Aiida plugin (#72)

* add the aiida plugin

* update uv.lock & pyproject.toml

* fix pre-commit

* improve property match check; fix aiida plugin

* aiida-plugin: make group optional

* print uuid for structure that errors

* switch to ase conversion

Author: eimrek

examples/aiida_archive/.gitignore

@@ -0,0 +1 @@
+optimade.jsonl

examples/aiida_archive/.testing/first_entry.json

@@ -0,0 +1 @@
+{"id": "4453cd37-17fd-4022-b571-ccd639bb6bd0", "type": "structures", "links": null, "meta": null, "attributes": {"immutable_id": "4453cd37-17fd-4022-b571-ccd639bb6bd0", "last_modified": "2025-02-21T17:24:17.741830+00:00", "elements": ["C"], "nelements": 1, "elements_ratios": [1.0], "chemical_formula_descriptive": "C2", "chemical_formula_reduced": "C", "chemical_formula_hill": null, "chemical_formula_anonymous": "A", "dimension_types": [1, 1, 1], "nperiodic_dimensions": 3, "lattice_vectors": [[0.0, 1.777412397431, 1.777412397431], [1.777412397431, 0.0, 1.777412397431], [1.777412397431, 1.777412397431, 0.0]], "space_group_symmetry_operations_xyz": null, "space_group_symbol_hall": null, "space_group_symbol_hermann_mauguin": null, "space_group_symbol_hermann_mauguin_extended": null, "space_group_it_number": null, "cartesian_site_positions": [[0.0, 0.0, 1.777412397431], [0.8887061987155, 2.6661185961465, 0.8887061987155]], "nsites": 2, "species": [{"name": "C", "chemical_symbols": ["C"], "concentration": [1.0], "mass": null, "original_name": null, "attached": null, "nattached": null}], "species_at_sites": ["C", "C"], "assemblies": null, "structure_features": [], "_optimake_test_extra": null, "_optimake_ctime": "2025-02-21T17:24:17.534593+00:00", "_optimake_energy": -492.9169718438, "_optimake_band_gap": 4.0381280210178, "_optimake_is_band_gap_direct": false, "_optimake_csv_property": 1}, "relationships": null}

examples/aiida_archive/README.md

@@ -0,0 +1,29 @@
+# Aiida example
+
+The example AiiDA database contains three crystals:
+
+- diamond (C<sub>2</sub>) (uuid: `4453cd37-17fd-4022-b571-ccd639bb6bd0`);
+- GaAs (uuid: `598c08c4-793f-4afb-b39e-d0c947821c6f`);
+- MgO (uuid: `c52d8ad2-2440-4b00-99ab-39b987d88c18`),
+
+where C<sub>2</sub> and GaAs have band structures calculated with Quantum Espresso, and MgO has no calculations done on it. The band structure calculation provenance is shown in the following schematic:
+
+```mermaid
+graph LR;
+  A("Initial crystal<br>(StructureData)") --> B["PwBandsWorkChain"];
+  B --> C("Relaxed crystal<br>(StructureData)");
+  B --> D("SCF parameters<br>(Dict)");
+  B --> E("Band structure<br>(BandsData)");
+  E --> F["get_bandgap<br>(CalcFunctionNode)"];
+  F --> G("Band gap results<br>(Dict)");
+
+  style A fill:#004400;
+  style B fill:#442200;
+  style C fill:#004400;
+  style D fill:#004400;
+  style E fill:#004400;
+  style F fill:#442200;
+  style G fill:#004400;
+```
+
+We want to include the "Relaxed crystal" nodes as OPTIMADE structures, and include custom properties from the various other AiiDA nodes (e.g. the band gap value from the "Band gap results" node). The example `optimade.yaml` shows how to achieve this.

examples/aiida_archive/data.csv

@@ -0,0 +1,4 @@
+id,csv_property
+4453cd37-17fd-4022-b571-ccd639bb6bd0,1
+598c08c4-793f-4afb-b39e-d0c947821c6f,2
+c52d8ad2-2440-4b00-99ab-39b987d88c18,3

examples/aiida_archive/example.aiida

@@ -0,0 +1,75 @@
+config_version: 0.1.0
+
+database_description: >-
+  This example aiida database contains optimized structures and band structure calculations.
+
+entries:
+  - entry_type: structures
+    entry_paths:
+      aiida_file: example.aiida # Aiida archive file, or
+      #aiida_profile: test-profile # Aiida profile
+      aiida_group: optimade_structures
+    property_paths:
+      # If all properties are stored in the AiiDA database,
+      # this can be omitted. But additional properties can be
+      # provided via a csv file.
+      - file: data.csv
+    property_definitions:
+      # ----
+      - name: test_extra
+        title: Test extra
+        description: Nested extra for testing.
+        type: string
+        aiida_query:
+          - project: extras.test.a
+      # ----
+      - name: ctime
+        title: Creation time
+        description: Time when the node was created.
+        type: timestamp
+        aiida_query:
+          - project: ctime
+      # ----
+      - name: energy
+        title: Total energy
+        description: The total energy computed by DFT
+        unit: eV
+        type: float
+        aiida_query:
+          - incoming_node: WorkChainNode
+          - outgoing_node: Dict
+            edge_filters:
+              label: scf_parameters
+          - project: attributes.energy
+      # ----
+      - name: band_gap
+        title: Band gap
+        description: Band gap of the material.
+        unit: eV
+        type: float
+        aiida_query:
+          - incoming_node: WorkChainNode
+          - outgoing_node: BandsData
+          - outgoing_node: CalcFunctionNode
+          - outgoing_node: Dict
+            edge_filters:
+              label: bandgap
+          - project: attributes.value
+      # ----
+      - name: is_band_gap_direct
+        title: Direct band gap
+        description: Is the band gap direct?
+        type: boolean
+        aiida_query:
+          - incoming_node: WorkChainNode
+          - outgoing_node: BandsData
+          - outgoing_node: CalcFunctionNode
+          - outgoing_node: Dict
+            edge_filters:
+              label: bandgap
+          - project: attributes.is_direct
+      # property provided by csv file:
+      - name: csv_property
+        title: Test property
+        description: Property from the csv file
+        type: integer

examples/aiida_archive/optimade.yaml

@@ -8,24 +8,24 @@ keywords = ["optimade", "jsonapi", "materials"]
 dynamic = ["version"]
 
 classifiers = [
-    "Development Status :: 4 - Beta",
-    "Programming Language :: Python :: 3 :: Only",
-    "Programming Language :: Python :: 3.10",
-    "Programming Language :: Python :: 3.11",
-    "Programming Language :: Python :: 3.12",
-    "Intended Audience :: Science/Research",
-    "Topic :: Database",
-    "Topic :: Scientific/Engineering",
+  "Development Status :: 4 - Beta",
+  "Programming Language :: Python :: 3 :: Only",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Intended Audience :: Science/Research",
+  "Topic :: Database",
+  "Topic :: Scientific/Engineering",
 ]
 
 dependencies = [
-    "pydantic~=2.2",
-    "optimade[server]~=1.1",
-    "pyyaml~=6.0",
-    "tqdm~=4.65",
-    "requests~=2.31",
-    "numpy >= 1.22, < 3",
-    "click~=8.1"
+  "pydantic~=2.2",
+  "optimade[server]~=1.1",
+  "pyyaml~=6.0",
+  "tqdm~=4.65",
+  "requests~=2.31",
+  "numpy >= 1.22, < 3",
+  "click~=8.1",
 ]
 
 [project.scripts]
@@ -43,7 +43,8 @@ version_scheme = "post-release"
 ase = ["ase ~= 3.22"]
 pymatgen = ["pymatgen >= 2023.9"]
 pandas = ["pandas >= 1.5, < 3"]
-ingest = ["optimade-maker[ase,pymatgen,pandas]"]
+aiida = ["aiida-core >= 2.6.3"]
+ingest = ["optimade-maker[ase,pymatgen,pandas,aiida]"]
 tests = ["pytest~=8.3", "pytest-cov~=6.0"]
 dev = ["ruff", "pre-commit", "mypy"]