Added ML Sklearn Prediction Node

nodes/src/nodes/ml_sklearn/IGlobal.py

@@ -0,0 +1,48 @@
+# =============================================================================
+# MIT License
+# Copyright (c) 2026 Aparavi Software AG
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+# =============================================================================
+
+from rocketlib import IGlobalBase, OPEN_MODE
+from ai.common.preprocessor import PreProcessorBase
+
+
+class IGlobal(IGlobalBase):
+    preprocessor: PreProcessorBase | None = None
+
+    def beginGlobal(self):
+        # Are we in config mode or some other mode?
+        if self.IEndpoint.endpoint.openMode == OPEN_MODE.CONFIG:
+            # We are going to get a call to configureService but
+            # we don't actually need to load the driver for that
+            pass
+        else:
+            from .code import PreProcessor
+
+            # Get our bag
+            bag = self.IEndpoint.endpoint.bag
+
+            # Create the preprocessor
+            self.preprocessor = PreProcessor(self.glb.logicalType, self.glb.connConfig, bag)
+
+    def endGlobal(self):
+        # Destroy the preprocessor
+        self.preprocessor = None

nodes/src/nodes/ml_sklearn/Instance.py

@@ -0,0 +1,91 @@
+# =============================================================================
+# MIT License
+# Copyright (c) 2026 Aparavi Software AG
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+# =============================================================================
+
+from rocketlib import IInstanceBase, Entry, warning
+from typing import List
+from ai.common.schema import Doc, DocMetadata
+from . import IGlobal
+
+
+class IInstance(IInstanceBase):
+    IGlobal: IGlobal
+
+    chunkId: int = 0
+    tableId: int = 0
+
+    def _writeTableOrText(self, text: str, isTable: bool = False):
+        # Fill in the metadata
+        metadata = DocMetadata(
+            self,
+            chunkId=0,
+            isTable=isTable,
+            tableId=0,
+            isDeleted=False,
+        )
+
+        # Chunk the document
+        textChunks = self.IGlobal.preprocessor.process(text)
+        if not textChunks:
+            warning(f'The file {self.instance.currentObject.path} could not be processed, because it does not appear to contain supported source code in one of these languages: c/c++, python, javascript, typescript, typescript.')
+            return
+
+        # Create the documents
+        documents: List[Doc] = []
+        for chunk in textChunks:
+            # Create the document from it
+            document = Doc(page_content=chunk, metadata=metadata.model_copy())
+
+            # Assign the chunk id
+            document.metadata.chunkId = self.chunkId
+            self.chunkId = self.chunkId + 1
+
+            # If this is a table or not
+            if isTable:
+                self.tableId = self.tableId
+            else:
+                self.tableId = 0
+
+            # Append it to the list
+            documents.append(document)
+
+        # If there are no documents, done
+        if not len(documents):
+            return
+
+        # If this is a table
+        if isTable:
+            metadata.tableId = self.tableId
+            self.tableId += 1
+
+        # Write the documents
+        self.instance.writeDocuments(documents)
+
+    def open(self, object: Entry):
+        self.chunkId = 0
+        self.tableId = 0
+
+    def writeTable(self, table: str):
+        self._writeTableOrText(table, True)
+
+    def writeText(self, text: str):
+        self._writeTableOrText(text, False)

nodes/src/nodes/ml_sklearn/README.md

@@ -0,0 +1,20 @@
+# ML Sklearn Prediction Node
+
+This node performs predictions using a trained sklearn model.
+
+## Input
+- price (number)
+
+## Output
+- prediction (number)
+
+## Example
+Input:
+{
+  "price": 250
+}
+
+Output:
+{
+  "prediction": 3.5
+}

nodes/src/nodes/ml_sklearn/code.py

@@ -0,0 +1,33 @@
+import pickle
+import os
+
+class PreProcessor:
+    '''ML Sklearn Prediction Node'''
+
+    def __init__(self, *args, **kwargs):
+        '''Load trained sklearn model'''
+        model_path = os.path.join(os.path.dirname(__file__), 'model.pkl')
+        with open(model_path, 'rb') as f:
+            self.model = pickle.load(f)
+
+    def run(self, input_data):
+        try:
+            if not isinstance(input_data, dict):
+                return {'error': 'Input must be a dictionary'}
+
+            price = input_data.get('price')
+
+            if price is None:
+                return {'error': "Missing 'price'"}
+
+            try:
+                price = float(price)
+            except (ValueError, TypeError):
+                return {'error': 'Price must be a number'}
+
+            prediction = self.model.predict([[price]])
+
+            return {'prediction': float(prediction[0])}
+
+        except Exception as e:
+            return {'error': str(e)}

nodes/src/nodes/ml_sklearn/requirements.txt

@@ -0,0 +1,2 @@
+scikit-learn>=1.0
+numpy>=1.21

nodes/src/nodes/ml_sklearn/services.json

@@ -0,0 +1,29 @@
+{
+  "title": "ML Sklearn Prediction",
+  "protocol": "ml_sklearn://",
+  "classType": ["machine_learning"],
+  "capabilities": [],
+  "register": "filter",
+  "node": "python",
+  "path": "nodes.ml_sklearn",
+  "prefix": "ML",
+  "description": [
+    "A machine learning node that performs prediction using a trained sklearn model.",
+    "It accepts numerical input and returns predicted output."
+  ],
+  "icon": "python.svg",
+  "documentation": "https://docs.rocketride.org",
+  "lanes": {
+    "input": ["data"]
+  },
+  "input": [
+    {
+      "lane": "input",
+      "output": [
+        {
+          "lane": "data"
+        }
+      ]
+    }
+  ]
+}