linkml-store 0.0.0__tar.gz → 0.1.7__tar.gz

{linkml_store-0.0.0 → linkml_store-0.1.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: linkml-store
-Version: 0.0.0
+Version: 0.1.7
 Summary: linkml-store
 License: MIT
 Author: Author 1
@@ -14,17 +14,25 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Provides-Extra: analytics
 Provides-Extra: app
+Provides-Extra: chromadb
+Provides-Extra: h5py
 Provides-Extra: llm
+Provides-Extra: map
 Provides-Extra: mongodb
 Provides-Extra: tests
+Provides-Extra: validation
 Requires-Dist: black (>=24.0.0) ; extra == "tests"
+Requires-Dist: chromadb ; extra == "chromadb"
 Requires-Dist: click
 Requires-Dist: duckdb (>=0.10.1,<0.11.0)
-Requires-Dist: duckdb-engine (>=0.11.2,<0.12.0)
+Requires-Dist: duckdb-engine (>=0.11.2)
+Requires-Dist: h5py ; extra == "h5py"
+Requires-Dist: linkml ; extra == "validation"
 Requires-Dist: linkml-runtime (>=1.7.5,<2.0.0)
+Requires-Dist: linkml_map ; extra == "map"
 Requires-Dist: llm ; extra == "llm"
 Requires-Dist: matplotlib ; extra == "analytics"
-Requires-Dist: pandas (>=2.2.1,<3.0.0) ; extra == "analytics"
+Requires-Dist: pandas (>=2.2.1) ; extra == "analytics"
 Requires-Dist: plotly ; extra == "analytics"
 Requires-Dist: pydantic (>=2.0.0,<3.0.0)
 Requires-Dist: pymongo ; extra == "mongodb"
@@ -36,9 +44,12 @@ Description-Content-Type: text/markdown
 
 # linkml-store
 
-This is the project description.
+An integration layer for multiple database backends
 
-# Acknowledgements
+Currently this software is alpha, and has only been tested with DuckDB backends. See the Tutorial for more information.
 
-This [cookiecutter](https://cookiecutter.readthedocs.io/en/stable/README.html) project was developed from the [monarch-project-template](https://github.com/monarch-initiative/monarch-project-template) template and will be kept up-to-date using [cruft](https://cruft.github.io/cruft/).
+There is also experimental support for vector-based indexing using OpenAI test embedding via the `llm` library.
+
+The goals of this project are to provide high level access to data stored in heterogeneous databases,
+with optional schema management using LinkML.
 

linkml_store-0.1.7/README.md

@@ -0,0 +1,10 @@
+# linkml-store
+
+An integration layer for multiple database backends
+
+Currently this software is alpha, and has only been tested with DuckDB backends. See the Tutorial for more information.
+
+There is also experimental support for vector-based indexing using OpenAI test embedding via the `llm` library.
+
+The goals of this project are to provide high level access to data stored in heterogeneous databases,
+with optional schema management using LinkML.

{linkml_store-0.0.0 → linkml_store-0.1.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "linkml-store"
-version = "0.0.0"
+version = "0.1.7"
 description = "linkml-store"
 authors = ["Author 1 <author@org.org>"]
 license = "MIT"
@@ -14,7 +14,7 @@ linkml-runtime = "^1.7.5"
 streamlit = { version = "^1.32.2", optional = true }
 sqlalchemy = "*"
 duckdb = "^0.10.1"
-duckdb-engine = "^0.11.2"
+duckdb-engine = ">=0.11.2"
 matplotlib = { version = "*", optional = true }
 seaborn = { version = "*", optional = true }
 plotly = { version = "*", optional = true }
@@ -22,7 +22,11 @@ pystow = "^0.5.4"
 black = { version=">=24.0.0", optional = true }
 llm = { version="*", optional = true }
 pymongo = { version="*", optional = true }
-pandas = "^2.2.1"
+chromadb = { version="*", optional = true }
+h5py = { version="*", optional = true }
+linkml = { version="*", optional = true }
+linkml_map = { version="*", optional = true }
+pandas = ">=2.2.1"
 
 [tool.poetry.group.dev.dependencies]
 pytest = {version = ">=7.1.2"}
@@ -32,7 +36,9 @@ sphinx = {version = ">=6.1.3"}
 sphinx-rtd-theme = {version = ">=1.0.0"}
 sphinx-autodoc-typehints = {version = "<2.0.0"}
 sphinx-click = {version = ">=4.3.0"}
+sphinx-automodapi = "*"
 myst-parser = {version = ">=0.18.1"}
+furo = {version = "*"}
 nbsphinx = "*"
 jupyter = "*"
 
@@ -50,9 +56,13 @@ app = ["streamlit"]
 tests = ["black"]
 llm = ["llm"]
 mongodb = ["pymongo"]
+chromadb = ["chromadb"]
+h5py = ["h5py"]
+validation = ["linkml"]
+map = ["linkml_map"]
 
 [tool.poetry.scripts]
-linkml-store = "linkml_store.cli:main"
+linkml-store = "linkml_store.cli:cli"
 
 [tool.poetry-dynamic-versioning]
 enable = false

{linkml_store-0.0.0 → linkml_store-0.1.7}/src/linkml_store/api/__init__.py

@@ -1,8 +1,8 @@
 # flake8: noqa: E402
 from linkml_store.api.collection import Collection
 from linkml_store.api.database import Database
-from linkml_store.api.metadata import MetaData
 from linkml_store.api.client import Client
+
 # flake8: noqa
 
-__all__ = ["Client", "Database", "MetaData", "Collection"]
+__all__ = ["Client", "Database", "Collection"]

{linkml_store-0.0.0 → linkml_store-0.1.7}/src/linkml_store/api/client.py

@@ -1,20 +1,31 @@
-from dataclasses import dataclass
-from typing import Dict, Optional
+from pathlib import Path
+from typing import Dict, Optional, Union
 
+import yaml
 from linkml_runtime import SchemaView
 
 from linkml_store.api import Database
+from linkml_store.api.config import ClientConfig
+from linkml_store.api.stores.chromadb.chromadb_database import ChromaDBDatabase
 from linkml_store.api.stores.duckdb.duckdb_database import DuckDBDatabase
+from linkml_store.api.stores.mongodb.mongodb_database import MongoDBDatabase
+from linkml_store.api.stores.solr.solr_database import SolrDatabase
 
 HANDLE_MAP = {
     "duckdb": DuckDBDatabase,
+    "solr": SolrDatabase,
+    "mongodb": MongoDBDatabase,
+    "chromadb": ChromaDBDatabase,
 }
 
 
-@dataclass
 class Client:
     """
-    A client provides access to named collections.
+    A client is the top-level object for interacting with databases.
+
+    A client has access to one or more :class:`Database` objects.
+
+    Each database consists of a number of :class:`.Collection` objects.
 
     Examples
     --------
@@ -22,7 +33,7 @@ class Client:
     >>> db = client.attach_database("duckdb", alias="test")
     >>> collection = db.create_collection("Person")
     >>> objs = [{"id": "P1", "name": "John", "age_in_years": 30}, {"id": "P2", "name": "Alice", "age_in_years": 25}]
-    >>> collection.add(objs)
+    >>> collection.insert(objs)
     >>> qr = collection.find()
     >>> len(qr.rows)
     2
@@ -38,9 +49,76 @@ class Client:
 
     """
 
-    handle: Optional[str] = None
+    metadata: Optional[ClientConfig] = None
     _databases: Optional[Dict[str, Database]] = None
 
+    def __init__(self, handle: Optional[str] = None, metadata: Optional[ClientConfig] = None):
+        """
+        Initialize a client.
+
+        :param handle:
+        :param metadata:
+        """
+        self.metadata = metadata
+        if not self.metadata:
+            self.metadata = ClientConfig()
+        self.metadata.handle = handle
+
+    @property
+    def handle(self) -> Optional[str]:
+        return self.metadata.handle
+
+    @property
+    def base_dir(self) -> Optional[str]:
+        """
+        Get the base directory for the client.
+
+        Wraps metadata.base_dir.
+
+        :return:
+        """
+        return self.metadata.base_dir
+
+    def from_config(self, config: Union[ClientConfig, str, Path], base_dir=None, **kwargs):
+        """
+        Create a client from a configuration.
+
+        Examples
+        --------
+        >>> from linkml_store.api.config import ClientConfig
+        >>> client = Client().from_config(ClientConfig(databases={"test": {"handle": "duckdb:///:memory:"}}))
+        >>> len(client.databases)
+        1
+        >>> "test" in client.databases
+        True
+        >>> client.databases["test"].handle
+        'duckdb:///:memory:'
+
+        :param config:
+        :param kwargs:
+        :return:
+
+        """
+        if isinstance(config, Path):
+            config = str(config)
+        if isinstance(config, str):
+            if not base_dir:
+                base_dir = Path(config).parent
+            parsed_obj = yaml.safe_load(open(config))
+            config = ClientConfig(**parsed_obj)
+        self.metadata = config
+        if base_dir:
+            self.metadata.base_dir = base_dir
+        self._initialize_databases(**kwargs)
+        return self
+
+    def _initialize_databases(self, **kwargs):
+        for name, db_config in self.metadata.databases.items():
+            handle = db_config.handle.format(base_dir=self.base_dir)
+            db_config.handle = handle
+            db = self.attach_database(handle, alias=name, **kwargs)
+            db.from_config(db_config)
+
     def attach_database(
         self,
         handle: str,
@@ -69,7 +147,6 @@ class Client:
         :param schema_view: schema view to associate with the database
         :param kwargs:
         :return:
-
         """
         if ":" not in handle:
             scheme = handle
@@ -87,6 +164,7 @@ class Client:
         if not self._databases:
             self._databases = {}
         self._databases[alias] = db
+        db.parent = self
         return db
 
     def get_database(self, name: Optional[str] = None, create_if_not_exists=True, **kwargs) -> Database:
@@ -101,7 +179,7 @@ class Client:
         >>> db == retrieved_db
         True
 
-        :param name:
+        :param name: if None, there must be a single database attached
         :param create_if_not_exists:
         :param kwargs:
         :return:
@@ -149,3 +227,30 @@ class Client:
         if not self._databases:
             self._databases = {}
         return self._databases
+
+    def drop_database(self, name: str, missing_ok=False, **kwargs):
+        """
+        Drop a database.
+
+        :param name:
+        :param missing_ok:
+        :return:
+        """
+        if name in self._databases:
+            db = self._databases[name]
+            db.drop(**kwargs)
+            del self._databases[name]
+        else:
+            if not missing_ok:
+                raise ValueError(f"Database {name} not found")
+
+    def drop_all_databases(self, **kwargs):
+        """
+        Drop all databases.
+
+        :param missing_ok:
+        :return:
+        """
+        for name in list(self._databases.keys()):
+            self.drop_database(name, missing_ok=False, **kwargs)
+        self._databases = {}