Add scripts to support metadata mapping via LLM

.gitignore

@@ -139,4 +139,5 @@ upload_check*
 *manifests/
 annotations/inputs/*
 annotations/outputs/*
-annotations/output/*
+annotations/output/*
+utils/example_files/*

build_ttl_graphs.sh

@@ -0,0 +1,29 @@
+#/usr/bin/bash
+
+#Usage: bash build_ttl_graphs.sh [SOURCE_DIR] [FILE_EXTENSION] [ORG_NAME] [VERSION]
+
+#This script will convert files of the given extension to TTL-formatted RDF via csv_to_ttl.py
+#It will concatenate multiple TTLs to a single file, if multiple were provided in the source directory
+
+
+dir="$1"
+datatype="$2"
+org="$3"
+version="$4"
+outdir="$org"_ttl_graphs
+
+mkdir -p ./"$outdir"
+
+for file in "$dir"/*."$datatype"; do
+	if [ -f "$file" ]; then
+		python utils/csv_to_ttl.py -m "$file" -g "$org" -o "$outdir" -v "$version"
+	fi
+done
+
+for ttl in "$outdir"/*.ttl; do
+	if [ -f "$ttl" ]; then
+		cat "$ttl" >> "$org"_"$version"_model.ttl
+	fi
+done
+
+mv "$org"_"$version"_model.ttl "$outdir"

build_ttl_templates.sh

@@ -0,0 +1,29 @@
+#/usr/bin/bash
+
+#Usage: bash build_ttl_templates.sh [SOURCE_DIR] [FILE_EXTENSION] [ORG_NAME] [VERSION]
+
+#This script will convert files of the given extension to TTL-formatted template specifications via build_template_ttl.py
+#It will concatenate multiple TTLs to a single file, if multiple were provided in the source directory
+
+
+dir="$1"
+datatype="$2"
+org="$3"
+version="$4"
+outdir="$org"_ttl_templates
+
+mkdir -p ./"$outdir"
+
+for file in "$dir"/*."$datatype"; do
+	if [ -f "$file" ]; then
+		python utils/build_template_ttl.py -t "$file" -g "$org" -o "$outdir" -v "$version"
+	fi
+done
+
+for ttl in "$outdir"/*.ttl; do
+	if [ -f "$ttl" ]; then
+		cat "$ttl" >> "$org"_"$version"_all_templates.ttl
+	fi
+done
+
+mv "$org"_"$version"_all_templates.ttl "$outdir"

requirements.txt

@@ -1,2 +1,184 @@
-pandas >= 1.5.1
-openpyxl >= 3.0.10
+altair==4.2.0
+anyio==4.10.0
+appnope==0.1.4
+argon2-cffi==25.1.0
+argon2-cffi-bindings==25.1.0
+arrow==1.3.0
+asttokens==3.0.0
+async-lru==2.0.5
+asyncio==3.4.3
+asyncio-atexit==1.0.1
+attrs==25.3.0
+babel==2.17.0
+beautifulsoup4==4.13.5
+bleach==6.2.0
+cachetools==5.5.2
+certifi==2025.8.3
+cffi==2.0.0
+charset-normalizer==3.4.3
+click==8.2.1
+click-log==0.4.0
+clickclick==20.10.2
+colorama==0.4.6
+comm==0.2.3
+connexion==2.14.2
+cryptography==45.0.7
+dataclasses-json==0.6.7
+dateparser==1.2.2
+debugpy==1.8.16
+decorator==5.2.1
+defusedxml==0.7.1
+Deprecated==1.2.18
+dill==0.4.0
+entrypoints==0.4
+et_xmlfile==2.0.0
+exceptiongroup==1.3.0
+executing==2.2.1
+fastjsonschema==2.21.2
+Flask==2.2.5
+Flask-Cors==4.0.2
+fqdn==1.5.1
+google-api-core==2.25.1
+google-api-python-client==2.123.0
+google-auth==2.40.3
+google-auth-httplib2==0.1.1
+google-auth-oauthlib==0.8.0
+googleapis-common-protos==1.70.0
+graphviz==0.20.3
+great-expectations==0.15.50
+h11==0.16.0
+httpcore==1.0.9
+httplib2==0.30.0
+httpx==0.28.1
+idna==3.10
+importlib_metadata==8.7.0
+inflection==0.5.1
+ipykernel==6.30.1
+ipython==8.37.0
+ipywidgets==8.1.7
+isodate==0.6.1
+isoduration==20.11.0
+itsdangerous==2.2.0
+jedi==0.19.2
+Jinja2==3.1.6
+json5==0.12.1
+jsonpatch==1.33
+jsonpointer==3.0.0
+jsonschema==4.25.1
+jsonschema-specifications==2025.9.1
+jupyter-events==0.12.0
+jupyter-lsp==2.3.0
+jupyter_client==8.6.3
+jupyter_core==5.8.1
+jupyter_server==2.17.0
+jupyter_server_terminals==0.5.3
+jupyterlab==4.4.7
+jupyterlab_pygments==0.3.0
+jupyterlab_server==2.27.3
+jupyterlab_widgets==3.0.15
+lark==1.2.2
+makefun==1.16.0
+MarkupSafe==3.0.2
+marshmallow==3.26.1
+matplotlib-inline==0.1.7
+mistune==3.1.4
+mypy_extensions==1.1.0
+nbclient==0.10.2
+nbconvert==7.16.6
+nbformat==5.10.4
+nest-asyncio==1.6.0
+networkx==3.4.2
+notebook==7.4.5
+notebook_shim==0.2.4
+numpy==1.26.4
+oauth2client==4.1.3
+oauthlib==3.3.1
+openpyxl==3.1.5
+opentelemetry-api==1.36.0
+opentelemetry-exporter-otlp-proto-common==1.36.0
+opentelemetry-exporter-otlp-proto-http==1.36.0
+opentelemetry-instrumentation==0.57b0
+opentelemetry-instrumentation-flask==0.57b0
+opentelemetry-instrumentation-httpx==0.57b0
+opentelemetry-instrumentation-requests==0.57b0
+opentelemetry-instrumentation-threading==0.57b0
+opentelemetry-instrumentation-urllib==0.57b0
+opentelemetry-instrumentation-wsgi==0.57b0
+opentelemetry-proto==1.36.0
+opentelemetry-sdk==1.36.0
+opentelemetry-semantic-conventions==0.57b0
+opentelemetry-util-http==0.57b0
+overrides==7.7.0
+packaging==25.0
+pandarallel==1.6.5
+pandas==2.3.2
+pandocfilters==1.5.1
+parso==0.8.5
+pexpect==4.9.0
+platformdirs==4.4.0
+prometheus_client==0.22.1
+prompt_toolkit==3.0.52
+proto-plus==1.26.1
+protobuf==6.32.0
+psutil==5.9.8
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pyasn1==0.6.1
+pyasn1_modules==0.4.2
+pycparser==2.22
+pydantic==1.10.22
+Pygments==2.19.2
+pygsheets==2.0.6
+PyJWT==2.10.1
+pyparsing==3.2.3
+python-dateutil==2.9.0.post0
+python-dotenv==0.21.1
+python-json-logger==3.3.0
+pytz==2025.2
+PyYAML==6.0.2
+pyzmq==27.1.0
+rdflib==6.3.2
+referencing==0.36.2
+regex==2025.9.1
+requests==2.32.5
+requests-oauthlib==2.0.0
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rfc3987-syntax==1.1.0
+rpds-py==0.27.1
+rsa==4.9.1
+ruamel.yaml==0.17.17
+schematicpy==25.8.1
+scipy==1.15.3
+Send2Trash==1.8.3
+six==1.17.0
+sniffio==1.3.1
+soupsieve==2.8
+stack-data==0.6.3
+swagger-ui-bundle==0.0.9
+synapseclient==4.8.0
+tenacity==8.5.0
+terminado==0.18.1
+tinycss2==1.4.0
+toml==0.10.2
+tomli==2.2.1
+toolz==1.0.0
+tornado==6.5.2
+tqdm==4.67.1
+traitlets==5.14.3
+types-python-dateutil==2.9.0.20250822
+typing-inspect==0.9.0
+typing_extensions==4.15.0
+tzdata==2025.2
+tzlocal==5.3.1
+uri-template==1.3.0
+uritemplate==4.2.0
+urllib3==1.26.20
+wcwidth==0.2.13
+webcolors==24.11.1
+webencodings==0.5.1
+websocket-client==1.8.0
+Werkzeug==2.2.3
+widgetsnbextension==4.0.14
+wrapt==1.17.3
+zipp==3.23.0