@vespermcp/mcp-server 1.2.21 → 1.2.22

package/src/python/normalize_engine.py

@@ -0,0 +1,83 @@
+"""
+Normalize any supported dataset file to parquet format.
+Usage: normalize_engine.py <input_path> <output_path>
+Outputs JSON: {"ok": true, "output_path": "...", "rows": N} or {"ok": false, "error": "..."}
+"""
+import sys
+import json
+import os
+
+try:
+    import polars as pl
+except Exception:
+    print(json.dumps({"ok": False, "error": "polars is required"}))
+    sys.exit(1)
+
+
+def _load(src: str) -> pl.DataFrame:
+    ext = os.path.splitext(src)[1].lower()
+
+    if ext == ".csv":
+        return pl.read_csv(src, ignore_errors=True, infer_schema_length=10000)
+    if ext in (".tsv", ".tab"):
+        return pl.read_csv(src, separator="\t", ignore_errors=True, infer_schema_length=10000)
+    if ext in (".parquet", ".pq"):
+        return pl.read_parquet(src)
+    if ext in (".feather", ".ftr", ".arrow", ".ipc"):
+        return pl.read_ipc(src)
+    if ext in (".jsonl", ".ndjson"):
+        return pl.read_ndjson(src)
+    if ext == ".json":
+        raw = open(src, "r", encoding="utf-8").read().strip()
+        if raw.startswith("["):
+            return pl.read_json(src)
+        # Try NDJSON
+        if "\n" in raw and raw.split("\n")[0].strip().startswith("{"):
+            return pl.read_ndjson(src)
+        # Try wrapper object
+        obj = json.loads(raw)
+        if isinstance(obj, dict):
+            for key in ("data", "rows", "items", "records", "results", "entries", "samples"):
+                if key in obj and isinstance(obj[key], list):
+                    return pl.DataFrame(obj[key])
+            # Last resort - take first list value
+            for v in obj.values():
+                if isinstance(v, list) and len(v) > 0 and isinstance(v[0], dict):
+                    return pl.DataFrame(v)
+        return pl.read_json(src)
+    if ext == ".txt":
+        return pl.read_csv(src, ignore_errors=True, infer_schema_length=10000)
+
+    # Fallback: try csv
+    return pl.read_csv(src, ignore_errors=True, infer_schema_length=10000)
+
+
+def normalize(input_path: str, output_path: str):
+    df = _load(input_path)
+    os.makedirs(os.path.dirname(output_path), exist_ok=True)
+    df.write_parquet(output_path)
+    return df.height
+
+
+def main():
+    if len(sys.argv) < 3:
+        print(json.dumps({"ok": False, "error": "Usage: normalize_engine.py <input> <output>"}))
+        sys.exit(1)
+
+    input_path = sys.argv[1]
+    output_path = sys.argv[2]
+
+    if not os.path.exists(input_path):
+        print(json.dumps({"ok": False, "error": f"File not found: {input_path}"}))
+        sys.exit(1)
+
+    try:
+        rows = normalize(input_path, output_path)
+        print(json.dumps({"ok": True, "output_path": output_path, "rows": rows}))
+    except Exception as e:
+        print(json.dumps({"ok": False, "error": str(e)}))
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

package/src/python/requirements.txt

@@ -0,0 +1,12 @@
+polars==1.2.0
+pandas==2.2.0
+numpy==1.26.0
+scikit-learn==1.4.0
+# Optional source/download extras:
+kaggle>=1.6.17
+aiohttp>=3.9.0
+aiofiles>=24.1.0
+datasets>=2.20.0
+webdataset>=0.2.86
+# Optional for secure key storage (preferred over file fallback):
+# keyring>=24.0.0

package/src/python/vesper/core/asset_downloader.py

@@ -191,6 +191,7 @@ class AssetDownloader:
         kaggle_ref: Optional[str] = None,
         urls: Optional[List[str]] = None,
         output_format: str = "webdataset",
+        output_dir: Optional[str] = None,
         max_items: Optional[int] = None,
         image_column: Optional[str] = None,
     ) -> Dict[str, Any]:
@@ -231,7 +232,10 @@ class AssetDownloader:
                 raise ValueError("urls are required for source=url")
 
         # --- Now safe to create directories ---
-        dataset_dir = self.output_root / dataset_id.replace("/", "_").replace(":", "_")
+        if output_dir:
+            dataset_dir = Path(output_dir).expanduser().resolve()
+        else:
+            dataset_dir = self.output_root / dataset_id.replace("/", "_").replace(":", "_")
         images_dir = dataset_dir / "images"
         dataset_dir.mkdir(parents=True, exist_ok=True)
         images_dir.mkdir(parents=True, exist_ok=True)

package/wizard.cjs

@@ -0,0 +1,3 @@
+#!/usr/bin/env node
+
+require('./scripts/wizard.cjs');