Vector client release 0.4.0

.flake8

@@ -0,0 +1,4 @@
+[flake8]
+ignore = E501
+max-line-length = 88 # black compatability
+ignore = E501, E203  # black compatability

.gitignore

@@ -155,3 +155,11 @@ cython_debug/
 # PyCharm
 .idea/
 
+# Vector search test files
+tests/siftsmall/*
+tests/siftsmall.tar.gz
+
+# Notes
+notes.txt
+
+public-key.asc

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/conf.py

@@ -0,0 +1,36 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# For the full list of built-in configuration values, see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Project information -----------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
+import os
+import sys
+sys.path.insert(0, os.path.abspath('../src/aerospike_vector'))
+import sphinx.ext.autodoc
+
+project = 'D'
+copyright = '2024, D'
+author = 'D'
+release = 'D'
+
+# -- General configuration ---------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
+
+extensions = [
+    # Other extensions...
+    'sphinx.ext.autodoc',
+]
+
+
+templates_path = ['_templates']
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+
+
+
+# -- Options for HTML output -------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
+
+html_theme = 'sphinx_rtd_theme'
+html_static_path = ['_static']

docs/index.rst

@@ -0,0 +1,20 @@
+.. D documentation master file, created by
+   sphinx-quickstart on Sun Apr  7 22:14:55 2024.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Welcome to D's documentation! SCOBEDY BABALOUIE
+=============================
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Contents:
+
+   vectordb_client
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`

docs/make.bat

@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=.
+set BUILDDIR=_build
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

docs/vectodb_client.rst

@@ -0,0 +1,4 @@
+.. automodule:: aerospike_vector.vectordb_client
+   :members:
+   :undoc-members:
+   :show-inheritance:

pyproject.toml

@@ -8,7 +8,7 @@ description = "Aerospike Proximus Client Library for Python"
 authors = [
     { name = "Aerospike, Inc.", email = "[email protected]" }
 ]
-readme = "README.rst"
+readme = "README.md"
 license = { text = "Apache Software License" }
 keywords = ["aerospike", "vector", "database", "ANN"]
 classifiers = [
@@ -22,7 +22,7 @@ classifiers = [
     "Programming Language :: Python :: Implementation :: CPython",
     "Topic :: Database"
 ]
-version = "0.3.2.dev1"
+version = "0.4.0dev1"
 requires-python = ">3.8"
 dependencies = [
     "grpcio",

src/aerospike_vector/__init__.py

@@ -1 +1,4 @@
+import logging
 name = "aerospike_vector"
+
+logging.getLogger(__name__).addHandler(logging.NullHandler())

src/aerospike_vector/conversions.py

@@ -18,20 +18,28 @@ def toVectorDbValue(value: Any) -> types_pb2.Value:
         if isinstance(value[0], float):
             return types_pb2.Value(
                 vectorValue=types_pb2.Vector(
-                    floatData={"value": [float(x) for x in value]}))
+                    floatData={"value": [float(x) for x in value]}
+                )
+            )
         elif isinstance(value[0], bool):
             return types_pb2.Value(
                 vectorValue=types_pb2.Vector(
-                    boolData={"value": [True if x else False for x in value]}))
+                    boolData={"value": [True if x else False for x in value]}
+                )
+            )
         else:
             return types_pb2.Value(
-                listValue=types_pb2.List(
-                    entries=[toVectorDbValue(x) for x in value]))
+                listValue=types_pb2.List(entries=[toVectorDbValue(x) for x in value])
+            )
     elif isinstance(value, dict):
         d = types_pb2.Value(
-            mapValue=types_pb2.Map(entries=[
-                types_pb2.MapEntry(key=toMapKey(k), value=toVectorDbValue(v))
-                for k, v in value.items()]))
+            mapValue=types_pb2.Map(
+                entries=[
+                    types_pb2.MapEntry(key=toMapKey(k), value=toVectorDbValue(v))
+                    for k, v in value.items()
+                ]
+            )
+        )
         return d
     else:
         raise Exception("Invalid type " + str(type(value)))
@@ -61,7 +69,9 @@ def fromVectorDbKey(key: types_pb2.Key) -> types.Key:
     elif key.HasField("bytesValue"):
         keyValue = key.bytesValue
 
-    return types.Key(key.namespace, key.set, key.digest, keyValue)
+    return types.Key(
+        namespace=key.namespace, set=key.set, digest=key.digest, key=keyValue
+    )
 
 
 def fromVectorDbRecord(record: types_pb2.Record) -> dict[str, Any]:
@@ -72,11 +82,10 @@ def fromVectorDbRecord(record: types_pb2.Record) -> dict[str, Any]:
     return bins
 
 
-def fromVectorDbNeighbor(input: types_pb2.Neighbor) -> (
-        types.Neighbor):
-    return types.Neighbor(fromVectorDbKey(input.key),
-                          fromVectorDbRecord(input.record),
-                          input.distance)
+def fromVectorDbNeighbor(input: types_pb2.Neighbor) -> types.Neighbor:
+    return types.Neighbor(
+        key=fromVectorDbKey(input.key), bins=fromVectorDbRecord(input.record), distance=input.distance
+    )
 
 
 def fromVectorDbValue(input: types_pb2.Value) -> Any:

src/aerospike_vector/types.py

@@ -1,29 +1,140 @@
-from typing import Any
+import enum
+from typing import Any, Optional
+
+from . import types_pb2
 
 
 class HostPort(object):
-    def __init__(self, address: str, port: int, isTls=False):
-        self.address = address
+    def __init__(self, *, host: str, port: int, isTls: Optional[bool] = False) -> None:
+        self.host = host
         self.port = port
         self.isTls = isTls
 
 
 class Key(object):
-    def __init__(self, namespace: str, set: str, digest: bytearray, key: Any):
+    def __init__(
+        self, *, namespace: str, set: str, digest: bytearray, key: Any
+    ) -> None:
         self.namespace = namespace
         self.set = set
         self.digest = digest
         self.key = key
 
+    def __str__(self):
+        return f"Key: namespace='{self.namespace}', set='{self.set}', digest={self.digest}, key={self.key}"
+
 
 class RecordWithKey(object):
-    def __init__(self, key: Key, bins: dict[str, Any]):
+    def __init__(self, *, key: Key, bins: dict[str, Any]) -> None:
         self.key = key
         self.bins = bins
 
+    def __str__(self):
+        bins_info = ""
+        for key, value in self.bins.items():
+            if isinstance(value, list):
+                if len(value) > 4:
+                    value_str = (
+                        "[\n"
+                        + ",\n".join("\t\t\t{}".format(val) for val in value[:3])
+                        + ",\n\t\t\t...\n\t\t]"
+                    )
+                else:
+                    value_str = str(value)
+            else:
+                value_str = str(value)
+            bins_info += "\n\t\t{}: {}".format(key, value_str)
+        return "{{\n\t{},\n\tbins: {{\n{}\n\t}}\n}}".format(self.key, bins_info)
+
 
 class Neighbor(object):
-    def __init__(self, key: Key, bins: dict[str, Any], distance: float):
+    def __init__(self, *, key: Key, bins: dict[str, Any], distance: float) -> None:
         self.key = key
         self.bins = bins
         self.distance = distance
+
+    def __str__(self):
+        bins_info = ""
+        for key, value in self.bins.items():
+            if isinstance(value, list):
+                if len(value) > 4:
+                    value_str = (
+                        "[\n"
+                        + ",\n".join("\t\t\t{}".format(val) for val in value[:3])
+                        + ",\n\t\t\t...\n\t\t]"
+                    )
+                else:
+                    value_str = str(value)
+            else:
+                value_str = str(value)
+            bins_info += "\n\t\t{}: {}".format(key, value_str)
+        return "{{\n\t{},\n\tdistance: {},\n\tbins: {{\n{}\n\t}}\n}}".format(
+            self.key, self.distance, bins_info
+        )
+
+
+class VectorDistanceMetric(enum.Enum):
+    SQUARED_EUCLIDEAN: types_pb2.VectorDistanceMetric = (
+        types_pb2.VectorDistanceMetric.SQUARED_EUCLIDEAN
+    )
+    COSINE: types_pb2.VectorDistanceMetric = types_pb2.VectorDistanceMetric.COSINE
+    DOT_PRODUCT: types_pb2.VectorDistanceMetric = (
+        types_pb2.VectorDistanceMetric.DOT_PRODUCT
+    )
+    MANHATTAN: types_pb2.VectorDistanceMetric = types_pb2.VectorDistanceMetric.MANHATTAN
+    HAMMING: types_pb2.VectorDistanceMetric = types_pb2.VectorDistanceMetric.HAMMING
+
+
+class HnswBatchingParams(object):
+    def __init__(
+        self,
+        *,
+        max_records: Optional[int] = 10000,
+        interval: Optional[int] = 10000,
+        disabled: Optional[bool] = False,
+    ) -> None:
+        self.max_records = max_records
+        self.interval = interval
+        self.disabled = disabled
+
+    def to_pb2(self):
+        # Create an instance of HnswBatchingParams
+        params = types_pb2.HnswBatchingParams()
+        params.maxRecords = self.max_records
+        params.interval = self.interval
+        params.disabled = self.disabled
+        return params
+
+
+class HnswParams(object):
+    def __init__(
+        self,
+        *,
+        m: Optional[int] = 16,
+        ef_construction: Optional[int] = 100,
+        ef: Optional[int] = 100,
+        batching_params: Optional[HnswBatchingParams] = HnswBatchingParams(),
+    ) -> None:
+        self.m = m
+        self.ef_construction = ef_construction
+        self.ef = ef
+        self.batching_params = batching_params
+
+    def to_pb2(self):
+        # Create an instance of HnswParams
+        params = types_pb2.HnswParams()
+        params.m = self.m
+        params.efConstruction = self.ef_construction
+        params.ef = self.ef
+
+        # Assign HnswBatchingParams instance to HnswParams
+        params.batchingParams.CopyFrom(self.batching_params.to_pb2())
+        return params
+
+class HnswSearchParams(object):
+    def __init__(self, *, ef: Optional[int] = None) -> None:
+        self.ef = ef
+    def to_pb2(self):
+        params = types_pb2.HnswSearchParams()
+        params.ef = self.ef
+        return params