Initial commit

skills/extract_from_pdfs/assets/api_config_template.json

@@ -0,0 +1,62 @@
+{
+  "_comment": "Configuration for API validation in step 05",
+  "_instructions": [
+    "Specify which external APIs to use for validating/enriching each field",
+    "Available APIs:",
+    "  - gbif_taxonomy: GBIF for biological taxonomy",
+    "  - wfo_plants: World Flora Online for plant names",
+    "  - geonames: GeoNames for geographic locations (requires account)",
+    "  - geocode: OpenStreetMap Nominatim for geocoding",
+    "  - pubchem: PubChem for chemical compounds",
+    "  - ncbi_gene: NCBI Gene database",
+    "Customize the field_mappings below based on your extraction schema"
+  ],
+
+  "field_mappings": {
+    "_example_species_field": {
+      "api": "gbif_taxonomy",
+      "output_field": "validated_species",
+      "description": "Validate species names against GBIF"
+    },
+
+    "_example_location_field": {
+      "api": "geocode",
+      "output_field": "geocoded_location",
+      "description": "Geocode location to lat/lon coordinates"
+    },
+
+    "_example_compound_field": {
+      "api": "pubchem",
+      "output_field": "validated_compound",
+      "description": "Validate chemical compound names"
+    }
+  },
+
+  "nested_field_mappings": {
+    "_comment": "For fields nested in 'records' array",
+    "_example": "records.species would validate the 'species' field within each record",
+
+    "records.species": {
+      "api": "gbif_taxonomy",
+      "output_field": "validated_species"
+    },
+
+    "records.location": {
+      "api": "geocode",
+      "output_field": "coordinates"
+    }
+  },
+
+  "api_specific_settings": {
+    "geonames": {
+      "_note": "Requires free account at geonames.org",
+      "_setup": "Set GEONAMES_USERNAME environment variable"
+    },
+
+    "rate_limits": {
+      "_comment": "Be respectful of API rate limits",
+      "default_delay_seconds": 0.5,
+      "nominatim_delay_seconds": 1.0
+    }
+  }
+}