datachain 0.13.1__tar.gz → 0.14.0__tar.gz

{datachain-0.13.1 → datachain-0.14.0}/.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
       - id: trailing-whitespace
         exclude: '^LICENSES/'
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.11.0'
+    rev: 'v0.11.2'
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]

{datachain-0.13.1 → datachain-0.14.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.13.1
+Version: 0.14.0
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0
@@ -169,16 +169,16 @@ high confidence scores.
 
 .. code:: py
 
-    from datachain import Column, DataChain
+    import datachain as dc
 
-    meta = DataChain.from_json("gs://datachain-demo/dogs-and-cats/*json", object_name="meta", anon=True)
-    images = DataChain.from_storage("gs://datachain-demo/dogs-and-cats/*jpg", anon=True)
+    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)
 
     images_id = images.map(id=lambda file: file.path.split('.')[-2])
     annotated = images_id.merge(meta, on="id", right_on="meta.id")
 
-    likely_cats = annotated.filter((Column("meta.inference.confidence") > 0.93) \
-                                   & (Column("meta.inference.class_") == "cat"))
+    likely_cats = annotated.filter((dc.Column("meta.inference.confidence") > 0.93) \
+                                   & (dc.Column("meta.inference.class_") == "cat"))
     likely_cats.to_storage("high-confidence-cats/", signal="file")
 
 
@@ -199,11 +199,11 @@ Python code:
 
     import os
     from mistralai import Mistral
-    from datachain import File, DataChain, Column
+    import datachain as dc
 
     PROMPT = "Was this dialog successful? Answer in a single word: Success or Failure."
 
-    def eval_dialogue(file: File) -> bool:
+    def eval_dialogue(file: dc.File) -> bool:
          client = Mistral(api_key = os.environ["MISTRAL_API_KEY"])
          response = client.chat.complete(
              model="open-mixtral-8x22b",
@@ -213,13 +213,13 @@ Python code:
          return result.lower().startswith("success")
 
     chain = (
-       DataChain.from_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
+       dc.from_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
        .settings(parallel=4, cache=True)
        .map(is_success=eval_dialogue)
        .save("mistral_files")
     )
 
-    successful_chain = chain.filter(Column("is_success") == True)
+    successful_chain = chain.filter(dc.Column("is_success") == True)
     successful_chain.to_storage("./output_mistral")
 
     print(f"{successful_chain.count()} files were exported")

{datachain-0.13.1 → datachain-0.14.0}/README.rst

@@ -58,16 +58,16 @@ high confidence scores.
 
 .. code:: py
 
-    from datachain import Column, DataChain
+    import datachain as dc
 
-    meta = DataChain.from_json("gs://datachain-demo/dogs-and-cats/*json", object_name="meta", anon=True)
-    images = DataChain.from_storage("gs://datachain-demo/dogs-and-cats/*jpg", anon=True)
+    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)
 
     images_id = images.map(id=lambda file: file.path.split('.')[-2])
     annotated = images_id.merge(meta, on="id", right_on="meta.id")
 
-    likely_cats = annotated.filter((Column("meta.inference.confidence") > 0.93) \
-                                   & (Column("meta.inference.class_") == "cat"))
+    likely_cats = annotated.filter((dc.Column("meta.inference.confidence") > 0.93) \
+                                   & (dc.Column("meta.inference.class_") == "cat"))
     likely_cats.to_storage("high-confidence-cats/", signal="file")
 
 
@@ -88,11 +88,11 @@ Python code:
 
     import os
     from mistralai import Mistral
-    from datachain import File, DataChain, Column
+    import datachain as dc
 
     PROMPT = "Was this dialog successful? Answer in a single word: Success or Failure."
 
-    def eval_dialogue(file: File) -> bool:
+    def eval_dialogue(file: dc.File) -> bool:
          client = Mistral(api_key = os.environ["MISTRAL_API_KEY"])
          response = client.chat.complete(
              model="open-mixtral-8x22b",
@@ -102,13 +102,13 @@ Python code:
          return result.lower().startswith("success")
 
     chain = (
-       DataChain.from_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
+       dc.from_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
        .settings(parallel=4, cache=True)
        .map(is_success=eval_dialogue)
        .save("mistral_files")
     )
 
-    successful_chain = chain.filter(Column("is_success") == True)
+    successful_chain = chain.filter(dc.Column("is_success") == True)
     successful_chain.to_storage("./output_mistral")
 
     print(f"{successful_chain.count()} files were exported")

{datachain-0.13.1 → datachain-0.14.0}/docs/examples.md

@@ -13,10 +13,10 @@ title: Examples
     For example, let us consider the New Yorker Cartoon caption contest dataset, where cartoons are matched against the potential titles. Let us imagine we want to augment this dataset with synthetic scene descriptions coming from an AI model. The below code takes images from the cloud, and applies PaliGemma model to caption the first five of them and put the results in the column “scene”:
 
     ```python
-    from datachain import Column, DataChain, File # (1)!
+    import datachain as dc # (1)!
     from transformers import AutoProcessor, PaliGemmaForConditionalGeneration # (2)!
 
-    images = DataChain.from_storage("gs://datachain-demo/newyorker_caption_contest/images", type="image")
+    images = dc.from_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")
@@ -80,7 +80,7 @@ In the below example, we are calling a Mixtral 8x22b model to judge the “servi
 # $ export MISTRAL_API_KEY='your key'
 
 import os
-from datachain import Column, DataChain, DataModel, Feature
+import datachain as dc
 from mistralai.client import MistralClient
 from mistralai.models.chat_completion import ChatMessage
 from mistralai.models.chat_completion import ChatCompletionResponse as MistralModel
@@ -89,12 +89,12 @@ prompt = "Was this dialog successful? Describe the 'result' as 'Yes' or 'No' in
 api_key = os.environ["MISTRAL_API_KEY"]
 
 ## register the data model ###
-DataModel.register(MistralModel)
+dc.DataModel.register(MistralModel)
 
 chain = (
-    DataChain
+    dc
     .from_storage("gs://datachain-demo/chatbot-KiT/", type="text")
-    .filter(Column("file.name").glob("*.txt"))
+    .filter(dc.Column("file.name").glob("*.txt"))
     .limit(5)
     .settings(parallel=4, cache=True)
     .map(
@@ -145,13 +145,13 @@ 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
-DataChain.from_dataset("rating").limit(2).save("dialog-rating")
+dc.from_dataset("rating").limit(2).save("dialog-rating")
 ```
 
 Persistent datasets are immutable and automatically versioned. Here is how to access the dataset registry:
 
 ```python
-mydatasets = DataChain.datasets()
+mydatasets = dc.datasets()
 for ds in mydatasets.collect("dataset"):
     print(f"{ds.name}@v{ds.version}")
 
@@ -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 = DataChain.from_dataset("dialog-rating", version = 1)
+ds = dc.from_dataset("dialog-rating", version = 1)
 ```
 
 ### Chain execution, optimization and parallelism
@@ -190,7 +190,7 @@ Here is an example of reading a simple CSV file where schema is heuristically de
 from datachain import DataChain
 
 uri="gs://datachain-demo/chatbot-csv/"
-csv_dataset = DataChain.from_csv(uri)
+csv_dataset = dc.from_csv(uri)
 
 print(csv_dataset.to_pandas())
 ```
@@ -231,15 +231,14 @@ Note how complicated the setup is. Every image is references by the name, and th
 However, Datachain can easily parse the entire COCO structure via several reading and merging operators:
 
 ```python
-
-from datachain import Column, DataChain
+import datachain as dc
 
 images_uri="gs://datachain-demo/coco2017/images/val/"
 captions_uri="gs://datachain-demo/coco2017/annotations/captions_val2017.json"
 
-images = DataChain.from_storage(images_uri)
-meta = DataChain.from_json(captions_uri, jmespath = "images")
-captions = DataChain.from_json(captions_uri, jmespath = "annotations")
+images = dc.from_storage(images_uri)
+meta = dc.from_json(captions_uri, jmespath = "images")
+captions = dc.from_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")
@@ -248,7 +247,7 @@ captioned_images = images_meta.merge(captions, on="images.id", right_on="annotat
 The resulting dataset has image entries as files decorated with all the metadata and captions:
 
 ```python
-images_with_dogs = captioned_images.filter(Column("annotations.caption").glob("*dog*"))
+images_with_dogs = captioned_images.filter(dc.Column("annotations.caption").glob("*dog*"))
 images_with_dogs.select("annotations", "file.name").show()
 ```
 

{datachain-0.13.1 → datachain-0.14.0}/docs/quick-start.md

@@ -37,16 +37,16 @@ Example of downloading only _`high-confidence cat`_ inferred images
 using JSON metadata:
 
 ``` py
-from datachain import Column, DataChain
+import datachain as dc
 
-meta = DataChain.from_json("gs://datachain-demo/dogs-and-cats/*json", object_name="meta", anon=True)
-images = DataChain.from_storage("gs://datachain-demo/dogs-and-cats/*jpg", anon=True)
+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)
 
 images_id = images.map(id=lambda file: file.path.split('.')[-2])
 annotated = images_id.merge(meta, on="id", right_on="meta.id")
 
-likely_cats = annotated.filter((Column("meta.inference.confidence") > 0.93) \
-                               & (Column("meta.inference.class_") == "cat"))
+likely_cats = annotated.filter((dc.Column("meta.inference.confidence") > 0.93) \
+                               & (dc.Column("meta.inference.class_") == "cat"))
 likely_cats.to_storage("high-confidence-cats/", signal="file")
 ```
 
@@ -67,7 +67,7 @@ sentiment detected are then copied to the local directory.
 
 ``` py
 from transformers import pipeline
-from datachain import DataChain, Column
+import datachain as dc
 
 classifier = pipeline("sentiment-analysis", device="cpu",
                 model="distilbert/distilbert-base-uncased-finetuned-sst-2-english")
@@ -77,7 +77,7 @@ def is_positive_dialogue_ending(file) -> bool:
     return classifier(dialogue_ending)[0]["label"] == "POSITIVE"
 
 chain = (
-   DataChain.from_storage("gs://datachain-demo/chatbot-KiT/",
+   dc.from_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)
@@ -118,11 +118,11 @@ to 4 requests at the same time.
 ``` py
 import os
 from mistralai import Mistral
-from datachain import File, DataChain, Column
+import datachain as dc
 
 PROMPT = "Was this dialog successful? Answer in a single word: Success or Failure."
 
-def eval_dialogue(file: File) -> bool:
+def eval_dialogue(file: dc.File) -> bool:
      client = Mistral(api_key = os.environ["MISTRAL_API_KEY"])
      response = client.chat.complete(
          model="open-mixtral-8x22b",
@@ -132,12 +132,12 @@ def eval_dialogue(file: File) -> bool:
      return result.lower().startswith("success")
 
 chain = (
-   DataChain.from_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
+   dc.from_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
    .map(is_success=eval_dialogue)
    .save("mistral_files")
 )
 
-successful_chain = chain.filter(Column("is_success") == True)
+successful_chain = chain.filter(dc.Column("is_success") == True)
 successful_chain.to_storage("./output_mistral")
 
 print(f"{successful_chain.count()} files were exported")
@@ -165,11 +165,11 @@ serialize the entire LLM response to the internal DB:
 ``` py
 from mistralai import Mistral
 from mistralai.models import ChatCompletionResponse
-from datachain import File, DataChain, Column
+import datachain as dc
 
 PROMPT = "Was this dialog successful? Answer in a single word: Success or Failure."
 
-def eval_dialog(file: File) -> ChatCompletionResponse:
+def eval_dialog(file: dc.File) -> ChatCompletionResponse:
      client = MistralClient()
      return client.chat(
          model="open-mixtral-8x22b",
@@ -177,7 +177,7 @@ def eval_dialog(file: File) -> ChatCompletionResponse:
                    {"role": "user", "content": file.read()}])
 
 chain = (
-   DataChain.from_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
+   dc.from_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])
@@ -186,7 +186,7 @@ chain = (
 
 chain.select("file.name", "status", "response.usage").show(5)
 
-success_rate = chain.filter(Column("status") == "success").count() / chain.count()
+success_rate = chain.filter(dc.Column("status") == "success").count() / chain.count()
 print(f"{100*success_rate:.1f}% dialogs were successful")
 ```
 
@@ -210,12 +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 `DataChain.from_dataset("dataset_name")`.
+can be accessed using `dc.from_dataset("dataset_name")`.
 
 Here is how to retrieve a saved dataset and iterate over the objects:
 
 ``` py
-chain = DataChain.from_dataset("response")
+import datachain as dc
+
+chain = dc.from_dataset("response")
 
 # Iterating one-by-one: support out-of-memory workflow
 for file, response in chain.limit(5).collect("file", "response"):
@@ -245,7 +247,8 @@ assuming the Mixtral call costs $2 per 1M input tokens and $6 per 1M
 output tokens:
 
 ``` py
-chain = DataChain.from_dataset("mistral_dataset")
+import datachain as dc
+chain = dc.from_dataset("mistral_dataset")
 
 cost = chain.sum("response.usage.prompt_tokens")*0.000002 \
            + chain.sum("response.usage.completion_tokens")*0.000006
@@ -268,12 +271,12 @@ file name suffix, the following code will do it:
 from torch.utils.data import DataLoader
 from transformers import CLIPProcessor
 
-from datachain import C, DataChain
+import datachain as dc
 
 processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
 
 chain = (
-    DataChain.from_storage("gs://datachain-demo/dogs-and-cats/", type="image", anon=True)
+    dc.from_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-0.13.1 → datachain-0.14.0}/docs/references/data-types/file.md

@@ -2,13 +2,13 @@
 
 `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 [`DataChain.from_storage`](../datachain.md#datachain.lib.dc.DataChain.from_storage):
+such as in [`dc.from_storage`](../datachain.md#datachain.lib.dc.storage.from_storage):
 
 ```python
-from datachain import DataChain
+import datachain as dc
 
-dc = DataChain.from_storage("gs://datachain-demo/dogs-and-cats")
-dc.print_schema()
+chain = dc.from_storage("gs://datachain-demo/dogs-and-cats")
+chain.print_schema()
 ```
 
 Output:

{datachain-0.13.1 → datachain-0.14.0}/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.DataChain.from_storage), using `type="image"` param:
+`ImageFile` is generated when a `DataChain` is created [from storage](../datachain.md#datachain.lib.dc.storage.from_storage), using `type="image"` param:
 
 ```python
-from datachain import DataChain
+import datachain as dc
 
-dc = DataChain.from_storage("s3://bucket-name/", type="image")
+chain = dc.from_storage("s3://bucket-name/", type="image")
 ```
 
 ::: datachain.lib.file.ImageFile

{datachain-0.13.1 → datachain-0.14.0}/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.DataChain.from_storage), using `type="text"` param:
+`TextFile` is generated when a `DataChain` is created [from storage](../datachain.md#datachain.lib.dc.storage.from_storage), using `type="text"` param:
 
 ```python
-from datachain import DataChain
+import datachain as dc
 
-dc = DataChain.from_storage("s3://bucket-name/", type="text")
+chain = dc.from_storage("s3://bucket-name/", type="text")
 ```
 
 ::: datachain.lib.file.TextFile

{datachain-0.13.1 → datachain-0.14.0}/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.DataChain.from_storage) with the `type="video"` parameter:
+`VideoFile` instances are created when a `DataChain` is initialized [from storage](../datachain.md#datachain.lib.dc.storage.from_storage) with the `type="video"` parameter:
 
 ```python
-from datachain import DataChain
+import datachain as dc
 
-dc = DataChain.from_storage("s3://bucket-name/", type="video")
+chain = dc.from_storage("s3://bucket-name/", type="video")
 ```
 
 There are additional models for working with video files:

{datachain-0.13.1 → datachain-0.14.0}/docs/references/datachain.md

@@ -9,6 +9,28 @@ for examples of how to create a chain.
 
 ::: datachain.query.schema.Column
 
+::: datachain.lib.dc.csv.from_csv
+
+::: datachain.lib.dc.datasets.from_dataset
+
+::: datachain.lib.dc.datasets.datasets
+
+::: datachain.lib.dc.hf.from_hf
+
+::: datachain.lib.dc.json.from_json
+
+::: datachain.lib.dc.listings.listings
+
+::: datachain.lib.dc.pandas.from_pandas
+
+::: datachain.lib.dc.parquet.from_parquet
+
+::: datachain.lib.dc.records.from_records
+
+::: datachain.lib.dc.storage.from_storage
+
+::: datachain.lib.dc.values.from_values
+
 ::: datachain.lib.dc.DataChain
 
 ::: datachain.lib.utils.DataChainError

{datachain-0.13.1 → datachain-0.14.0}/docs/references/remotes.md

@@ -1,13 +1,13 @@
 # Interacting with remote storage
 
-DataChain supports reading and writing data from different remote storages using methods like `DataChain.from_storage` and `DataChain.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.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.
 
 Example implementation for reading and writing data from/to different remote storages:
 
 ```python
-from datachain import DataChain
+import datachain as dc
 
-dc = DataChain.from_storage("s3://bucket-name/path/to/data")
+dc = dc.from_storage("s3://bucket-name/path/to/data")
 dc.to_storage("gs://bucket-name/path/to/data")
 ```
 
@@ -135,7 +135,7 @@ DataChain uses [s3fs](https://s3fs.readthedocs.io/en/latest/) to interact with A
 
 Example:
 ```python
-chain = DataChain.from_storage(
+chain = dc.from_storage(
     "s3://my-bucket/my-dir",
     client_config = {
 		"endpoint_url": "<minio-endpoint-url>",

{datachain-0.13.1 → datachain-0.14.0}/examples/computer_vision/iptc_exif_xmp_lib.py

@@ -13,7 +13,7 @@ from PIL import (
     TiffImagePlugin,
 )
 
-from datachain import C, DataChain
+import datachain as dc
 
 source = "gs://datachain-demo/open-images-v6/"
 
@@ -67,9 +67,9 @@ def image_description(file):
 
 if __name__ == "__main__":
     (
-        DataChain.from_storage(source, type="image")
+        dc.from_storage(source, type="image")
         .settings(parallel=-1)
-        .filter(C("file.path").glob("*.jpg"))
+        .filter(dc.C("file.path").glob("*.jpg"))
         .limit(5000)
         .map(
             image_description,
@@ -77,6 +77,6 @@ if __name__ == "__main__":
             output={"xmp": dict, "exif": dict, "iptc": dict, "error": str},
         )
         .select("file.path", "xmp", "exif", "iptc", "error")
-        .filter((C("xmp") != "{}") | (C("exif") != "{}") | (C("iptc") != "{}"))
+        .filter((dc.C("xmp") != "{}") | (dc.C("exif") != "{}") | (dc.C("iptc") != "{}"))
         .show()
     )

{datachain-0.13.1 → datachain-0.14.0}/examples/computer_vision/llava2_image_desc_lib.py

@@ -11,7 +11,7 @@ from transformers import (
     LlavaForConditionalGeneration,
 )
 
-from datachain import C, DataChain, Mapper
+import datachain as dc
 
 model = "llava-hf/llava-1.5-7b-hf"
 
@@ -41,7 +41,7 @@ def infer_dtype(device):
     return torch.float16
 
 
-class LLaVADescribe(Mapper):
+class LLaVADescribe(dc.Mapper):
     def __init__(self, device="cpu", model="llava-hf/llava-1.5-7b-hf", max_tokens=300):
         self.device = device
         self.model_name = model
@@ -71,8 +71,8 @@ class LLaVADescribe(Mapper):
 
 if __name__ == "__main__":
     (
-        DataChain.from_storage(source, type="image")
-        .filter(C("file.path").glob("*/cat*.jpg"))
+        dc.from_storage(source, type="image")
+        .filter(dc.C("file.path").glob("*/cat*.jpg"))
         .map(
             desc=LLaVADescribe(
                 device=device,

{datachain-0.13.1 → datachain-0.14.0}/examples/computer_vision/openimage-detect.py

@@ -2,7 +2,8 @@ import json
 
 from PIL import Image
 
-from datachain import C, DataChain, File, model
+import datachain as dc
+from datachain import File, model
 from datachain.func import path
 
 
@@ -40,8 +41,8 @@ def openimage_detect(args):
 source = "gs://datachain-demo/openimages-v6-test-jsonpairs/"
 
 (
-    DataChain.from_storage(source)
-    .filter(C("file.path").glob("*.jpg") | C("file.path").glob("*.json"))
+    dc.from_storage(source)
+    .filter(dc.C("file.path").glob("*.jpg") | dc.C("file.path").glob("*.json"))
     .agg(
         openimage_detect,
         partition_by=path.file_stem("file.path"),

{datachain-0.13.1 → datachain-0.14.0}/examples/computer_vision/ultralytics-bbox.py

@@ -1,17 +1,17 @@
 from ultralytics import YOLO
 
-from datachain import C, DataChain, File
+import datachain as dc
 from datachain.model.ultralytics import YoloBBoxes
 
 
-def process_bboxes(yolo: YOLO, file: File) -> YoloBBoxes:
+def process_bboxes(yolo: YOLO, file: dc.File) -> YoloBBoxes:
     results = yolo(file.as_image_file().read(), verbose=False)
     return YoloBBoxes.from_results(results)
 
 
 (
-    DataChain.from_storage("gs://datachain-demo/openimages-v6-test-jsonpairs/")
-    .filter(C("file.path").glob("*.jpg"))
+    dc.from_storage("gs://datachain-demo/openimages-v6-test-jsonpairs/")
+    .filter(dc.C("file.path").glob("*.jpg"))
     .limit(20)
     .setup(yolo=lambda: YOLO("yolo11n.pt"))
     .map(boxes=process_bboxes)

{datachain-0.13.1 → datachain-0.14.0}/examples/computer_vision/ultralytics-pose.py

@@ -1,17 +1,17 @@
 from ultralytics import YOLO
 
-from datachain import C, DataChain, File
+import datachain as dc
 from datachain.model.ultralytics import YoloPoses
 
 
-def process_poses(yolo: YOLO, file: File) -> YoloPoses:
+def process_poses(yolo: YOLO, file: dc.File) -> YoloPoses:
     results = yolo(file.as_image_file().read(), verbose=False)
     return YoloPoses.from_results(results)
 
 
 (
-    DataChain.from_storage("gs://datachain-demo/openimages-v6-test-jsonpairs/")
-    .filter(C("file.path").glob("*.jpg"))
+    dc.from_storage("gs://datachain-demo/openimages-v6-test-jsonpairs/")
+    .filter(dc.C("file.path").glob("*.jpg"))
     .limit(20)
     .setup(yolo=lambda: YOLO("yolo11n-pose.pt"))
     .map(poses=process_poses)

{datachain-0.13.1 → datachain-0.14.0}/examples/computer_vision/ultralytics-segment.py

@@ -1,17 +1,17 @@
 from ultralytics import YOLO
 
-from datachain import C, DataChain, File
+import datachain as dc
 from datachain.model.ultralytics import YoloSegments
 
 
-def process_segments(yolo: YOLO, file: File) -> YoloSegments:
+def process_segments(yolo: YOLO, file: dc.File) -> YoloSegments:
     results = yolo(file.as_image_file().read(), verbose=False)
     return YoloSegments.from_results(results)
 
 
 (
-    DataChain.from_storage("gs://datachain-demo/openimages-v6-test-jsonpairs/")
-    .filter(C("file.path").glob("*.jpg"))
+    dc.from_storage("gs://datachain-demo/openimages-v6-test-jsonpairs/")
+    .filter(dc.C("file.path").glob("*.jpg"))
     .limit(20)
     .setup(yolo=lambda: YOLO("yolo11n-seg.pt"))
     .map(segments=process_segments)