parakeet-index-docstore-sqlite 0.1.0__tar.gz

parakeet_index_docstore_sqlite-0.1.0/.gitignore

@@ -0,0 +1,85 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+#IDE
+.DS_Store
+.idea
+.vscode
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Mkdocs documentation
+docs/_build/
+docs/api_reference/site/
+
+# Ruff
+.ruff_cache/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+.python-version
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/

parakeet_index_docstore_sqlite-0.1.0/PKG-INFO

@@ -0,0 +1,22 @@
+Metadata-Version: 2.5
+Name: parakeet-index-docstore-sqlite
+Version: 0.1.0
+Summary: parakeet-index docstore sqlite integration
+Author-email: Leonardo Furnielis <leonardofurnielis@outlook.com>
+License: Apache-2.0
+Requires-Python: <3.14,>=3.11
+Requires-Dist: parakeet-index-core<0.2.0,>=0.1.2
+Requires-Dist: sqlalchemy<2.1.0,>=2.0.51
+Provides-Extra: dev
+Requires-Dist: pytest-asyncio<2.0.0,>=1.4.0; extra == 'dev'
+Requires-Dist: pytest<10.0.0,>=9.1.1; extra == 'dev'
+Requires-Dist: ruff<0.16.0,>=0.15.20; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# Parakeet Index docstore integration - SQLite
+
+## Installation
+
+```bash
+pip install parakeet-index-docstore-sqlite
+```

parakeet_index_docstore_sqlite-0.1.0/README.md

@@ -0,0 +1,7 @@
+# Parakeet Index docstore integration - SQLite
+
+## Installation
+
+```bash
+pip install parakeet-index-docstore-sqlite
+```

parakeet_index_docstore_sqlite-0.1.0/parakeet_index/docstore/sqlite/__init__.py

@@ -0,0 +1,3 @@
+from parakeet_index.docstore.sqlite.base import SQLiteDocStore
+
+__all__ = ["SQLiteDocStore"]

parakeet_index_docstore_sqlite-0.1.0/parakeet_index/docstore/sqlite/base.py

@@ -0,0 +1,147 @@
+from datetime import datetime, timezone
+from typing import Any
+
+from parakeet_index.core.bridge.pydantic import Field, PrivateAttr
+from parakeet_index.core.docstore import BaseDocStore
+from parakeet_index.core.document import Document
+
+
+class SQLiteDocStore(BaseDocStore):
+    """
+    SQLite-backed document store.
+
+    Attributes:
+        db_path (str): Path to the SQLite database file. Defaults to ``parakeet-index-docstore.db``.
+
+    Example:
+        ```python
+        from parakeet_index.docstore.sqlite import SQLiteDocStore
+
+        doc_store = SQLiteDocStore(db_path="./my-index.db")
+        ```
+    """
+
+    db_path: str = Field(
+        default="parakeet-index-docstore.db",
+        description="Path to the SQLite database file.",
+    )
+
+    _engine: Any = PrivateAttr()
+    _table: Any = PrivateAttr()
+
+    def model_post_init(self, __context):  # noqa: PYI063
+        from sqlalchemy import (
+            Column,
+            Index,
+            MetaData,
+            String,
+            Table,
+            Text,
+            create_engine,
+        )
+
+        self._engine = create_engine(f"sqlite:///{self.db_path}")
+
+        metadata = MetaData()
+        self._table = Table(
+            "parakeet_index_docstore",
+            metadata,
+            Column("doc_id", String, primary_key=True),
+            Column("doc_hash", String, nullable=False),
+            Column("text", Text, nullable=False),
+            Column("created_at", String, nullable=False),
+            Column("updated_at", String, nullable=False),
+            Index("idx_doc_hash", "doc_hash"),
+        )
+        metadata.create_all(self._engine)
+
+    @classmethod
+    def class_name(cls) -> str:
+        return "SQLiteDocStore"
+
+    def upsert_documents(self, documents: list[Document]) -> None:
+        """Insert or update document records."""
+        if not documents:
+            return
+
+        from sqlalchemy.dialects.sqlite import insert
+
+        now = datetime.now(timezone.utc).isoformat()
+
+        values = [
+            {
+                "doc_id": doc.id_,
+                "doc_hash": doc.hash,
+                "text": doc.get_content(),
+                "created_at": now,
+                "updated_at": now,
+            }
+            for doc in documents
+        ]
+
+        stmt = insert(self._table)
+        stmt = stmt.on_conflict_do_update(
+            index_elements=["doc_id"],
+            set_={
+                "doc_hash": stmt.excluded.doc_hash,
+                "text": stmt.excluded.text,
+                "updated_at": stmt.excluded.updated_at,
+            },
+        )
+
+        with self._engine.begin() as conn:
+            conn.execute(stmt, values)
+
+    def list_documents(self) -> list[Document]:
+        """Return all documents currently stored, including text."""
+        from sqlalchemy import select
+
+        stmt = select(
+            self._table.c.doc_id,
+            self._table.c.text,
+        )
+
+        with self._engine.connect() as conn:
+            rows = conn.execute(stmt).fetchall()
+
+        return [Document(id_=row[0], text=row[1]) for row in rows]
+
+    def delete_documents(self, ids: list[str]) -> None:
+        """Delete records by document ID."""
+        if not ids:
+            return
+
+        from sqlalchemy import delete
+
+        stmt = delete(self._table).where(self._table.c.doc_id.in_(ids))
+
+        with self._engine.begin() as conn:
+            conn.execute(stmt)
+
+    def get_document_hash(self, doc_id: str) -> str | None:
+        """Get the stored hash for a single document, if it exists."""
+        from sqlalchemy import select
+
+        stmt = select(self._table.c.doc_hash).where(self._table.c.doc_id == doc_id)
+
+        with self._engine.connect() as conn:
+            row = conn.execute(stmt).fetchone()
+
+        return row[0] if row is not None else None
+
+    def get_document(self, doc_id: str) -> Document | None:
+        """Return a single document record by Id, including text."""
+        from sqlalchemy import select
+
+        stmt = select(
+            self._table.c.doc_id,
+            self._table.c.text,
+        ).where(self._table.c.doc_id == doc_id)
+
+        with self._engine.connect() as conn:
+            row = conn.execute(stmt).fetchone()
+
+        if row is None:
+            return None
+
+        return Document(id_=row[0], text=row[1])

parakeet_index_docstore_sqlite-0.1.0/pyproject.toml

@@ -0,0 +1,29 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "parakeet-index-docstore-sqlite"
+version = "0.1.0"
+description = "parakeet-index docstore sqlite integration"
+authors = [{ name = "Leonardo Furnielis", email = "leonardofurnielis@outlook.com" }]
+license = { text = "Apache-2.0" }
+readme = "README.md"
+requires-python = ">=3.11,<3.14"
+dependencies = [
+    "sqlalchemy>=2.0.51,<2.1.0",
+    "parakeet-index-core>=0.1.2,<0.2.0",
+]
+
+[tool.hatch.build.targets.sdist]
+include = ["parakeet_index/"]
+
+[tool.hatch.build.targets.wheel]
+include = ["parakeet_index/"]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=9.1.1,<10.0.0",
+    "pytest-asyncio>=1.4.0,<2.0.0",
+    "ruff>=0.15.20,<0.16.0",
+]