Fix prompt tests for schema_constraints and Pydantic V2 deprecation

Author: mykola-pereyma

lexical-graph/src/graphrag_toolkit/lexical_graph/indexing/extract/stages/schema_filter_stage.py

@@ -6,6 +6,7 @@
 
 from llama_index.core.schema import BaseNode, TransformComponent
 from llama_index.core.bridge.pydantic import Field
+from pydantic import ConfigDict
 
 from graphrag_toolkit.lexical_graph.indexing.extract.extraction_stage import ExtractionStage
 from graphrag_toolkit.lexical_graph.indexing.extract.extraction_schema import ExtractionSchema
@@ -20,8 +21,7 @@ class SchemaFilter(TransformComponent):
 
     extraction_schema: ExtractionSchema = Field(description='Extraction schema for filtering')
 
-    class Config:
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     def __call__(self, nodes: Sequence[BaseNode], **kwargs) -> Sequence[BaseNode]:
         if not self.extraction_schema.strict:

lexical-graph/src/graphrag_toolkit/lexical_graph/indexing/extract/topic_extractor.py

@@ -234,4 +234,4 @@ def blocking_llm_call():
                 (topics, garbage) = parse_extracted_topics(raw_response)
         else:
             (topics, garbage) = parse_extracted_topics(raw_response)
-        return (topics, garbage)
+        return (topics, garbage)

lexical-graph/tests/unit/indexing/test_prompts.py

@@ -131,19 +131,23 @@ def test_extract_topics_substitution(self):
         text = "GraphRAG is a framework."
         preferred_topics = "Technology, Software"
         preferred_entity_classifications = "Company, Product"
+        schema_constraints = "Focus on Technology entities."
 
         formatted_prompt = EXTRACT_TOPICS_PROMPT.format(
             text=text,
             preferred_topics=preferred_topics,
-            preferred_entity_classifications=preferred_entity_classifications
+            preferred_entity_classifications=preferred_entity_classifications,
+            schema_constraints=schema_constraints
         )
 
         assert text in formatted_prompt
         assert preferred_topics in formatted_prompt
         assert preferred_entity_classifications in formatted_prompt
+        assert schema_constraints in formatted_prompt
         assert '{text}' not in formatted_prompt
         assert '{preferred_topics}' not in formatted_prompt
         assert '{preferred_entity_classifications}' not in formatted_prompt
+        assert '{schema_constraints}' not in formatted_prompt
 
     def test_domain_entity_classifications_substitution(self):
         """Verify DOMAIN_ENTITY_CLASSIFICATIONS_PROMPT variable substitution works correctly."""
@@ -250,7 +254,7 @@ def test_prompts_have_no_unintended_placeholders(self):
         # Define expected placeholders for each prompt
         expected_placeholders = {
             'EXTRACT_PROPOSITIONS_PROMPT': ['{source_info}', '{text}'],
-            'EXTRACT_TOPICS_PROMPT': ['{text}', '{preferred_topics}', '{preferred_entity_classifications}'],
+            'EXTRACT_TOPICS_PROMPT': ['{text}', '{preferred_topics}', '{preferred_entity_classifications}', '{schema_constraints}'],
             'DOMAIN_ENTITY_CLASSIFICATIONS_PROMPT': ['{text_chunks}', '{existing_classifications}'],
             'RANK_ENTITY_CLASSIFICATIONS_PROMPT': ['{classifications}']
         }