vortexdb 0.1.0__py3-none-any.whl

vortexdb/grpc/vector_db_pb2_grpc.py

@@ -0,0 +1,317 @@
+# Generated by the gRPC Python protocol compiler plugin. DO NOT EDIT!
+"""Client and server classes corresponding to protobuf-defined services."""
+import grpc
+import warnings
+
+from google.protobuf import empty_pb2 as google_dot_protobuf_dot_empty__pb2
+from . import vector_db_pb2 as vector__db__pb2
+
+GRPC_GENERATED_VERSION = '1.81.1'
+GRPC_VERSION = grpc.__version__
+_version_not_supported = False
+
+try:
+    from grpc._utilities import first_version_is_lower
+    _version_not_supported = first_version_is_lower(GRPC_VERSION, GRPC_GENERATED_VERSION)
+except ImportError:
+    _version_not_supported = True
+
+if _version_not_supported:
+    raise RuntimeError(
+        f'The grpc package installed is at version {GRPC_VERSION},'
+        + ' but the generated code in vector_db_pb2_grpc.py depends on'
+        + f' grpcio>={GRPC_GENERATED_VERSION}.'
+        + f' Please upgrade your grpc module to grpcio>={GRPC_GENERATED_VERSION}'
+        + f' or downgrade your generated code using grpcio-tools<={GRPC_VERSION}.'
+    )
+
+
+class VectorDBStub:
+    """Missing associated documentation comment in .proto file."""
+
+    def __init__(self, channel):
+        """Constructor.
+
+        Args:
+            channel: A grpc.Channel.
+        """
+        self.InsertVector = channel.unary_unary(
+                '/vectordb.VectorDB/InsertVector',
+                request_serializer=vector__db__pb2.InsertVectorRequest.SerializeToString,
+                response_deserializer=vector__db__pb2.PointID.FromString,
+                _registered_method=True)
+        self.DeletePoint = channel.unary_unary(
+                '/vectordb.VectorDB/DeletePoint',
+                request_serializer=vector__db__pb2.PointID.SerializeToString,
+                response_deserializer=google_dot_protobuf_dot_empty__pb2.Empty.FromString,
+                _registered_method=True)
+        self.GetPoint = channel.unary_unary(
+                '/vectordb.VectorDB/GetPoint',
+                request_serializer=vector__db__pb2.PointID.SerializeToString,
+                response_deserializer=vector__db__pb2.Point.FromString,
+                _registered_method=True)
+        self.SearchPoints = channel.unary_unary(
+                '/vectordb.VectorDB/SearchPoints',
+                request_serializer=vector__db__pb2.SearchRequest.SerializeToString,
+                response_deserializer=vector__db__pb2.SearchResponse.FromString,
+                _registered_method=True)
+        self.InsertVectorsBatch = channel.unary_unary(
+                '/vectordb.VectorDB/InsertVectorsBatch',
+                request_serializer=vector__db__pb2.InsertVectorsBatchRequest.SerializeToString,
+                response_deserializer=vector__db__pb2.InsertVectorsBatchResponse.FromString,
+                _registered_method=True)
+        self.SearchPointsBatch = channel.unary_unary(
+                '/vectordb.VectorDB/SearchPointsBatch',
+                request_serializer=vector__db__pb2.SearchPointsBatchRequest.SerializeToString,
+                response_deserializer=vector__db__pb2.SearchPointsBatchResponse.FromString,
+                _registered_method=True)
+
+
+class VectorDBServicer:
+    """Missing associated documentation comment in .proto file."""
+
+    def InsertVector(self, request, context):
+        """Insert a vector with a payload and return the assigned PointID
+        """
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def DeletePoint(self, request, context):
+        """Delete a vector by its PointID
+        """
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def GetPoint(self, request, context):
+        """Get a vector and its payload by PointID
+        """
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def SearchPoints(self, request, context):
+        """Search for the k nearest vectors to a target vector given a distance function
+        """
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def InsertVectorsBatch(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+    def SearchPointsBatch(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+
+def add_VectorDBServicer_to_server(servicer, server):
+    rpc_method_handlers = {
+            'InsertVector': grpc.unary_unary_rpc_method_handler(
+                    servicer.InsertVector,
+                    request_deserializer=vector__db__pb2.InsertVectorRequest.FromString,
+                    response_serializer=vector__db__pb2.PointID.SerializeToString,
+            ),
+            'DeletePoint': grpc.unary_unary_rpc_method_handler(
+                    servicer.DeletePoint,
+                    request_deserializer=vector__db__pb2.PointID.FromString,
+                    response_serializer=google_dot_protobuf_dot_empty__pb2.Empty.SerializeToString,
+            ),
+            'GetPoint': grpc.unary_unary_rpc_method_handler(
+                    servicer.GetPoint,
+                    request_deserializer=vector__db__pb2.PointID.FromString,
+                    response_serializer=vector__db__pb2.Point.SerializeToString,
+            ),
+            'SearchPoints': grpc.unary_unary_rpc_method_handler(
+                    servicer.SearchPoints,
+                    request_deserializer=vector__db__pb2.SearchRequest.FromString,
+                    response_serializer=vector__db__pb2.SearchResponse.SerializeToString,
+            ),
+            'InsertVectorsBatch': grpc.unary_unary_rpc_method_handler(
+                    servicer.InsertVectorsBatch,
+                    request_deserializer=vector__db__pb2.InsertVectorsBatchRequest.FromString,
+                    response_serializer=vector__db__pb2.InsertVectorsBatchResponse.SerializeToString,
+            ),
+            'SearchPointsBatch': grpc.unary_unary_rpc_method_handler(
+                    servicer.SearchPointsBatch,
+                    request_deserializer=vector__db__pb2.SearchPointsBatchRequest.FromString,
+                    response_serializer=vector__db__pb2.SearchPointsBatchResponse.SerializeToString,
+            ),
+    }
+    generic_handler = grpc.method_handlers_generic_handler(
+            'vectordb.VectorDB', rpc_method_handlers)
+    server.add_generic_rpc_handlers((generic_handler,))
+    server.add_registered_method_handlers('vectordb.VectorDB', rpc_method_handlers)
+
+
+ # This class is part of an EXPERIMENTAL API.
+class VectorDB:
+    """Missing associated documentation comment in .proto file."""
+
+    @staticmethod
+    def InsertVector(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(
+            request,
+            target,
+            '/vectordb.VectorDB/InsertVector',
+            vector__db__pb2.InsertVectorRequest.SerializeToString,
+            vector__db__pb2.PointID.FromString,
+            options,
+            channel_credentials,
+            insecure,
+            call_credentials,
+            compression,
+            wait_for_ready,
+            timeout,
+            metadata,
+            _registered_method=True)
+
+    @staticmethod
+    def DeletePoint(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(
+            request,
+            target,
+            '/vectordb.VectorDB/DeletePoint',
+            vector__db__pb2.PointID.SerializeToString,
+            google_dot_protobuf_dot_empty__pb2.Empty.FromString,
+            options,
+            channel_credentials,
+            insecure,
+            call_credentials,
+            compression,
+            wait_for_ready,
+            timeout,
+            metadata,
+            _registered_method=True)
+
+    @staticmethod
+    def GetPoint(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(
+            request,
+            target,
+            '/vectordb.VectorDB/GetPoint',
+            vector__db__pb2.PointID.SerializeToString,
+            vector__db__pb2.Point.FromString,
+            options,
+            channel_credentials,
+            insecure,
+            call_credentials,
+            compression,
+            wait_for_ready,
+            timeout,
+            metadata,
+            _registered_method=True)
+
+    @staticmethod
+    def SearchPoints(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(
+            request,
+            target,
+            '/vectordb.VectorDB/SearchPoints',
+            vector__db__pb2.SearchRequest.SerializeToString,
+            vector__db__pb2.SearchResponse.FromString,
+            options,
+            channel_credentials,
+            insecure,
+            call_credentials,
+            compression,
+            wait_for_ready,
+            timeout,
+            metadata,
+            _registered_method=True)
+
+    @staticmethod
+    def InsertVectorsBatch(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(
+            request,
+            target,
+            '/vectordb.VectorDB/InsertVectorsBatch',
+            vector__db__pb2.InsertVectorsBatchRequest.SerializeToString,
+            vector__db__pb2.InsertVectorsBatchResponse.FromString,
+            options,
+            channel_credentials,
+            insecure,
+            call_credentials,
+            compression,
+            wait_for_ready,
+            timeout,
+            metadata,
+            _registered_method=True)
+
+    @staticmethod
+    def SearchPointsBatch(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(
+            request,
+            target,
+            '/vectordb.VectorDB/SearchPointsBatch',
+            vector__db__pb2.SearchPointsBatchRequest.SerializeToString,
+            vector__db__pb2.SearchPointsBatchResponse.FromString,
+            options,
+            channel_credentials,
+            insecure,
+            call_credentials,
+            compression,
+            wait_for_ready,
+            timeout,
+            metadata,
+            _registered_method=True)

vortexdb/models.py

@@ -0,0 +1,131 @@
+from dataclasses import dataclass
+from enum import Enum
+from typing import List
+from vortexdb.grpc import vector_db_pb2
+
+
+# I found this to be a good idea, because 
+# 1. readability
+# 2. will help in HTTP client
+# 3. transport conversion at the very end, won't break if proto enum changes
+
+class Similarity(Enum):
+    EUCLIDEAN = "euclidean"
+    MANHATTAN = "manhattan"
+    HAMMING = "hamming"
+    COSINE = "cosine"
+
+    def to_proto(self) -> int:
+        return {
+            Similarity.EUCLIDEAN: vector_db_pb2.Euclidean,
+            Similarity.MANHATTAN: vector_db_pb2.Manhattan,
+            Similarity.HAMMING: vector_db_pb2.Hamming,
+            Similarity.COSINE: vector_db_pb2.Cosine,
+        }[self]
+
+
+class ContentType(Enum):
+    TEXT = "text"
+    IMAGE = "image"
+
+    def to_proto(self) -> int:
+        return {
+            ContentType.TEXT: vector_db_pb2.Text,
+            ContentType.IMAGE: vector_db_pb2.Image,
+        }[self]
+
+    @staticmethod
+    def from_proto(value: int) -> "ContentType":
+        return {
+            vector_db_pb2.Text: ContentType.TEXT,
+            vector_db_pb2.Image: ContentType.IMAGE,
+        }[value]
+
+
+# TODO Extend support to other data types than lists or tuples (numpy arrays probably)
+# TODO Further compatibility to allow conversions directly to numpy arrays (similar to .to_list())
+@dataclass(frozen=True)
+class DenseVector:
+    values: List[float]
+
+    def __post_init__(self):
+        if not isinstance(self.values, (list, tuple)):
+            raise TypeError("DenseVector expects a list or tuple of floats")
+
+        if not self.values:
+            raise ValueError("DenseVector cannot be empty")
+
+        for v in self.values:
+            if not isinstance(v, (int, float)):
+                raise TypeError(
+                    "DenseVector values must be numeric (int or float)"
+                )
+
+        # force float normalization
+        object.__setattr__(self, "values", [float(v) for v in self.values])
+    
+    def to_proto(self) -> vector_db_pb2.DenseVector:
+        return vector_db_pb2.DenseVector(values=self.values)
+    
+    def to_list(self) -> list[float]:
+        return list(self.values)
+
+
+
+
+@dataclass(frozen=True)
+class Payload:
+    content_type: ContentType
+    content: str
+
+    @staticmethod
+    def text(content: str) -> "Payload":
+        return Payload(ContentType.TEXT, content)
+
+    @staticmethod
+    def image(content: str) -> "Payload":
+        return Payload(ContentType.IMAGE, content)
+
+    def __post_init__(self):
+        if not isinstance(self.content_type, ContentType):
+            raise TypeError("content_type must be ContentType enum")
+
+
+    def to_proto(self) -> vector_db_pb2.Payload:
+        return vector_db_pb2.Payload(
+            content_type=self.content_type.to_proto(),
+            content=self.content,
+        )
+
+
+@dataclass(frozen=True)
+class Point:
+    id: str
+    vector: DenseVector
+    payload: Payload
+
+    @staticmethod
+    def from_proto(proto: vector_db_pb2.Point) -> "Point":
+        payload = proto.payload
+        if payload is None:
+            payload_obj = Payload.text("")
+        else:
+            payload_obj = Payload(
+                content_type=ContentType.from_proto(payload.content_type),
+                content=payload.content,
+            )
+
+        return Point(
+            id=proto.id.id.value,
+            vector=DenseVector(list(proto.vector.values)),
+            payload=payload_obj,
+        )
+    
+    def pretty(self) -> str:
+        return (
+            f"\nPoint:\n id = {self.id},\n"
+            f" vector_dim = {len(self.vector.values)},\n"
+            f" vector = {self.vector},\n"
+            f" payload_type = {self.payload.content_type.name},\n"
+            f" payload = '{self.payload.content}'"
+        )

vortexdb/protoutils.py

@@ -0,0 +1,64 @@
+from vortexdb.grpc import vector_db_pb2
+from vortexdb.models import DenseVector, Payload, Similarity
+
+
+def build_insert_request(
+    *,
+    vector: DenseVector,
+    payload: Payload,
+) -> vector_db_pb2.InsertVectorRequest:
+    return vector_db_pb2.InsertVectorRequest(
+        vector=vector.to_proto(),
+        payload=payload.to_proto(),
+    )
+
+
+def build_batch_insert_request(
+    *,
+    points: list[tuple[DenseVector, Payload]],
+) -> vector_db_pb2.InsertVectorsBatchRequest:
+    return vector_db_pb2.InsertVectorsBatchRequest(
+        vectors=[
+            build_insert_request(vector=vector, payload=payload)
+            for vector, payload in points
+        ]
+    )
+
+
+def build_point_id_request(point_id: str) -> vector_db_pb2.PointID:
+    return vector_db_pb2.PointID(
+        id=vector_db_pb2.UUID(value=point_id)
+    )
+
+
+def build_search_request(
+    *,
+    vector: DenseVector,
+    similarity: Similarity,
+    limit: int,
+    ef: int | None = None,
+) -> vector_db_pb2.SearchRequest:
+    return vector_db_pb2.SearchRequest(
+        query_vector=vector.to_proto(),
+        similarity=similarity.to_proto(),
+        limit=limit,
+        ef=ef or 0,
+    )
+
+
+def build_batch_search_request(
+    *,
+    queries: list[tuple[DenseVector, Similarity, int]],
+    ef: int | None = None,
+) -> vector_db_pb2.SearchPointsBatchRequest:
+    return vector_db_pb2.SearchPointsBatchRequest(
+        queries=[
+            build_search_request(
+                vector=vector,
+                similarity=similarity,
+                limit=limit,
+                ef=ef,
+            )
+            for vector, similarity, limit in queries
+        ]
+    )