Fix TripletStore initialization and store method; update notebooks

2026-08-29 04:26:20 +00:00 · 2025-12-20 21:10:50 +05:30
parent 35760f97aa
commit fe1d8c425c
3 changed files with 266 additions and 35 deletions
@@ -25,21 +25,37 @@
    "pip install semantica[all]\n",
    "```\n",
    "\n",
-    "## Workflow: Build KG \u2192 Generate Ontology \u2192 Create Semantic Layer \u2192 Export RDF \u2192 Triplet Store\n"
+    "## Workflow: Build KG → Generate Ontology → Create Semantic Layer → Export RDF \n"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
   "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNING: Ignoring invalid distribution ~gno (C:\\Users\\Mohd Kaif\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages)\n",
+      "WARNING: Ignoring invalid distribution ~lotly (C:\\Users\\Mohd Kaif\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages)\n",
+      "WARNING: Ignoring invalid distribution ~ython-socketio (C:\\Users\\Mohd Kaif\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages)\n",
+      "WARNING: Ignoring invalid distribution ~gno (C:\\Users\\Mohd Kaif\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages)\n",
+      "WARNING: Ignoring invalid distribution ~lotly (C:\\Users\\Mohd Kaif\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages)\n",
+      "WARNING: Ignoring invalid distribution ~ython-socketio (C:\\Users\\Mohd Kaif\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages)\n",
+      "WARNING: Ignoring invalid distribution ~gno (C:\\Users\\Mohd Kaif\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages)\n",
+      "WARNING: Ignoring invalid distribution ~lotly (C:\\Users\\Mohd Kaif\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages)\n",
+      "WARNING: Ignoring invalid distribution ~ython-socketio (C:\\Users\\Mohd Kaif\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages)\n"
+     ]
+    }
+   ],
   "source": [
-    "!pip install semantica\n"
+    "!pip install -qU semantica\n"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
@@ -58,9 +74,22 @@
  },
  {
   "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
   "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div style='font-family: monospace;'><h4>🧠 Semantica - 📊 Current Progress</h4><table style='width: 100%; border-collapse: collapse;'><tr><th>Status</th><th>Action</th><th>Module</th><th>Submodule</th><th>File</th><th>Time</th></tr><tr><td>✅</td><td>Semantica is building</td><td>🧠 kg</td><td>GraphBuilder</td><td>-</td><td>0.13s</td></tr><tr><td>🔄</td><td>Semantica is building</td><td>🧠 kg</td><td>EntityResolver</td><td>-</td><td>7.37s</td></tr><tr><td>✅</td><td>Semantica is deduplicating</td><td>🔄 deduplication</td><td>DuplicateDetector</td><td>-</td><td>0.09s</td></tr><tr><td>✅</td><td>Semantica is deduplicating</td><td>🔄 deduplication</td><td>SimilarityCalculator</td><td>-</td><td>0.01s</td></tr><tr><td>✅</td><td>Semantica is resolving</td><td>⚠️ conflicts</td><td>ConflictDetector</td><td>-</td><td>0.00s</td></tr><tr><td>✅</td><td>Semantica is generating</td><td>📚 ontology</td><td>OntologyGenerator</td><td>-</td><td>0.06s</td></tr><tr><td>✅</td><td>Semantica is generating</td><td>📚 ontology</td><td>ClassInferrer</td><td>-</td><td>0.01s</td></tr><tr><td>✅</td><td>Semantica is generating</td><td>📚 ontology</td><td>PropertyGenerator</td><td>-</td><td>0.01s</td></tr><tr><td>✅</td><td>Semantica is exporting</td><td>💾 export</td><td>RDFExporter</td><td>-</td><td>0.01s</td></tr><tr><td>✅</td><td>Semantica is storing</td><td>🗄️ triplet_store</td><td>BulkLoader</td><td>-</td><td>3.01s</td></tr></table></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
   "source": [
    "builder = GraphBuilder()\n",
    "\n",
@@ -90,7 +119,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
@@ -107,7 +136,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
@@ -159,9 +188,17 @@
  },
  {
   "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
   "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Exported knowledge graph to knowledge_graph.ttl\n"
+     ]
+    }
+   ],
   "source": [
    "exporter = RDFExporter()\n",
    "# Export Knowledge Graph\n",
@@ -169,23 +206,6 @@
    "print(\"Exported knowledge graph to knowledge_graph.ttl\")\n"
   ]
  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Step 5: Store in Triplet Store\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "triplet_store = TripletStore()\n",
-    "triplet_store.store(knowledge_graph, ontology)\n"
-   ]
-  },
  {
   "cell_type": "markdown",
   "metadata": {},
@@ -196,16 +216,44 @@
    "- Knowledge Graph Built\n",
    "- Ontology Generated\n",
    "- Semantic Layer Created with Mappings\n",
-    "- RDF Export Completed\n",
-    "- Triplet Store Storage Completed\n"
+    "- RDF Export Completed\n"
   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
  }
 ],
 "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
  "language_info": {
-   "name": "python"
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
-}
+}
@@ -0,0 +1,20 @@
+<e1> a <Person> ;
+    semantica:text "" ;
+    semantica:confidence 1.0 .
+
+<e2> a <Person> ;
+    semantica:text "" ;
+    semantica:confidence 1.0 .
+
+<e3> a <Organization> ;
+    semantica:text "" ;
+    semantica:confidence 1.0 .
+
+<e4> a <Project> ;
+    semantica:text "" ;
+    semantica:confidence 1.0 .
+
+<e1> <reports_to> <e2> .
+<e1> <works_for> <e3> .
+<e2> <works_for> <e3> .
+<e1> <works_on> <e4> .
@@ -93,6 +93,11 @@ class TripletStore:
                backend_config = self.config.copy()
                if self.endpoint:
                    backend_config["endpoint"] = self.endpoint
+                else:
+                    backend_config["endpoint"] = triplet_store_config.get(
+                        "blazegraph_endpoint", 
+                        "http://localhost:9999/blazegraph"
+                    )
                
                self._store_backend = BlazegraphStore(**backend_config)

@@ -101,9 +106,12 @@ class TripletStore:
                
                backend_config = self.config.copy()
                if self.endpoint:
-                    # JenaStore might use different param names or structure
-                    # Assuming JenaStore accepts endpoint or url
-                    backend_config["url"] = self.endpoint 
+                    backend_config["endpoint"] = self.endpoint
+                else:
+                    backend_config["endpoint"] = triplet_store_config.get(
+                        "jena_endpoint",
+                        "http://localhost:3030/ds"
+                    )
                
                self._store_backend = JenaStore(**backend_config)

@@ -113,6 +121,11 @@ class TripletStore:
                backend_config = self.config.copy()
                if self.endpoint:
                    backend_config["endpoint"] = self.endpoint
+                else:
+                    backend_config["endpoint"] = triplet_store_config.get(
+                        "rdf4j_endpoint",
+                        "http://localhost:8080/rdf4j-server"
+                    )
                
                self._store_backend = RDF4JStore(**backend_config)
                
@@ -122,6 +135,156 @@ class TripletStore:
            self.logger.error(f"Failed to initialize {self.backend_type} backend: {e}")
            raise ProcessingError(f"Failed to initialize backend: {e}")

+    def store(
+        self, 
+        knowledge_graph: Union[Dict[str, Any], Any], 
+        ontology: Union[Dict[str, Any], Any], 
+        **options
+    ) -> Dict[str, Any]:
+        """
+        Store knowledge graph and ontology in the triplet store.
+        
+        Args:
+            knowledge_graph: Knowledge graph dictionary or object
+            ontology: Ontology dictionary or object
+            **options: Additional options
+        
+        Returns:
+            Operation status
+        """
+        # Convert inputs to dictionaries if they are objects
+        if hasattr(knowledge_graph, "to_dict"):
+            knowledge_graph = knowledge_graph.to_dict()
+        if hasattr(ontology, "to_dict"):
+            ontology = ontology.to_dict()
+            
+        triplets = []
+        
+        # Standard Namespaces
+        RDF_TYPE = "http://www.w3.org/1999/02/22-rdf-syntax-ns#type"
+        RDFS_SUBCLASS = "http://www.w3.org/2000/01/rdf-schema#subClassOf"
+        OWL_CLASS = "http://www.w3.org/2002/07/owl#Class"
+        OWL_OBJECT_PROPERTY = "http://www.w3.org/2002/07/owl#ObjectProperty"
+        OWL_DATATYPE_PROPERTY = "http://www.w3.org/2002/07/owl#DatatypeProperty"
+        RDFS_DOMAIN = "http://www.w3.org/2000/01/rdf-schema#domain"
+        RDFS_RANGE = "http://www.w3.org/2000/01/rdf-schema#range"
+        
+        # 1. Process Ontology
+        classes = ontology.get("classes", [])
+        properties = ontology.get("properties", [])
+        
+        for cls in classes:
+            # Class definition
+            cls_uri = cls.get("uri") or cls.get("id") or cls.get("name")
+            if not cls_uri:
+                continue
+                
+            if not cls_uri.startswith("http") and not cls_uri.startswith("urn:"):
+                 # Fallback if no URI provided
+                 cls_uri = f"urn:class:{cls_uri}"
+                 
+            triplets.append(Triplet(cls_uri, RDF_TYPE, OWL_CLASS))
+            
+            # Hierarchy
+            parent = cls.get("parent") or cls.get("subClassOf")
+            if parent:
+                parent_uri = parent
+                if not parent.startswith("http") and not parent.startswith("urn:"):
+                    parent_uri = f"urn:class:{parent}"
+                triplets.append(Triplet(cls_uri, RDFS_SUBCLASS, parent_uri))
+                
+        for prop in properties:
+            prop_uri = prop.get("uri") or prop.get("id") or prop.get("name")
+            if not prop_uri:
+                continue
+                
+            if not prop_uri.startswith("http") and not prop_uri.startswith("urn:"):
+                 prop_uri = f"urn:property:{prop_uri}"
+                 
+            # Determine property type (Object or Datatype)
+            # Default to ObjectProperty if not specified
+            prop_type = prop.get("type", OWL_OBJECT_PROPERTY)
+            if prop_type == "datatype":
+                prop_type = OWL_DATATYPE_PROPERTY
+            elif prop_type == "object":
+                prop_type = OWL_OBJECT_PROPERTY
+            
+            triplets.append(Triplet(prop_uri, RDF_TYPE, prop_type))
+            
+            if "domain" in prop:
+                domains = prop["domain"]
+                if isinstance(domains, str):
+                    domains = [domains]
+                
+                for domain in domains:
+                    domain_uri = domain
+                    if not domain.startswith("http") and not domain.startswith("urn:"):
+                        domain_uri = f"urn:class:{domain}"
+                    triplets.append(Triplet(prop_uri, RDFS_DOMAIN, domain_uri))
+                
+            if "range" in prop:
+                ranges = prop["range"]
+                if isinstance(ranges, str):
+                    ranges = [ranges]
+                
+                for range_ in ranges:
+                    range_uri = range_
+                    if not range_.startswith("http") and not range_.startswith("urn:"):
+                        range_uri = f"urn:class:{range_}"
+                    triplets.append(Triplet(prop_uri, RDFS_RANGE, range_uri))
+
+        # 2. Process Knowledge Graph
+        entities = knowledge_graph.get("entities", [])
+        relationships = knowledge_graph.get("relationships", [])
+        
+        entity_map = {} # Map IDs to URIs
+        
+        for entity in entities:
+            entity_id = entity.get("id")
+            if not entity_id:
+                continue
+                
+            entity_uri = entity.get("uri")
+            if not entity_uri:
+                entity_uri = f"urn:entity:{entity_id}"
+            
+            entity_map[entity_id] = entity_uri
+            
+            # Entity Type
+            entity_type = entity.get("type")
+            if entity_type:
+                type_uri = entity_type
+                if not entity_type.startswith("http") and not entity_type.startswith("urn:"):
+                    type_uri = f"urn:class:{entity_type}"
+                triplets.append(Triplet(entity_uri, RDF_TYPE, type_uri))
+                
+            # Entity Properties
+            props = entity.get("properties", {})
+            for k, v in props.items():
+                prop_uri = k
+                if not k.startswith("http") and not k.startswith("urn:"):
+                    prop_uri = f"urn:property:{k}"
+                triplets.append(Triplet(entity_uri, prop_uri, str(v)))
+                
+        for rel in relationships:
+            source_id = rel.get("source")
+            target_id = rel.get("target")
+            rel_type = rel.get("type") or rel.get("label")
+            
+            if not source_id or not target_id or not rel_type:
+                continue
+            
+            source_uri = entity_map.get(source_id, f"urn:entity:{source_id}")
+            target_uri = entity_map.get(target_id, f"urn:entity:{target_id}")
+            rel_uri = rel_type
+            if not rel_type.startswith("http") and not rel_type.startswith("urn:"):
+                rel_uri = f"urn:property:{rel_type}"
+            
+            triplets.append(Triplet(source_uri, rel_uri, target_uri))
+            
+        # Bulk load all triplets
+        return self.add_triplets(triplets, **options)
+
    def add_triplet(self, triplet: Triplet, **options) -> Dict[str, Any]:
        """
        Add a single triplet to the store.