feature/make-from-str-default-native-text (Pipelex#78)

Author: thomashebrard

pipelex/core/stuff_factory.py

@@ -95,9 +95,9 @@ def make_from_blueprint(cls, blueprint: StuffBlueprint) -> "Stuff":
     @classmethod
     def make_from_str(
         cls,
-        concept_code: str,
         str_value: str,
         name: Optional[str] = None,
+        concept_code: str = NativeConcept.TEXT.code,
         pipelex_session_id: Optional[str] = None,
     ) -> Stuff:
         if not Concept.concept_str_contains_domain(concept_code):

pipelex/pipe_operators/pipe_llm_prompt.py

@@ -234,6 +234,7 @@ def get_output_structure_prompt(output_concept: str) -> str:
             "You do NOT need to output a formatted JSON object, another LLM will take care of that. "
             "If you cannot find a value that is Optional, output None for that field."
             "However, you MUST clearly output the values for each of these fields in your response.\n---\n"
+            "DO NOT create information. If the information is not present, output None."
         )
         return output_structure_prompt
 

pipelex/tools/typing/type_inspector.py

@@ -120,13 +120,19 @@ def collect_types(tp: Type[Any]) -> None:
                 for arg in non_none:
                     if isinstance(arg, type):
                         collect_types(arg)
+                    elif hasattr(arg, "__origin__"):  # Handle nested generics
+                        collect_types(arg)
             elif origin in (list, List):
                 if isinstance(args[0], type):
                     collect_types(args[0])
+                elif hasattr(args[0], "__origin__"):  # Handle nested generics
+                    collect_types(args[0])
             elif origin in (dict, Dict):
                 for arg in args:
                     if isinstance(arg, type):
                         collect_types(arg)
+                    elif hasattr(arg, "__origin__"):  # Handle nested generics
+                        collect_types(arg)
             return
 
         # Collect enums

tests/tools/typing/test_type_inspector.py

@@ -1,6 +1,7 @@
+from datetime import datetime
 from typing import List, Literal, Optional
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, field_validator
 from pytest import FixtureRequest
 
 from pipelex.core.stuff_content import ListContent, StructuredContent, TextContent
@@ -88,6 +89,38 @@ class ComplexListContent(ListContent[PersonContent]):
     items: List[PersonContent]
 
 
+class GanttTaskDetails(StructuredContent):
+    """Do not include timezone in the dates."""
+
+    name: str
+    start_date: Optional[datetime] = None
+    end_date: Optional[datetime] = None
+
+    @field_validator("start_date", "end_date")
+    @classmethod
+    def remove_tzinfo(cls, v: Optional[datetime]) -> Optional[datetime]:
+        if v is not None:
+            return v.replace(tzinfo=None)
+        return v
+
+
+class Milestone(StructuredContent):
+    name: str
+    date: Optional[datetime]
+
+    @field_validator("date")
+    @classmethod
+    def remove_tzinfo(cls, v: Optional[datetime]) -> Optional[datetime]:
+        if v is not None:
+            return v.replace(tzinfo=None)
+        return v
+
+
+class GanttChart(StructuredContent):
+    tasks: Optional[List[GanttTaskDetails]] = None
+    milestones: Optional[List[Milestone]] = None
+
+
 class TestTypeInspector:
     """Tests for the type inspector functionality"""
 
@@ -268,3 +301,24 @@ def test_literal_field_content(self, request: FixtureRequest):
             '    WORLD = "world"',
         ]
         assert result == expected, f"Expected:\n{''.join(expected)}\n\nGot:\n{''.join(result)}"
+
+    def test_gantt_chart_content(self, request: FixtureRequest):
+        """Test structure of Gantt chart content with datetime validators"""
+
+        result = get_type_structure(GanttChart, base_class=StructuredContent)
+        expected = [
+            "class GanttChart(StructuredContent):",
+            "    tasks: Optional[List[GanttTaskDetails]] = None",
+            "    milestones: Optional[List[Milestone]] = None",
+            "",
+            "class GanttTaskDetails(StructuredContent):",
+            '    """Do not include timezone in the dates."""',
+            "    name: str",
+            "    start_date: Optional[datetime] = None",
+            "    end_date: Optional[datetime] = None",
+            "",
+            "class Milestone(StructuredContent):",
+            "    name: str",
+            "    date: Optional[datetime] = None",
+        ]
+        assert result == expected, f"Expected:\n{''.join(expected)}\n\nGot:\n{''.join(result)}"