nomic 3.0.36__tar.gz → 3.0.41__tar.gz

{nomic-3.0.36 → nomic-3.0.41}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nomic
-Version: 3.0.36
+Version: 3.0.41
 Summary: The official Nomic python client.
 Home-page: https://github.com/nomic-ai/nomic
 Author: nomic.ai

{nomic-3.0.36 → nomic-3.0.41}/nomic/atlas.py

@@ -38,6 +38,7 @@ def map_data(
 
     Args:
         data: An ordered collection of the datapoints you are structuring. Can be a list of dictionaries, Pandas Dataframe or PyArrow Table.
+        blobs: A list of image paths, bytes, or PIL images to add to your image dataset that are stored locally.
         embeddings: An [N,d] numpy array containing the N embeddings to add.
         identifier: A name for your dataset that is used to generate the dataset identifier. A unique name will be chosen if not supplied.
         description: The description of your dataset

{nomic-3.0.36 → nomic-3.0.41}/nomic/dataset.py

@@ -1041,7 +1041,7 @@ class AtlasDataset(AtlasClass):
             name: The name of the index and the map.
             indexed_field: For text datasets, name the data field corresponding to the text to be mapped.
             reuse_embeddings_from_index: the name of the index to reuse embeddings from.
-            modality: The data modality of this index. Currently, Atlas supports either `text` or `embedding` indices.
+            modality: The data modality of this index. Currently, Atlas supports either `text`, `image`, or `embedding` indices.
             projection: Options for configuring the 2D projection algorithm
             topic_model: Options for configuring the topic model
             duplicate_detection: Options for configuring semantic duplicate detection
@@ -1064,7 +1064,7 @@ class AtlasDataset(AtlasClass):
         elif isinstance(topic_model, NomicTopicOptions):
             pass
         elif topic_model:
-            topic_model = NomicTopicOptions()
+            topic_model = NomicTopicOptions(topic_label_field=indexed_field)
         else:
             topic_model = NomicTopicOptions(build_topic_model=False)
 
@@ -1086,6 +1086,9 @@ class AtlasDataset(AtlasClass):
         else:
             embedding_model = NomicEmbedOptions()
 
+        if modality is None:
+            modality = self.meta["modality"]
+
         colorable_fields = []
 
         for field in self.dataset_fields:
@@ -1093,7 +1096,7 @@ class AtlasDataset(AtlasClass):
                 colorable_fields.append(field)
 
         build_template = {}
-        if self.modality == "embedding":
+        if modality == "embedding":
             if topic_model.topic_label_field is None:
                 logger.warning(
                     "You did not specify the `topic_label_field` option in your topic_model, your dataset will not contain auto-labeled topics."
@@ -1135,7 +1138,7 @@ class AtlasDataset(AtlasClass):
                 ),
             }
 
-        elif self.modality == "text" or self.modality == "image":
+        elif modality == "text" or modality == "image":
             # find the index id of the index with name reuse_embeddings_from_index
             reuse_embedding_from_index_id = None
             indices = self.indices
@@ -1149,13 +1152,18 @@ class AtlasDataset(AtlasClass):
                         f"Could not find the index '{reuse_embeddings_from_index}' to re-use from. Possible options are {[index.name for index in indices]}"
                     )
 
-            if indexed_field is None:
+            if indexed_field is None and modality == "text":
                 raise Exception("You did not specify a field to index. Specify an 'indexed_field'.")
 
+            if modality == "image":
+                indexed_field = "_blob_hash"
+                if indexed_field is not None:
+                    logger.warning("Ignoring indexed_field for image datasets. Only _blob_hash is supported.")
+
             if indexed_field not in self.dataset_fields:
                 raise Exception(f"Indexing on {indexed_field} not allowed. Valid options are: {self.dataset_fields}")
 
-            if self.modality == "image":
+            if modality == "image":
                 if topic_model.topic_label_field is None:
                     print(
                         "You did not specify the `topic_label_field` option in your topic_model, your dataset will not contain auto-labeled topics."
@@ -1163,7 +1171,9 @@ class AtlasDataset(AtlasClass):
                     topic_field = None
                     topic_model.build_topic_model = False
                 else:
-                    topic_field = topic_model.topic_label_field
+                    topic_field = (
+                        topic_model.topic_label_field if topic_model.topic_label_field != indexed_field else None
+                    )
             else:
                 topic_field = topic_model.topic_label_field
 
@@ -1245,7 +1255,7 @@ class AtlasDataset(AtlasClass):
             logger.warning("Could not find a map being built for this dataset.")
         else:
             logger.info(
-                f"Created map `{atlas_projection.name}` in dataset `{self.identifier}`: {atlas_projection.map_link}"
+                f"Created map `{atlas_projection.name}` in dataset `{self.identifier}`: {atlas_projection.dataset_link}"
             )
         return atlas_projection
 
@@ -1346,6 +1356,7 @@ class AtlasDataset(AtlasClass):
         Args:
             data: A pandas DataFrame, list of dictionaries, or pyarrow Table matching the dataset schema.
             embeddings: A numpy array of embeddings: each row corresponds to a row in the table. Use if you already have embeddings for your datapoints.
+            blobs: A list of image paths, bytes, or PIL Images. Use if you want to create an AtlasDataset using image embeddings over your images. Note: Blobs are stored locally only.
             pbar: (Optional). A tqdm progress bar to update.
         """
         if embeddings is not None:
@@ -1364,6 +1375,7 @@ class AtlasDataset(AtlasClass):
         """
         Add data, with associated blobs, to the dataset.
         Uploads blobs to the server and associates them with the data.
+        Blobs must reference objects stored locally
         """
         if isinstance(data, DataFrame):
             data = pa.Table.from_pandas(data)

{nomic-3.0.36 → nomic-3.0.41}/nomic.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: nomic
-Version: 3.0.36
+Version: 3.0.41
 Summary: The official Nomic python client.
 Home-page: https://github.com/nomic-ai/nomic
 Author: nomic.ai

{nomic-3.0.36 → nomic-3.0.41}/setup.py

@@ -8,7 +8,7 @@ description = "The official Nomic python client."
 
 setup(
     name="nomic",
-    version="3.0.36",
+    version="3.0.41",
     url="https://github.com/nomic-ai/nomic",
     description=description,
     long_description=description,