vesper-wizard 2.0.7 → 2.0.8

package/README.md

@@ -222,6 +222,28 @@ export_dataset(
 
 ---
 
+#### `vesper_download_assets`
+Download image/media assets to a user-controlled local directory.
+
+**Parameters:**
+- `dataset_id` (string): Dataset identifier
+- `source` (string): `huggingface`, `kaggle`, or `url`
+- `target_dir` (string, optional): Exact local directory where assets should be written
+- `output_dir` (string, optional): Alias for `target_dir`
+- `output_format` (string, optional): `webdataset`, `imagefolder`, or `parquet`
+
+**Example:**
+```
+vesper_download_assets(
+  dataset_id="cats_vs_dogs",
+  source="kaggle",
+  target_dir="./datasets/cats_dogs_100",
+  output_format="imagefolder"
+)
+```
+
+---
+
 ### Quality Analysis
 
 #### `analyze_image_quality`

package/build/index.js

@@ -960,6 +960,8 @@ server.setRequestHandler(ListToolsRequestSchema, async () => {
                         kaggle_ref: { type: "string", description: "Kaggle dataset ref (owner/dataset)." },
                         urls: { type: "array", items: { type: "string" }, description: "Direct asset URLs." },
                         output_format: { type: "string", enum: ["webdataset", "imagefolder", "parquet"], description: "Output asset format." },
+                        target_dir: { type: "string", description: "Optional local directory where downloaded assets should be written. If provided, Vesper writes directly to this directory instead of managed asset storage." },
+                        output_dir: { type: "string", description: "Alias for target_dir. When provided, downloaded assets are written directly to this local directory." },
                         max_items: { type: "number", description: "Optional cap on number of assets to fetch." },
                         workers: { type: "number", description: "Parallel worker count (default 8)." },
                         image_column: { type: "string", description: "Explicit image column name. If omitted, auto-detected from HF features, column names, and sample values." },
@@ -1521,6 +1523,11 @@ server.setRequestHandler(CallToolRequestSchema, async (request) => {
                 ? (request.params.arguments?.urls).map(v => String(v))
                 : undefined;
             const outputFormat = String(request.params.arguments?.output_format || "webdataset");
+            const requestedOutputDir = request.params.arguments?.target_dir
+                ? String(request.params.arguments.target_dir).trim()
+                : request.params.arguments?.output_dir
+                    ? String(request.params.arguments.output_dir).trim()
+                    : undefined;
             const maxItems = request.params.arguments?.max_items ? Number(request.params.arguments.max_items) : undefined;
             const workers = request.params.arguments?.workers ? Number(request.params.arguments.workers) : 8;
             const imageColumn = request.params.arguments?.image_column ? String(request.params.arguments.image_column) : undefined;
@@ -1563,6 +1570,7 @@ server.setRequestHandler(CallToolRequestSchema, async (request) => {
                 kaggle_ref: kaggleRef,
                 urls,
                 output_format: outputFormat,
+                output_dir: requestedOutputDir,
                 max_items: maxItems,
                 workers,
                 image_column: imageColumn,

package/build/python/asset_downloader_engine.py

@@ -26,6 +26,7 @@ def _print(payload: Dict[str, Any]) -> None:
 async def _run_download(args: argparse.Namespace) -> Dict[str, Any]:
     payload = json.loads(args.payload)
     output_root = payload.get("output_root") or str(Path.home() / ".vesper" / "data" / "assets")
+    output_dir = payload.get("output_dir")
     workers = int(payload.get("workers") or 8)
     recipes_dir = payload.get("recipes_dir")
 
@@ -43,6 +44,7 @@ async def _run_download(args: argparse.Namespace) -> Dict[str, Any]:
         kaggle_ref=payload.get("kaggle_ref"),
         urls=payload.get("urls"),
         output_format=payload.get("output_format", "webdataset"),
+        output_dir=str(output_dir) if output_dir else None,
         max_items=payload.get("max_items"),
         image_column=payload.get("image_column"),
     )

package/build/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/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vesper-wizard",
-  "version": "2.0.7",
+  "version": "2.0.8",
   "description": "AI-powered dataset discovery, quality analysis, and preparation MCP server with multimodal support (text, image, audio, video)",
   "type": "module",
   "main": "build/index.js",

package/src/python/asset_downloader_engine.py

@@ -26,6 +26,7 @@ def _print(payload: Dict[str, Any]) -> None:
 async def _run_download(args: argparse.Namespace) -> Dict[str, Any]:
     payload = json.loads(args.payload)
     output_root = payload.get("output_root") or str(Path.home() / ".vesper" / "data" / "assets")
+    output_dir = payload.get("output_dir")
     workers = int(payload.get("workers") or 8)
     recipes_dir = payload.get("recipes_dir")
 
@@ -43,6 +44,7 @@ async def _run_download(args: argparse.Namespace) -> Dict[str, Any]:
         kaggle_ref=payload.get("kaggle_ref"),
         urls=payload.get("urls"),
         output_format=payload.get("output_format", "webdataset"),
+        output_dir=str(output_dir) if output_dir else None,
         max_items=payload.get("max_items"),
         image_column=payload.get("image_column"),
     )

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)