linkml-store 0.1.7__tar.gz → 0.1.9__tar.gz

{linkml_store-0.1.7 → linkml_store-0.1.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: linkml-store
-Version: 0.1.7
+Version: 0.1.9
 Summary: linkml-store
 License: MIT
 Author: Author 1
@@ -19,6 +19,7 @@ Provides-Extra: h5py
 Provides-Extra: llm
 Provides-Extra: map
 Provides-Extra: mongodb
+Provides-Extra: pyarrow
 Provides-Extra: tests
 Provides-Extra: validation
 Requires-Dist: black (>=24.0.0) ; extra == "tests"
@@ -27,6 +28,8 @@ Requires-Dist: click
 Requires-Dist: duckdb (>=0.10.1,<0.11.0)
 Requires-Dist: duckdb-engine (>=0.11.2)
 Requires-Dist: h5py ; extra == "h5py"
+Requires-Dist: jinja2 (>=3.1.4,<4.0.0)
+Requires-Dist: jsonlines (>=4.0.0,<5.0.0)
 Requires-Dist: linkml ; extra == "validation"
 Requires-Dist: linkml-runtime (>=1.7.5,<2.0.0)
 Requires-Dist: linkml_map ; extra == "map"
@@ -34,6 +37,7 @@ Requires-Dist: llm ; extra == "llm"
 Requires-Dist: matplotlib ; extra == "analytics"
 Requires-Dist: pandas (>=2.2.1) ; extra == "analytics"
 Requires-Dist: plotly ; extra == "analytics"
+Requires-Dist: pyarrow ; extra == "pyarrow"
 Requires-Dist: pydantic (>=2.0.0,<3.0.0)
 Requires-Dist: pymongo ; extra == "mongodb"
 Requires-Dist: pystow (>=0.5.4,<0.6.0)
@@ -53,3 +57,5 @@ There is also experimental support for vector-based indexing using OpenAI test e
 The goals of this project are to provide high level access to data stored in heterogeneous databases,
 with optional schema management using LinkML.
 
+See [these slides](https://docs.google.com/presentation/d/e/2PACX-1vSgtWUNUW0qNO_ZhMAGQ6fYhlXZJjBNMYT0OiZz8DDx8oj7iG9KofRs6SeaMXBBOICGknoyMG2zaHnm/embed?start=false&loop=false&delayms=3000) for more details
+

{linkml_store-0.1.7 → linkml_store-0.1.9}/README.md

@@ -8,3 +8,5 @@ There is also experimental support for vector-based indexing using OpenAI test e
 
 The goals of this project are to provide high level access to data stored in heterogeneous databases,
 with optional schema management using LinkML.
+
+See [these slides](https://docs.google.com/presentation/d/e/2PACX-1vSgtWUNUW0qNO_ZhMAGQ6fYhlXZJjBNMYT0OiZz8DDx8oj7iG9KofRs6SeaMXBBOICGknoyMG2zaHnm/embed?start=false&loop=false&delayms=3000) for more details

{linkml_store-0.1.7 → linkml_store-0.1.9}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "linkml-store"
-version = "0.1.7"
+version = "0.1.9"
 description = "linkml-store"
 authors = ["Author 1 <author@org.org>"]
 license = "MIT"
@@ -23,10 +23,13 @@ black = { version=">=24.0.0", optional = true }
 llm = { version="*", optional = true }
 pymongo = { version="*", optional = true }
 chromadb = { version="*", optional = true }
+pyarrow = { version="*", optional = true }
 h5py = { version="*", optional = true }
 linkml = { version="*", optional = true }
 linkml_map = { version="*", optional = true }
 pandas = ">=2.2.1"
+jinja2 = "^3.1.4"
+jsonlines = "^4.0.0"
 
 [tool.poetry.group.dev.dependencies]
 pytest = {version = ">=7.1.2"}
@@ -41,6 +44,8 @@ myst-parser = {version = ">=0.18.1"}
 furo = {version = "*"}
 nbsphinx = "*"
 jupyter = "*"
+jupysql = "*"
+papermill = "*"
 
 [tool.poetry.group.tests.dependencies]
 pytest = "^7.4.0"
@@ -58,6 +63,7 @@ llm = ["llm"]
 mongodb = ["pymongo"]
 chromadb = ["chromadb"]
 h5py = ["h5py"]
+pyarrow = ["pyarrow"]
 validation = ["linkml"]
 map = ["linkml_map"]
 
@@ -125,7 +131,7 @@ skip = '.git,*.pdf,*.svg,./tests,pyproject.toml,*.dill,poetry.lock,*.ipynb'
 # Ignore table where words could be split across rows
 # Ignore shortcut specifications like [Ff]alse
 ignore-regex = '(\|.*\|.*\|.*\||\[[A-Z][a-z]\][a-z][a-z])'
-ignore-words-list = 'mater,connexion,infarction'
+ignore-words-list = 'mater,connexion,infarction,nin'
 count = ""
 quiet-level = 3
 

{linkml_store-0.1.7 → linkml_store-0.1.9}/src/linkml_store/api/client.py

@@ -1,3 +1,4 @@
+import logging
 from pathlib import Path
 from typing import Dict, Optional, Union
 
@@ -8,14 +9,19 @@ 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.filesystem.filesystem_database import FileSystemDatabase
 from linkml_store.api.stores.mongodb.mongodb_database import MongoDBDatabase
 from linkml_store.api.stores.solr.solr_database import SolrDatabase
 
+logger = logging.getLogger(__name__)
+
+
 HANDLE_MAP = {
     "duckdb": DuckDBDatabase,
     "solr": SolrDatabase,
     "mongodb": MongoDBDatabase,
     "chromadb": ChromaDBDatabase,
+    "file": FileSystemDatabase,
 }
 
 
@@ -23,14 +29,27 @@ class Client:
     """
     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.
+    * A client has access to one or more :class:`.Database` objects.
+    * Each database consists of a number of :class:`.Collection` objects.
 
-    Examples
-    --------
+    Creating a client
+    -----------------
     >>> client = Client()
+
+    Attaching a database
+    --------------------
     >>> db = client.attach_database("duckdb", alias="test")
+
+    Note that normally a handle would be specified by a locator such as ``duckdb:///<PATH>``, but
+    for convenience, an in-memory duckdb object can be specified without a full locator
+
+    We can check the actual handle:
+
+    >>> db.handle
+    'duckdb:///:memory:'
+
+    Creating a new collection
+    -------------------------
     >>> collection = db.create_collection("Person")
     >>> objs = [{"id": "P1", "name": "John", "age_in_years": 30}, {"id": "P2", "name": "Alice", "age_in_years": 25}]
     >>> collection.insert(objs)
@@ -151,6 +170,8 @@ class Client:
         if ":" not in handle:
             scheme = handle
             handle = None
+            if alias is None:
+                alias = scheme
         else:
             scheme, _ = handle.split(":", 1)
         if scheme not in HANDLE_MAP:
@@ -165,6 +186,11 @@ class Client:
             self._databases = {}
         self._databases[alias] = db
         db.parent = self
+        if db.alias:
+            if db.alias != alias:
+                raise AssertionError(f"Inconsistent alias: {db.alias} != {alias}")
+        else:
+            db.metadata.alias = alias
         return db
 
     def get_database(self, name: Optional[str] = None, create_if_not_exists=True, **kwargs) -> Database:
@@ -195,6 +221,7 @@ class Client:
             self._databases = {}
         if name not in self._databases:
             if create_if_not_exists:
+                logger.info(f"Creating database: {name}")
                 self.attach_database(name, **kwargs)
             else:
                 raise ValueError(f"Database {name} does not exist")