datachain 0.14.0__tar.gz → 0.14.2__tar.gz

{datachain-0.14.0/src/datachain.egg-info → datachain-0.14.2}/PKG-INFO

@@ -1,9 +1,9 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.14.0
+Version: 0.14.2
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
-License: Apache-2.0
+License-Expression: Apache-2.0
 Project-URL: Documentation, https://datachain.dvc.ai
 Project-URL: Issues, https://github.com/iterative/datachain/issues
 Project-URL: Source, https://github.com/iterative/datachain
@@ -38,7 +38,7 @@ Requires-Dist: sqlalchemy>=2
 Requires-Dist: multiprocess==0.70.16
 Requires-Dist: cloudpickle
 Requires-Dist: orjson>=3.10.5
-Requires-Dist: pydantic<3,>=2
+Requires-Dist: pydantic<2.11,>=2
 Requires-Dist: jmespath>=1.0
 Requires-Dist: datamodel-code-generator>=0.25
 Requires-Dist: Pillow<12,>=10.0.0
@@ -171,8 +171,8 @@ high confidence scores.
 
     import datachain as dc
 
-    meta = dc.from_json("gs://datachain-demo/dogs-and-cats/*json", object_name="meta", anon=True)
-    images = dc.from_storage("gs://datachain-demo/dogs-and-cats/*jpg", anon=True)
+    meta = dc.read_json("gs://datachain-demo/dogs-and-cats/*json", object_name="meta", anon=True)
+    images = dc.read_storage("gs://datachain-demo/dogs-and-cats/*jpg", anon=True)
 
     images_id = images.map(id=lambda file: file.path.split('.')[-2])
     annotated = images_id.merge(meta, on="id", right_on="meta.id")
@@ -213,7 +213,7 @@ Python code:
          return result.lower().startswith("success")
 
     chain = (
-       dc.from_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
+       dc.read_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
        .settings(parallel=4, cache=True)
        .map(is_success=eval_dialogue)
        .save("mistral_files")

{datachain-0.14.0 → datachain-0.14.2}/README.rst

@@ -60,8 +60,8 @@ high confidence scores.
 
     import datachain as dc
 
-    meta = dc.from_json("gs://datachain-demo/dogs-and-cats/*json", object_name="meta", anon=True)
-    images = dc.from_storage("gs://datachain-demo/dogs-and-cats/*jpg", anon=True)
+    meta = dc.read_json("gs://datachain-demo/dogs-and-cats/*json", object_name="meta", anon=True)
+    images = dc.read_storage("gs://datachain-demo/dogs-and-cats/*jpg", anon=True)
 
     images_id = images.map(id=lambda file: file.path.split('.')[-2])
     annotated = images_id.merge(meta, on="id", right_on="meta.id")
@@ -102,7 +102,7 @@ Python code:
          return result.lower().startswith("success")
 
     chain = (
-       dc.from_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
+       dc.read_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
        .settings(parallel=4, cache=True)
        .map(is_success=eval_dialogue)
        .save("mistral_files")

{datachain-0.14.0 → datachain-0.14.2}/docs/examples.md

@@ -16,7 +16,7 @@ title: Examples
     import datachain as dc # (1)!
     from transformers import AutoProcessor, PaliGemmaForConditionalGeneration # (2)!
 
-    images = dc.from_storage("gs://datachain-demo/newyorker_caption_contest/images", type="image")
+    images = dc.read_storage("gs://datachain-demo/newyorker_caption_contest/images", type="image")
 
     model = PaliGemmaForConditionalGeneration.from_pretrained("google/paligemma-3b-mix-224")
     processor = AutoProcessor.from_pretrained("google/paligemma-3b-mix-224")
@@ -93,20 +93,20 @@ dc.DataModel.register(MistralModel)
 
 chain = (
     dc
-    .from_storage("gs://datachain-demo/chatbot-KiT/", type="text")
+    .read_storage("gs://datachain-demo/chatbot-KiT/", type="text")
     .filter(dc.Column("file.name").glob("*.txt"))
     .limit(5)
     .settings(parallel=4, cache=True)
     .map(
-       mistral=lambda file: MistralClient(api_key=api_key).chat(
-                                          model="open-mixtral-8x22b",
-                                          response_format={"type": "json_object"},
-                                          messages= [
-                                             ChatMessage(role="system", content=f"{prompt}"),
-                                             ChatMessage(role="user", content=f"{file.read()}")
-                                          ]
-                            ),
-       output=MistralModel
+        mistral=lambda file: MistralClient(api_key=api_key).chat(
+            model="open-mixtral-8x22b",
+            response_format={"type": "json_object"},
+            messages=[
+                ChatMessage(role="system", content=f"{prompt}"),
+                ChatMessage(role="user", content=f"{file.read()}")
+            ]
+        ),
+        output=MistralModel
     )
     .save("dialog-rating")
 )
@@ -145,7 +145,7 @@ The cost of 5 calls to Mixtral 8x22b : $0.0142
 The “save” operation makes chain dataset persistent in the current (working) directory of the query. A hidden folder `.datachain/` holds the records. A persistent dataset can be accessed later to start a derivative chain:
 
 ```python
-dc.from_dataset("rating").limit(2).save("dialog-rating")
+dc.read_dataset("rating").limit(2).save("dialog-rating")
 ```
 
 Persistent datasets are immutable and automatically versioned. Here is how to access the dataset registry:
@@ -167,7 +167,7 @@ dialog-rating@v2
 By default, when a saved dataset is loaded, the latest version is fetched but another version can be requested:
 
 ```python
-ds = dc.from_dataset("dialog-rating", version = 1)
+ds = dc.read_dataset("dialog-rating", version=1)
 ```
 
 ### Chain execution, optimization and parallelism
@@ -189,8 +189,8 @@ Here is an example of reading a simple CSV file where schema is heuristically de
 ```python
 from datachain import DataChain
 
-uri="gs://datachain-demo/chatbot-csv/"
-csv_dataset = dc.from_csv(uri)
+uri = "gs://datachain-demo/chatbot-csv/"
+csv_dataset = dc.read_csv(uri)
 
 print(csv_dataset.to_pandas())
 ```
@@ -233,12 +233,12 @@ However, Datachain can easily parse the entire COCO structure via several readin
 ```python
 import datachain as dc
 
-images_uri="gs://datachain-demo/coco2017/images/val/"
-captions_uri="gs://datachain-demo/coco2017/annotations/captions_val2017.json"
+images_uri = "gs://datachain-demo/coco2017/images/val/"
+captions_uri = "gs://datachain-demo/coco2017/annotations/captions_val2017.json"
 
-images = dc.from_storage(images_uri)
-meta = dc.from_json(captions_uri, jmespath = "images")
-captions = dc.from_json(captions_uri, jmespath = "annotations")
+images = dc.read_storage(images_uri)
+meta = dc.read_json(captions_uri, jmespath="images")
+captions = dc.read_json(captions_uri, jmespath="annotations")
 
 images_meta = images.merge(meta, on="file.name", right_on="images.file_name")
 captioned_images = images_meta.merge(captions, on="images.id", right_on="annotations.image_id")

{datachain-0.14.0 → datachain-0.14.2}/docs/quick-start.md

@@ -39,8 +39,8 @@ using JSON metadata:
 ``` py
 import datachain as dc
 
-meta = dc.from_json("gs://datachain-demo/dogs-and-cats/*json", object_name="meta", anon=True)
-images = dc.from_storage("gs://datachain-demo/dogs-and-cats/*jpg", anon=True)
+meta = dc.read_json("gs://datachain-demo/dogs-and-cats/*json", object_name="meta", anon=True)
+images = dc.read_storage("gs://datachain-demo/dogs-and-cats/*jpg", anon=True)
 
 images_id = images.map(id=lambda file: file.path.split('.')[-2])
 annotated = images_id.merge(meta, on="id", right_on="meta.id")
@@ -77,7 +77,7 @@ def is_positive_dialogue_ending(file) -> bool:
     return classifier(dialogue_ending)[0]["label"] == "POSITIVE"
 
 chain = (
-   dc.from_storage("gs://datachain-demo/chatbot-KiT/",
+   dc.read_storage("gs://datachain-demo/chatbot-KiT/",
                           object_name="file", type="text", anon=True)
    .settings(parallel=8, cache=True)
    .map(is_positive=is_positive_dialogue_ending)
@@ -132,7 +132,7 @@ def eval_dialogue(file: dc.File) -> bool:
      return result.lower().startswith("success")
 
 chain = (
-   dc.from_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
+   dc.read_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
    .map(is_success=eval_dialogue)
    .save("mistral_files")
 )
@@ -177,7 +177,7 @@ def eval_dialog(file: dc.File) -> ChatCompletionResponse:
                    {"role": "user", "content": file.read()}])
 
 chain = (
-   dc.from_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
+   dc.read_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
    .settings(parallel=4, cache=True)
    .map(response=eval_dialog)
    .map(status=lambda response: response.choices[0].message.content.lower()[:7])
@@ -210,14 +210,14 @@ name                  usage        usage             usage
 
 In the previous examples, datasets were saved in the embedded database
 (`SQLite` in folder `.datachain` of the working directory). These datasets were automatically versioned, and
-can be accessed using `dc.from_dataset("dataset_name")`.
+can be accessed using `dc.read_dataset("dataset_name")`.
 
 Here is how to retrieve a saved dataset and iterate over the objects:
 
 ``` py
 import datachain as dc
 
-chain = dc.from_dataset("response")
+chain = dc.read_dataset("response")
 
 # Iterating one-by-one: support out-of-memory workflow
 for file, response in chain.limit(5).collect("file", "response"):
@@ -248,7 +248,7 @@ output tokens:
 
 ``` py
 import datachain as dc
-chain = dc.from_dataset("mistral_dataset")
+chain = dc.read_dataset("mistral_dataset")
 
 cost = chain.sum("response.usage.prompt_tokens")*0.000002 \
            + chain.sum("response.usage.completion_tokens")*0.000006
@@ -276,7 +276,7 @@ import datachain as dc
 processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
 
 chain = (
-    dc.from_storage("gs://datachain-demo/dogs-and-cats/", type="image", anon=True)
+    dc.read_storage("gs://datachain-demo/dogs-and-cats/", type="image", anon=True)
     .map(label=lambda name: name.split(".")[0], params=["file.name"])
     .select("file", "label").to_pytorch(
         transform=processor.image_processor,

{datachain-0.14.0 → datachain-0.14.2}/docs/references/data-types/file.md

@@ -2,12 +2,12 @@
 
 `File` is a special [`DataModel`](index.md#datachain.lib.data_model.DataModel),
 which is automatically generated when a `DataChain` is created from files,
-such as in [`dc.from_storage`](../datachain.md#datachain.lib.dc.storage.from_storage):
+such as in [`dc.read_storage`](../datachain.md#datachain.lib.dc.storage.read_storage):
 
 ```python
 import datachain as dc
 
-chain = dc.from_storage("gs://datachain-demo/dogs-and-cats")
+chain = dc.read_storage("gs://datachain-demo/dogs-and-cats")
 chain.print_schema()
 ```
 

{datachain-0.14.0 → datachain-0.14.2}/docs/references/data-types/imagefile.md

@@ -2,12 +2,12 @@
 
 `ImageFile` is inherited from [`File`](file.md) with additional methods for working with image files.
 
-`ImageFile` is generated when a `DataChain` is created [from storage](../datachain.md#datachain.lib.dc.storage.from_storage), using `type="image"` param:
+`ImageFile` is generated when a `DataChain` is created [from storage](../datachain.md#datachain.lib.dc.storage.read_storage), using `type="image"` param:
 
 ```python
 import datachain as dc
 
-chain = dc.from_storage("s3://bucket-name/", type="image")
+chain = dc.read_storage("s3://bucket-name/", type="image")
 ```
 
 ::: datachain.lib.file.ImageFile

{datachain-0.14.0 → datachain-0.14.2}/docs/references/data-types/textfile.md

@@ -2,12 +2,12 @@
 
 `TextFile` is inherited from [`File`](file.md) with additional methods for working with text files.
 
-`TextFile` is generated when a `DataChain` is created [from storage](../datachain.md#datachain.lib.dc.storage.from_storage), using `type="text"` param:
+`TextFile` is generated when a `DataChain` is created [from storage](../datachain.md#datachain.lib.dc.storage.read_storage), using `type="text"` param:
 
 ```python
 import datachain as dc
 
-chain = dc.from_storage("s3://bucket-name/", type="text")
+chain = dc.read_storage("s3://bucket-name/", type="text")
 ```
 
 ::: datachain.lib.file.TextFile

{datachain-0.14.0 → datachain-0.14.2}/docs/references/data-types/videofile.md

@@ -2,12 +2,12 @@
 
 `VideoFile` extends [`File`](file.md) and provides additional methods for working with video files.
 
-`VideoFile` instances are created when a `DataChain` is initialized [from storage](../datachain.md#datachain.lib.dc.storage.from_storage) with the `type="video"` parameter:
+`VideoFile` instances are created when a `DataChain` is initialized [from storage](../datachain.md#datachain.lib.dc.storage.read_storage) with the `type="video"` parameter:
 
 ```python
 import datachain as dc
 
-chain = dc.from_storage("s3://bucket-name/", type="video")
+chain = dc.read_storage("s3://bucket-name/", type="video")
 ```
 
 There are additional models for working with video files:

{datachain-0.14.0 → datachain-0.14.2}/docs/references/datachain.md

@@ -9,27 +9,27 @@ for examples of how to create a chain.
 
 ::: datachain.query.schema.Column
 
-::: datachain.lib.dc.csv.from_csv
+::: datachain.lib.dc.csv.read_csv
 
-::: datachain.lib.dc.datasets.from_dataset
+::: datachain.lib.dc.datasets.read_dataset
 
 ::: datachain.lib.dc.datasets.datasets
 
-::: datachain.lib.dc.hf.from_hf
+::: datachain.lib.dc.hf.read_hf
 
-::: datachain.lib.dc.json.from_json
+::: datachain.lib.dc.json.read_json
 
 ::: datachain.lib.dc.listings.listings
 
-::: datachain.lib.dc.pandas.from_pandas
+::: datachain.lib.dc.pandas.read_pandas
 
-::: datachain.lib.dc.parquet.from_parquet
+::: datachain.lib.dc.parquet.read_parquet
 
-::: datachain.lib.dc.records.from_records
+::: datachain.lib.dc.records.read_records
 
-::: datachain.lib.dc.storage.from_storage
+::: datachain.lib.dc.storage.read_storage
 
-::: datachain.lib.dc.values.from_values
+::: datachain.lib.dc.values.read_values
 
 ::: datachain.lib.dc.DataChain
 

{datachain-0.14.0 → datachain-0.14.2}/docs/references/remotes.md

@@ -1,17 +1,17 @@
 # Interacting with remote storage
 
-DataChain supports reading and writing data from different remote storages using methods like `dc.from_storage` and `dc.to_storage`. The supported storages includes: local file system, AWS S3 storage, Google Cloud Storage, Azure Blob Storage, Hugging Face and more.
+DataChain supports reading and writing data from different remote storages using methods like `dc.read_storage` and `dc.to_storage`. The supported storages includes: local file system, AWS S3 storage, Google Cloud Storage, Azure Blob Storage, Hugging Face and more.
 
 Example implementation for reading and writing data from/to different remote storages:
 
 ```python
 import datachain as dc
 
-dc = dc.from_storage("s3://bucket-name/path/to/data")
+dc = dc.read_storage("s3://bucket-name/path/to/data")
 dc.to_storage("gs://bucket-name/path/to/data")
 ```
 
-DataChain uses [fsspec](https://filesystem-spec.readthedocs.io/en/latest/) to interact with different remote storages. You can pass the following fsspec-supported URIs to `from_storage` and `to_storage` methods.
+DataChain uses [fsspec](https://filesystem-spec.readthedocs.io/en/latest/) to interact with different remote storages. You can pass the following fsspec-supported URIs to `read_storage` and `to_storage` methods.
 
 - Local file system: `file://path/to/data`
 - AWS S3 storage: `s3://bucket-name/path/to/data`
@@ -134,8 +134,9 @@ DataChain uses [s3fs](https://s3fs.readthedocs.io/en/latest/) to interact with A
 
 
 Example:
+
 ```python
-chain = dc.from_storage(
+chain = dc.read_storage(
     "s3://my-bucket/my-dir",
     client_config = {
 		"endpoint_url": "<minio-endpoint-url>",

{datachain-0.14.0 → datachain-0.14.2}/examples/computer_vision/iptc_exif_xmp_lib.py

@@ -67,7 +67,7 @@ def image_description(file):
 
 if __name__ == "__main__":
     (
-        dc.from_storage(source, type="image")
+        dc.read_storage(source, type="image")
         .settings(parallel=-1)
         .filter(dc.C("file.path").glob("*.jpg"))
         .limit(5000)

{datachain-0.14.0 → datachain-0.14.2}/examples/computer_vision/llava2_image_desc_lib.py

@@ -71,7 +71,7 @@ class LLaVADescribe(dc.Mapper):
 
 if __name__ == "__main__":
     (
-        dc.from_storage(source, type="image")
+        dc.read_storage(source, type="image")
         .filter(dc.C("file.path").glob("*/cat*.jpg"))
         .map(
             desc=LLaVADescribe(

{datachain-0.14.0 → datachain-0.14.2}/examples/computer_vision/openimage-detect.py

@@ -41,7 +41,7 @@ def openimage_detect(args):
 source = "gs://datachain-demo/openimages-v6-test-jsonpairs/"
 
 (
-    dc.from_storage(source)
+    dc.read_storage(source)
     .filter(dc.C("file.path").glob("*.jpg") | dc.C("file.path").glob("*.json"))
     .agg(
         openimage_detect,

{datachain-0.14.0 → datachain-0.14.2}/examples/computer_vision/ultralytics-bbox.py

@@ -10,7 +10,7 @@ def process_bboxes(yolo: YOLO, file: dc.File) -> YoloBBoxes:
 
 
 (
-    dc.from_storage("gs://datachain-demo/openimages-v6-test-jsonpairs/")
+    dc.read_storage("gs://datachain-demo/openimages-v6-test-jsonpairs/")
     .filter(dc.C("file.path").glob("*.jpg"))
     .limit(20)
     .setup(yolo=lambda: YOLO("yolo11n.pt"))

{datachain-0.14.0 → datachain-0.14.2}/examples/computer_vision/ultralytics-pose.py

@@ -10,7 +10,7 @@ def process_poses(yolo: YOLO, file: dc.File) -> YoloPoses:
 
 
 (
-    dc.from_storage("gs://datachain-demo/openimages-v6-test-jsonpairs/")
+    dc.read_storage("gs://datachain-demo/openimages-v6-test-jsonpairs/")
     .filter(dc.C("file.path").glob("*.jpg"))
     .limit(20)
     .setup(yolo=lambda: YOLO("yolo11n-pose.pt"))

{datachain-0.14.0 → datachain-0.14.2}/examples/computer_vision/ultralytics-segment.py

@@ -10,7 +10,7 @@ def process_segments(yolo: YOLO, file: dc.File) -> YoloSegments:
 
 
 (
-    dc.from_storage("gs://datachain-demo/openimages-v6-test-jsonpairs/")
+    dc.read_storage("gs://datachain-demo/openimages-v6-test-jsonpairs/")
     .filter(dc.C("file.path").glob("*.jpg"))
     .limit(20)
     .setup(yolo=lambda: YOLO("yolo11n-seg.pt"))

{datachain-0.14.0 → datachain-0.14.2}/examples/get_started/common_sql_functions.py

@@ -9,7 +9,7 @@ def num_chars_udf(file):
     return ([],)
 
 
-chain = dc.from_storage("gs://datachain-demo/dogs-and-cats/", anon=True)
+chain = dc.read_storage("gs://datachain-demo/dogs-and-cats/", anon=True)
 chain.map(num_chars_udf, params=["file"], output={"num_chars": list[str]}).select(
     "file.path", "num_chars"
 ).show(5)

{datachain-0.14.0 → datachain-0.14.2}/examples/get_started/json-csv-reader.py

@@ -31,7 +31,7 @@ ChatFeature = ModelStore.register(ChatDialog)
 def main():
     # Dynamic JSONl schema from 2 objects
     uri = "gs://datachain-demo/jsonl/object.jsonl"
-    jsonl_ds = dc.from_json(uri, format="jsonl", anon="True")
+    jsonl_ds = dc.read_json(uri, format="jsonl", anon="True")
     jsonl_ds.show()
 
     # Dynamic JSON schema from 200 OpenImage json-pairs with validation errors
@@ -39,7 +39,7 @@ def main():
     schema_uri = (
         "gs://datachain-demo/openimages-v6-test-jsonpairs/08392c290ecc9d2a.json"
     )
-    json_pairs_ds = dc.from_json(
+    json_pairs_ds = dc.read_json(
         uri, schema_from=schema_uri, jmespath="@", model_name="OpenImage", anon="True"
     )
     json_pairs_ds.show()
@@ -47,29 +47,29 @@ def main():
     uri = "gs://datachain-demo/coco2017/annotations_captions/"
 
     # Print JSON schema in Pydantic format from main COCO annotation
-    chain = dc.from_storage(uri, anon="True").filter(dc.C("file.path").glob("*.json"))
+    chain = dc.read_storage(uri, anon="True").filter(dc.C("file.path").glob("*.json"))
     file = next(chain.limit(1).collect("file"))
     print(gen_datamodel_code(file, jmespath="@", model_name="Coco"))
 
     # Static JSON schema test parsing 3/7 objects
-    static_json_ds = dc.from_json(
+    static_json_ds = dc.read_json(
         uri, jmespath="licenses", spec=LicenseFeature, nrows=3, anon="True"
     )
     static_json_ds.show()
 
     # Dynamic JSON schema test parsing 5K objects
-    dynamic_json_ds = dc.from_json(uri, jmespath="images", anon="True")
+    dynamic_json_ds = dc.read_json(uri, jmespath="images", anon="True")
     print(dynamic_json_ds.to_pandas())
 
     # Static CSV with header schema test parsing 3.5K objects
     uri = "gs://datachain-demo/chatbot-csv/"
-    static_csv_ds = dc.from_csv(uri, output=ChatDialog, object_name="chat", anon="True")
+    static_csv_ds = dc.read_csv(uri, output=ChatDialog, object_name="chat", anon="True")
     static_csv_ds.print_schema()
     static_csv_ds.show()
 
     # Dynamic CSV with header schema test parsing 3/3M objects
     uri = "gs://datachain-demo/laion-aesthetics-csv/laion_aesthetics_1024_33M_1.csv"
-    dynamic_csv_ds = dc.from_csv(uri, object_name="laion", nrows=3, anon="True")
+    dynamic_csv_ds = dc.read_csv(uri, object_name="laion", nrows=3, anon="True")
     dynamic_csv_ds.print_schema()
     dynamic_csv_ds.show()
 

{datachain-0.14.0 → datachain-0.14.2}/examples/get_started/torch-loader.py

@@ -55,7 +55,7 @@ class CNN(nn.Module):
 
 if __name__ == "__main__":
     ds = (
-        dc.from_storage(STORAGE, type="image")
+        dc.read_storage(STORAGE, type="image")
         .settings(prefetch=25)
         .filter(dc.C("file.path").glob("*.jpg"))
         .map(

{datachain-0.14.0 → datachain-0.14.2}/examples/get_started/udfs/parallel.py

@@ -30,7 +30,7 @@ def path_len_benchmark(path):
 
 
 # Run in chain
-dc.from_storage(
+dc.read_storage(
     "gs://datachain-demo/dogs-and-cats/",
 ).settings(parallel=-1).map(
     path_len_benchmark,

{datachain-0.14.0 → datachain-0.14.2}/examples/get_started/udfs/simple.py

@@ -10,7 +10,7 @@ def path_len(path):
 
 if __name__ == "__main__":
     # Run in chain
-    dc.from_storage(
+    dc.read_storage(
         uri="gs://datachain-demo/dogs-and-cats/",
     ).map(
         path_len,

{datachain-0.14.0 → datachain-0.14.2}/examples/get_started/udfs/stateful.py

@@ -34,7 +34,7 @@ class ImageEncoder(dc.Mapper):
 if __name__ == "__main__":
     # Run in chain
     (
-        dc.from_storage("gs://datachain-demo/dogs-and-cats/", type="image")
+        dc.read_storage("gs://datachain-demo/dogs-and-cats/", type="image")
         .filter(dc.C("file.path").glob("*cat*.jpg"))
         .settings(parallel=2)
         .limit(5)

{datachain-0.14.0 → datachain-0.14.2}/examples/llm_and_nlp/claude-query.py

@@ -39,7 +39,7 @@ class Rating(BaseModel):
 
 
 chain = (
-    dc.from_storage(DATA, type="text")
+    dc.read_storage(DATA, type="text")
     .filter(dc.Column("file.path").glob("*.txt"))
     .limit(5)
     .settings(parallel=4, cache=True)

{datachain-0.14.0 → datachain-0.14.2}/examples/llm_and_nlp/hf-dataset-llm-eval.py

@@ -48,7 +48,7 @@ def eval_dialog(
 # Save to HF as Parquet. Dataset can be previewed here:
 # https://huggingface.co/datasets/dvcorg/test-datachain-llm-eval/viewer
 (
-    dc.from_csv("hf://datasets/infinite-dataset-hub/MobilePlanAssistant/data.csv")
+    dc.read_csv("hf://datasets/infinite-dataset-hub/MobilePlanAssistant/data.csv")
     .settings(parallel=10)
     .setup(client=lambda: InferenceClient("meta-llama/Llama-3.1-70B-Instruct"))
     .map(response=eval_dialog)
@@ -58,7 +58,7 @@ def eval_dialog(
 # Read it back to filter and show.
 # It restores the Pydantic model from Parquet under the hood.
 (
-    dc.from_parquet(
+    dc.read_parquet(
         "hf://datasets/dvcorg/test-datachain-llm-eval/data.parquet", source=False
     )
     .filter(dc.C("response.result") == "Failure")

{datachain-0.14.0 → datachain-0.14.2}/examples/multimodal/clip_inference.py

@@ -9,8 +9,8 @@ source = "gs://datachain-demo/50k-laion-files/000000/00000000*"
 
 
 def create_dataset():
-    imgs = dc.from_storage(source, type="image").filter(dc.C("file.path").glob("*.jpg"))
-    captions = dc.from_storage(source, type="text").filter(
+    imgs = dc.read_storage(source, type="image").filter(dc.C("file.path").glob("*.jpg"))
+    captions = dc.read_storage(source, type="text").filter(
         dc.C("file.path").glob("*.txt")
     )
     return imgs.merge(

{datachain-0.14.0 → datachain-0.14.2}/examples/multimodal/hf_pipeline.py

@@ -50,7 +50,7 @@ if __name__ == "__main__":
     print("** HuggingFace pipeline helper model zoo demo **")
     print("\nZero-shot object detection and classification:")
     (
-        dc.from_storage(
+        dc.read_storage(
             image_source,
             anon=True,
             type="image",
@@ -72,7 +72,7 @@ if __name__ == "__main__":
 
     print("\nNot-safe-for-work image detection:")
     (
-        dc.from_storage(
+        dc.read_storage(
             image_source,
             anon=True,
             type="image",
@@ -95,7 +95,7 @@ if __name__ == "__main__":
     try:
         subprocess.run(["ffmpeg", "-L"], check=True)  # noqa: S603, S607
         (
-            dc.from_storage(
+            dc.read_storage(
                 audio_source,
                 anon=True,
                 type="binary",
@@ -118,7 +118,7 @@ if __name__ == "__main__":
 
     print("\nLong text summarization:")
     (
-        dc.from_storage(
+        dc.read_storage(
             text_source,
             anon=True,
             type="text",

{datachain-0.14.0 → datachain-0.14.2}/examples/multimodal/openai_image_desc_lib.py

@@ -72,7 +72,7 @@ def describe_image(
 
 if __name__ == "__main__":
     (
-        dc.from_storage(
+        dc.read_storage(
             SOURCE,
             anon=True,
         )

{datachain-0.14.0 → datachain-0.14.2}/examples/multimodal/wds.py

@@ -16,18 +16,18 @@ NPZ_METADATA = os.getenv(
 )
 
 wds_images = (
-    dc.from_storage(IMAGE_TARS, type="image")
+    dc.read_storage(IMAGE_TARS, type="image")
     .settings(cache=True)
     .gen(laion=process_webdataset(spec=WDSLaion), params="file")
 )
 
 wds_with_pq = (
-    dc.from_parquet(PARQUET_METADATA)
+    dc.read_parquet(PARQUET_METADATA)
     .settings(cache=True)
     .merge(wds_images, on="uid", right_on="laion.json.uid", inner=True)
 )
 
-wds_npz = dc.from_storage(NPZ_METADATA).settings(cache=True).gen(emd=process_laion_meta)
+wds_npz = dc.read_storage(NPZ_METADATA).settings(cache=True).gen(emd=process_laion_meta)
 
 
 res = wds_npz.merge(

{datachain-0.14.0 → datachain-0.14.2}/examples/multimodal/wds_filtered.py

@@ -6,10 +6,10 @@ from datachain.lib.webdataset_laion import WDSLaion
 
 name = "wds"
 try:
-    wds = dc.from_dataset(name=name)
+    wds = dc.read_dataset(name=name)
 except datachain.error.DatasetNotFoundError:
     wds = (
-        dc.from_storage("gs://datachain-demo/datacomp-small/shards")
+        dc.read_storage("gs://datachain-demo/datacomp-small/shards")
         .filter(dc.C("file.path").glob("*/00000000.tar"))
         .settings(cache=True)
         .gen(laion=process_webdataset(spec=WDSLaion), params="file")