feat: deploy training data to zoe root

scripts/generate_training_data.py

@@ -15,6 +15,9 @@ from typing import Any
 INSTRUCTION = "Map the following natural language request to the correct action and payload."
 DATASET_PREFIX = "module_controller_intents"
 DEFAULT_MIN_RECORDS_PER_ACTION = 20
+CUSTOM_LOCAL_LLM_ROOT = Path("/Volumes/Zoe/custom-local-llm")
+DEFAULT_OUTPUT_DIR = CUSTOM_LOCAL_LLM_ROOT / "training-data"
+DEFAULT_MANIFEST = CUSTOM_LOCAL_LLM_ROOT / "manifest.llm.json"
 
 
 def main() -> int:
@@ -32,8 +35,8 @@ def main() -> int:
 def parse_args() -> argparse.Namespace:
     parser = argparse.ArgumentParser(description=__doc__)
     parser.add_argument("--dictionary-dir", default="dictionary/")
-    parser.add_argument("--output-dir", default="../workspace_Data/data/")
-    parser.add_argument("--manifest", default="../workspace_Data/manifest.llm.json")
+    parser.add_argument("--output-dir", default=str(DEFAULT_OUTPUT_DIR))
+    parser.add_argument("--manifest", default=str(DEFAULT_MANIFEST))
     parser.add_argument("--dry-run", action="store_true")
     parser.add_argument("--sdg-host")
     parser.add_argument("--sdg-user")
@@ -469,6 +472,9 @@ def patch_manifest(
 
 def relative_data_path(dataset_dir: Path) -> str:
     parts = dataset_dir.parts
+    if "training-data" in parts:
+        index = len(parts) - 1 - list(reversed(parts)).index("training-data")
+        return "/".join(parts[index:])
     if "data" in parts:
         index = len(parts) - 1 - list(reversed(parts)).index("data")
         return "/".join(parts[index:])