list)
 
     def hash(self) -> str:
         """Generate a hash for the document content using SHA-3 for maximum collision resistance"""

src/sqlite_rag/sqliterag.py

@@ -103,7 +103,7 @@ def add(
                     if use_relative_paths
                     else str(file_path.absolute())
                 )
-                document = Document(content=content, uri=uri, metadata=metadata)
+                document = Document(content=content, uri=uri, metadata=metadata.copy())
 
                 exists = self._repository.document_exists_by_hash(document.hash())
                 if exists:
@@ -132,7 +132,7 @@ def add_text(
         """Add a text content into the database"""
         self._ensure_initialized()
 
-        document = Document(content=text, uri=uri, metadata=metadata)
+        document = Document(content=text, uri=uri, metadata=metadata.copy())
 
         self._engine.create_new_context()
         document = self._engine.process(document)

tests/test_sqlite_rag.py

@@ -141,6 +141,33 @@ def test_add_file_with_metadata(self):
         assert doc[0] == "This is a test document with metadata."
         assert doc[1] == json.dumps(metadata)
 
+    def test_add_documents_with_generated_title(self):
+        with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as doc1:
+            doc1.write("# Title 1\nThis is the second test document.")
+        with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as doc2:
+            doc2.write("# Title 2\nThis is the second test document.")
+
+        doc3 = "# Title 3\nThis is the third test document."
+        doc4 = "# Title 4\nThis is the fourth test document."
+
+        rag = SQLiteRag.create(db_path=":memory:")
+
+        rag.add(doc1.name)
+        rag.add(doc2.name)
+        rag.add_text(doc3)
+        rag.add_text(doc4)
+
+        conn = rag._conn
+        cursor = conn.execute("SELECT metadata FROM documents")
+        docs = cursor.fetchall()
+        assert len(docs) == 4
+
+        titles = [json.loads(doc[0]).get("generated", {}).get("title") for doc in docs]
+        assert "Title 1" in titles
+        assert "Title 2" in titles
+        assert "Title 3" in titles
+        assert "Title 4" in titles
+
     def test_add_empty_file(self):
         with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f:
             temp_file_path = f.name