Adds recursive func to delete all 'Unknown' enums

pyproject.toml

@@ -134,4 +134,6 @@ where = ["src"]
 perovskite_solar_cell = "perovskite_solar_cell_database:perovskite_solar_cell"
 solar_cell_app = "perovskite_solar_cell_database.apps:solar_cells"
 perovskite_composition = "perovskite_solar_cell_database:perovskite_composition"
-ion_parser = "perovskite_solar_cell_database:ion_parser"
+ion_parser = "perovskite_solar_cell_database:ion_parser"
+llm_extraction_schema = "perovskite_solar_cell_database:llm_extraction_schema"
+llm_extracted_solar_cells = "perovskite_solar_cell_database.apps:llm_extracted_solar_cells"

src/perovskite_solar_cell_database/__init__.py

@@ -66,3 +66,18 @@ def load(self):
         },
     },
 )
+
+
+class LLMSchemaExtractionPackageEntryPoint(SchemaPackageEntryPoint):
+    def load(self):
+        from perovskite_solar_cell_database.llm_extraction_schema import (
+            m_package,
+        )
+
+        return m_package
+
+
+llm_extraction_schema = LLMSchemaExtractionPackageEntryPoint(
+    name='LLMExtractionSchema',
+    description='Schema package defined for the perovskite solar cells database LLM extraction.',
+)

src/perovskite_solar_cell_database/apps/__init__.py

@@ -1,5 +1,8 @@
 from nomad.config.models.plugins import AppEntryPoint
 
+from perovskite_solar_cell_database.apps.llm_extracted_solarcells import (
+    llm_extracted_solar_cells,
+)
 from perovskite_solar_cell_database.apps.solar_cell_app import solar_cell_app
 
 solar_cells = AppEntryPoint(
@@ -12,3 +15,11 @@
     """,
     app=solar_cell_app,
 )
+
+llm_extracted_solar_cells = AppEntryPoint(
+    name='LLM Extracted Solar Cells',
+    description="""
+      This app allows you to search **LLM extracted solar cell data** within NOMAD.
+    """,
+    app=llm_extracted_solar_cells,
+)

src/perovskite_solar_cell_database/apps/llm_extracted_solarcells.py

@@ -0,0 +1,215 @@
+import yaml
+from nomad.config.models.ui import (
+    App,
+    Column,
+    Columns,
+    FilterMenu,
+    FilterMenus,
+    Filters,
+)
+
+llm_extracted_solar_cells = App(
+    # Label of the App
+    label='LLM Extracted Solar Cells',
+    # Path used in the URL, must be unique
+    path='llm-extracted-solar-cells',
+    # Used to categorize apps in the explore menu
+    category='LLM strcutured data extraction',
+    # Brief description used in the app menu
+    description="""
+    Explore the LLM extracted solar cells.
+    """,
+    # Longer description that can also use markdown
+    readme="""
+    Explore LLM extracted solar cells.
+    """,
+    # Controls the available search filters. If you want to filter by
+    # quantities in a schema package, you need to load the schema package
+    # explicitly here. Note that you can use a glob syntax to load the
+    # entire package, or just a single schema from a package.
+    filters=Filters(
+        include=[
+            '*#perovskite_solar_cell_database.llm_extraction_schema.LLMExtractedPerovskiteSolarCell',
+        ]
+    ),
+    # Controls which columns are shown in the results table
+    columns=Columns(
+        selected=[
+            'authors',
+            # 'results.material.elements',
+            'entry_type',
+            'data.review_completed#perovskite_solar_cell_database.llm_extraction_schema.LLMExtractedPerovskiteSolarCell',
+            'references',
+            # 'data.lab_id#nomad_material_processing.combinatorial.ThinFilmCombinatorialSample'
+        ],
+        options={
+            'entry_type': Column(label='Entry type', align='left'),
+            'entry_name': Column(label='Name', align='left'),
+            'entry_create_time': Column(label='Entry time', align='left'),
+            'authors': Column(label='Authors', align='left'),
+            'upload_name': Column(label='Upload name', align='left'),
+            'references': Column(label='References', align='left'),
+            'data.review_completed#perovskite_solar_cell_database.llm_extraction_schema.LLMExtractedPerovskiteSolarCell': Column(
+                label='Review completed', align='left'
+            ),  # noqa: E501
+            'data.publication_title#perovskite_solar_cell_database.llm_extraction_schema.LLMExtractedPerovskiteSolarCell': Column(
+                label='Publication title', align='left'
+            ),  # noqa: E501
+            # 'data.lab_id#nomad_htem_database.schema_packages.htem_package.HTEMLibrary': Column(  # noqa: E501
+            #     label='Library ID', align='left'
+            # ),
+            'results.material.elements': Column(label='Elements', align='left'),
+        },
+    ),
+    # Dictionary of search filters that are always enabled for queries made
+    # within this app. This is especially important to narrow down the
+    # results to the wanted subset. Any available search filter can be
+    # targeted here. This example makes sure that only entries that use
+    # MySchema are included.
+    filters_locked={
+        'entry_type': 'LLMExtractedPerovskiteSolarCell',
+    },
+    # Controls the filter menus shown on the left
+    filter_menus=FilterMenus(
+        options={
+            'material': FilterMenu(label='Material', level=0),
+            'elements': FilterMenu(label='Elements / Formula', level=1, size='xl'),
+            'eln': FilterMenu(label='Electronic Lab Notebook', level=0),
+            'custom_quantities': FilterMenu(
+                label='User Defined Quantities', level=0, size='l'
+            ),
+            'author': FilterMenu(label='Author / Origin / Dataset', level=0, size='m'),
+            'metadata': FilterMenu(label='Visibility / IDs / Schema', level=0),
+            'optimade': FilterMenu(label='Optimade', level=0, size='m'),
+        }
+    ),
+    # Controls the default dashboard shown in the search interface
+    dashboard=yaml.safe_load(
+        """
+    widgets:
+      - type: terms
+        scale: linear
+        quantity: data.journal#perovskite_solar_cell_database.llm_extraction_schema.LLMExtractedPerovskiteSolarCell
+        layout:
+          xxl:
+            minH: 3
+            minW: 3
+            h: 9
+            w: 6
+            y: 0
+            x: 6
+          xl:
+            minH: 3
+            minW: 3
+            h: 5
+            w: 6
+            y: 0
+            x: 6
+          lg:
+            minH: 3
+            minW: 3
+            h: 9
+            w: 6
+            y: 0
+            x: 6
+          md:
+            minH: 3
+            minW: 3
+            h: 5
+            w: 4
+            y: 0
+            x: 4
+          sm:
+            minH: 3
+            minW: 3
+            h: 5
+            w: 3
+            y: 0
+            x: 4
+      - type: terms
+        scale: linear
+        quantity: authors.name
+        title: Reviewer names
+        layout:
+          xxl:
+            minH: 3
+            minW: 3
+            h: 9
+            w: 6
+            y: 0
+            x: 0
+          xl:
+            minH: 3
+            minW: 3
+            h: 5
+            w: 6
+            y: 0
+            x: 0
+          lg:
+            minH: 3
+            minW: 3
+            h: 9
+            w: 6
+            y: 0
+            x: 0
+          md:
+            minH: 3
+            minW: 3
+            h: 5
+            w: 4
+            y: 0
+            x: 0
+          sm:
+            minH: 3
+            minW: 3
+            h: 5
+            w: 4
+            y: 0
+            x: 0
+      - type: histogram
+        autorange: false
+        nbins: 30
+        y:
+          scale: linear
+        x:
+          quantity: data.publication_date#perovskite_solar_cell_database.llm_extraction_schema.LLMExtractedPerovskiteSolarCell
+        layout:
+          xxl:
+            minH: 3
+            minW: 3
+            h: 3
+            w: 8
+            y: 0
+            x: 12
+          xl:
+            minH: 3
+            minW: 3
+            h: 3
+            w: 7
+            y: 0
+            x: 12
+          lg:
+            minH: 3
+            minW: 3
+            h: 3
+            w: 8
+            y: 0
+            x: 12
+          md:
+            minH: 3
+            minW: 3
+            h: 3
+            w: 7
+            y: 0
+            x: 8
+          sm:
+            minH: 3
+            minW: 3
+            h: 3
+            w: 5
+            y: 0
+            x: 7
+
+      """
+    ),
+)

src/perovskite_solar_cell_database/composition.py

@@ -463,9 +463,9 @@ class PerovskiteIonComponent(SystemComponent, PerovskiteIonSection):
         )
     )
     coefficient = Quantity(
-        type=float,
+        type=str,
         description='The stoichiometric coefficient',
-        a_eln=ELNAnnotation(component=ELNComponentEnum.NumberEditQuantity),
+        a_eln=ELNAnnotation(component=ELNComponentEnum.StringEditQuantity),
         shape=[],
     )
     system = Quantity(
@@ -692,7 +692,7 @@ class Impurity(PureSubstanceComponent, PerovskiteChemicalSection):
         type=float,
         description='The concentration of the additive or impurity.',
         a_eln=ELNAnnotation(
-            component=ELNComponentEnum.NumberEditQuantity, defaultDisplayUnit='mol%'
+            component=ELNComponentEnum.NumberEditQuantity, defaultDisplayUnit='cm^-3'
         ),
         unit='cm^-3',
         shape=[],
@@ -831,12 +831,10 @@ def normalize(self, archive: 'EntryArchive', logger: 'BoundLogger') -> None:
             self.short_form += ion.abbreviation
             if ion.coefficient is None:
                 continue
-            if ion.coefficient == 1:
+            if ion.coefficient == '1':
                 coefficient_str = ''
-            elif ion.coefficient == int(ion.coefficient):
-                coefficient_str = str(int(ion.coefficient))
             else:
-                coefficient_str = f'{ion.coefficient:.2}'
+                coefficient_str = ion.coefficient
             self.long_form += f'{ion.abbreviation}{coefficient_str}'
             if not isinstance(ion.molecular_formula, str):
                 continue
@@ -862,6 +860,7 @@ def normalize(self, archive: 'EntryArchive', logger: 'BoundLogger') -> None:
             label='Perovskite Composition',
             description='A system describing the chemistry and components of the perovskite.',
             system_relation=Relation(type='root'),
+            chemical_formula_descriptive=self.long_form,
         )
 
         parent_system.structural_type = archive.results.material.structural_type