LLM extraction schema update

[pilar12]

NOMAD Schema updated to reflect latest changes to the pydantic schema

• Solute section added
• Ions section added to Perovskite Composition
• Gas Quenching changed to Bool
• Names PCE fileds in Stability section updated to match pydantic schema

Summary by Sourcery

Add a new schema package for LLM extraction in the perovskite solar cell database, incorporating new sections for solutes and ions, and update existing schema to reflect changes in the pydantic schema.

New Features:

• Introduce a new schema package for LLM extraction in the perovskite solar cell database, including sections for solutes, ions, and processing steps.

Enhancements:

• Update the NOMAD schema to align with the latest pydantic schema changes, including modifications to the stability section and gas quenching field.

[sourcery-ai]

Reviewer's Guide by Sourcery

This PR updates the NOMAD schema to align with the latest pydantic schema changes for LLM extraction. The changes introduce a new schema package entry point for LLM extraction and add several new sections and fields to the schema, including Solute and Ion sections, while also modifying existing fields.

Class diagram for updated NOMAD schema

classDiagram
    class LLMSchemaExtractionPackageEntryPoint {
        +load()
    }
    class LightSource {
        +type: MEnum
        +description: str
        +light_intensity: float
        +lamp: str
    }
    class Stability {
        +time: float
        +light_intensity: float
        +humidity: float
        +temperature: float
        +PCE_T80: float
        +PCE_at_the_start_of_the_experiment: float
        +PCE_after_1000_hours: float
        +PCE_at_the_end_of_description: float
    }
    class ProcessingAtmosphere {
        +type: str
        +pressure: float
        +relative_humidity: float
    }
    class Solute {
        +name: str
        +concentration: float
        +concentration_unit: str
    }
    class ReactionSolution {
        +compounds: str[*]
        +volume: float
        +temperature: float
        +solvent: str
        +solutes: Solute[*]
    }
    class ProcessingStep {
        +step_name: str
        +method: str
        +temperature: float
        +duration: float
        +antisolvent: str
        +gas_quenching: bool
        +solution: ReactionSolution
        +atmosphere: ProcessingAtmosphere
    }
    class Deposition {
        +steps: ProcessingStep[*]
        +reviewer_additional_notes: str
        +additional_notes: str
    }
    class Layer {
        +name: str
        +thickness: float
        +functionality: MEnum
        +deposition: ProcessingStep[*]
        +additional_treatments: str
    }
    class Ion {
        +abbreviation: str
        +coefficient: str
    }
    class PerovskiteComposition {
        +formula: str
        +a_ions: Ion[*]
        +b_ions: Ion[*]
        +x_ions: Ion[*]
    }
    class LLMExtractedPerovskiteSolarCell {
        +review_completed: bool
        +DOI_number: str
        +cell_stack: str[*]
        +device_architecture: MEnum
        +pce: float
        +jsc: float
        +voc: float
        +ff: float
        +active_area: float
        +number_devices: int
        +averaged_quantities: bool
        +bandgap: float
        +encapsulated: bool
        +reviewer_additional_notes: str
        +additional_notes: str
        +light_source: LightSource
        +stability: Stability
        +layers: Layer[*]
        +perovskite_composition: PerovskiteComposition
    }

Loading

File-Level Changes

Change	Details	Files
Added new schema package entry point for LLM extraction	Created LLMSchemaExtractionPackageEntryPoint class Added new entry point registration in pyproject.toml	src/perovskite_solar_cell_database/__init__.py pyproject.toml
Created new schema file with updated structure	Defined base schema sections (LightSource, Stability, ProcessingAtmosphere) Added new Solute section for detailed solute information Added Ion section and integrated it into PerovskiteComposition Modified gas_quenching field to boolean type Updated PCE field names in Stability section Created comprehensive LLMExtractedPerovskiteSolarCell schema	src/perovskite_solar_cell_database/llm_extraction_schema.py

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time. You can also use
  this command to specify where the summary should be inserted.

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.