nomic 3.1.1__tar.gz → 3.1.3__tar.gz

{nomic-3.1.1 → nomic-3.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nomic
-Version: 3.1.1
+Version: 3.1.3
 Summary: The official Nomic python client.
 Home-page: https://github.com/nomic-ai/nomic
 Author: nomic.ai

{nomic-3.1.1 → nomic-3.1.3}/nomic/aws/sagemaker.py

@@ -38,26 +38,6 @@ def parse_sagemaker_response(response):
     return resp["embeddings"]
 
 
-def preprocess_texts(texts: List[str], task_type: str = "search_document"):
-    """
-    Preprocess a list of texts for embedding using a sagemaker model.
-
-    Args:
-        texts: List of texts to be embedded.
-        task_type: The task type to use when embedding. One of `search_query`, `search_document`, `classification`, `clustering`
-
-    Returns:
-        List of texts formatted for sagemaker embedding.
-    """
-    assert task_type in [
-        "search_query",
-        "search_document",
-        "classification",
-        "clustering",
-    ], f"Invalid task type: {task_type}"
-    return [f"{task_type}: {text}" for text in texts]
-
-
 def batch_transform_text(
     s3_input_path: str,
     s3_output_path: str,
@@ -157,7 +137,13 @@ def embed_text(
         logger.warning("No texts to embed.")
         return None
 
-    texts = preprocess_texts(texts, task_type)
+    assert task_type in [
+        "search_query",
+        "search_document",
+        "classification",
+        "clustering",
+    ], f"Invalid task type: {task_type}"
+
     assert dimensionality in (
         64,
         128,
@@ -175,6 +161,7 @@ def embed_text(
                 "texts": texts[i : i + batch_size],
                 "binary": binary,
                 "dimensionality": dimensionality,
+                "task_type": task_type,
             }
         )
         response = client.invoke_endpoint(EndpointName=sagemaker_endpoint, Body=batch, ContentType="application/json")

{nomic-3.1.1 → nomic-3.1.3}/nomic/dataset.py

@@ -1409,9 +1409,10 @@ class AtlasDataset(AtlasClass):
         # TODO: add support for other modalities
         images = []
         for uuid, blob in tqdm(zip(ids, blobs), total=len(ids), desc="Loading images"):
-            if isinstance(blob, str) and os.path.exists(blob):
+            if (isinstance(blob, str) or isinstance(blob, Path)) and os.path.exists(blob):
                 # Auto resize to max 512x512
                 image = Image.open(blob)
+                image = image.convert("RGB")
                 if image.height > 512 or image.width > 512:
                     image = image.resize((512, 512))
                 buffered = BytesIO()
@@ -1420,6 +1421,7 @@ class AtlasDataset(AtlasClass):
             elif isinstance(blob, bytes):
                 images.append((uuid, blob))
             elif isinstance(blob, Image.Image):
+                blob = blob.convert("RGB")  # type: ignore
                 if blob.height > 512 or blob.width > 512:
                     blob = blob.resize((512, 512))
                 buffered = BytesIO()

{nomic-3.1.1 → nomic-3.1.3}/nomic.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nomic
-Version: 3.1.1
+Version: 3.1.3
 Summary: The official Nomic python client.
 Home-page: https://github.com/nomic-ai/nomic
 Author: nomic.ai

{nomic-3.1.1 → nomic-3.1.3}/nomic.egg-info/requires.txt

@@ -25,7 +25,7 @@ coverage
 pylint
 pytest
 isort
-pyright
+pyright<=1.1.377
 myst-parser
 mkdocs-material
 mkautodoc

{nomic-3.1.1 → nomic-3.1.3}/setup.py

@@ -8,7 +8,7 @@ description = "The official Nomic python client."
 
 setup(
     name="nomic",
-    version="3.1.1",
+    version="3.1.3",
     url="https://github.com/nomic-ai/nomic",
     description=description,
     long_description=description,
@@ -48,7 +48,7 @@ setup(
             "pylint",
             "pytest",
             "isort",
-            "pyright",
+            "pyright<=1.1.377",
             "myst-parser",
             "mkdocs-material",
             "mkautodoc",