datachain 0.20.4__tar.gz → 0.21.1__tar.gz

{datachain-0.20.4 → datachain-0.21.1}/.github/workflows/tests-studio.yml

@@ -98,7 +98,6 @@ jobs:
       - name: Run tests
         # Generate `.test_durations` file with `pytest --store-durations --durations-path ../.github/.test_durations ...`
         run: >
-          DATACHAIN_METASTORE_ARG_PROJECT=john
           PYTHONPATH="$(pwd)/..:${PYTHONPATH}"
           pytest
           --config-file=pyproject.toml -rs

{datachain-0.20.4 → datachain-0.21.1}/.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
       - id: trailing-whitespace
         exclude: '^LICENSES/'
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.12.0'
+    rev: 'v0.11.13'
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]

{datachain-0.20.4 → datachain-0.21.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.20.4
+Version: 0.21.1
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0
@@ -94,7 +94,7 @@ Requires-Dist: scipy; extra == "tests"
 Requires-Dist: ultralytics; extra == "tests"
 Provides-Extra: dev
 Requires-Dist: datachain[docs,tests]; extra == "dev"
-Requires-Dist: mypy==1.16.1; extra == "dev"
+Requires-Dist: mypy==1.16.0; extra == "dev"
 Requires-Dist: types-python-dateutil; extra == "dev"
 Requires-Dist: types-pytz; extra == "dev"
 Requires-Dist: types-PyYAML; extra == "dev"

{datachain-0.20.4 → datachain-0.21.1}/docs/guide/index.md

@@ -10,4 +10,3 @@ Welcome to the DataChain User Guide! This section provides comprehensive documen
 - [Data Processing Overview](./processing.md) - Discover DataChain's specialized data processing features.
     - [Delta Processing](./delta.md) - Incremental data processing to efficiently handle large datasets that change over time.
     - [Error Handling and Retries](./retry.md) - Learn how to handle processing errors and selectively reprocess problematic records.
-- [Environment Variables](./env.md) - Configure DataChain's behavior using environment variables.

{datachain-0.20.4 → datachain-0.21.1}/examples/get_started/json-csv-reader.py

@@ -48,7 +48,7 @@ def main():
 
     # Print JSON schema in Pydantic format from main COCO annotation
     chain = dc.read_storage(uri, anon="True").filter(dc.C("file.path").glob("*.json"))
-    file = chain.limit(1).to_values("file")[0]
+    file = next(chain.limit(1).collect("file"))
     print(gen_datamodel_code(file, jmespath="@", model_name="Coco"))
 
     # Static JSON schema test parsing 3/7 objects

{datachain-0.20.4 → datachain-0.21.1}/examples/incremental_processing/delta.py

@@ -47,7 +47,7 @@ def process_files_with_delta():
     print("\nDataset versions:")
     test_dataset = dc.datasets().filter(C("name") == "test_files")
 
-    for version in test_dataset.to_iter("version"):
+    for version in test_dataset.collect("version"):
         print(f"- Version: {version}")
 
     # Show the last 3 records to demonstrate the incremental processing

{datachain-0.20.4 → datachain-0.21.1}/examples/llm_and_nlp/hf-dataset-llm-eval.py

@@ -1,5 +1,3 @@
-import os
-
 from huggingface_hub import InferenceClient
 from requests import HTTPError
 
@@ -25,7 +23,6 @@ def eval_dialog(
 ) -> DialogEval:
     try:
         completion = client.chat_completion(
-            model="meta-llama/Llama-3.3-70B-Instruct",
             messages=[
                 {
                     "role": "user",
@@ -34,10 +31,9 @@ def eval_dialog(
             ],
             response_format={"type": "json", "value": DialogEval.model_json_schema()},
         )
-    except HTTPError as e:
+    except HTTPError:
         return DialogEval(
-            result="Error",
-            reason=f"Error while interacting with the Hugging Face API. {e}",
+            result="Error", reason="Error while interacting with the Hugging Face API."
         )
 
     message = completion.choices[0].message
@@ -52,15 +48,9 @@ def eval_dialog(
 # Save to HF as Parquet. Dataset can be previewed here:
 # https://huggingface.co/datasets/dvcorg/test-datachain-llm-eval/viewer
 (
-    dc.read_csv(
-        "hf://datasets/infinite-dataset-hub/MobilePlanAssistant/data.csv", source=False
-    )
-    .settings(parallel=True)
-    .setup(
-        client=lambda: InferenceClient(
-            provider="hf-inference", api_key=os.environ["HF_TOKEN"]
-        )
-    )
+    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)
     .to_parquet("hf://datasets/dvcorg/test-datachain-llm-eval/data.parquet")
 )

{datachain-0.20.4 → datachain-0.21.1}/mkdocs.yml

@@ -105,7 +105,6 @@ nav:
               - Overview: guide/processing.md
               - Delta Processing: guide/delta.md
               - Errors Handling and Retries: guide/retry.md
-          - Environment Variables: guide/env.md
       - 🤝 Contributing: contributing.md
 
   - DataChain Website ↗: https://datachain.ai" target="_blank"

{datachain-0.20.4 → datachain-0.21.1}/pyproject.toml

@@ -108,7 +108,7 @@ tests = [
 ]
 dev = [
   "datachain[docs,tests]",
-  "mypy==1.16.1",
+  "mypy==1.16.0",
   "types-python-dateutil",
   "types-pytz",
   "types-PyYAML",
@@ -221,8 +221,7 @@ ignore = [
   "PERF203",  # perflint - try-except-in-loop, irrelevant for Python>=3.11
   "PERF401",
   "D100",  # undocumented-public-module
-  "D205",  # one-blank-line-after-class
-  "PLC0415"  # import-outside-top-level
+  "D205"  # one-blank-line-after-class
 ]
 select = [
   "B",  # flake8-bugbear

{datachain-0.20.4 → datachain-0.21.1}/src/datachain/__init__.py

@@ -32,7 +32,6 @@ from datachain.lib.file import (
     VideoFrame,
 )
 from datachain.lib.model_store import ModelStore
-from datachain.lib.projects import create as create_project
 from datachain.lib.udf import Aggregator, Generator, Mapper
 from datachain.lib.utils import AbstractUDF, DataChainError
 from datachain.query import metrics, param
@@ -63,7 +62,6 @@ __all__ = [
     "VideoFile",
     "VideoFragment",
     "VideoFrame",
-    "create_project",
     "datasets",
     "delete_dataset",
     "is_chain_type",

{datachain-0.20.4 → datachain-0.21.1}/src/datachain/cache.py

@@ -39,7 +39,7 @@ def temporary_cache(
             cache.destroy()
 
 
-class Cache:  # noqa: PLW1641
+class Cache:
     def __init__(self, cache_dir: str, tmp_dir: str):
         self.odb = LocalHashFileDB(
             LocalFileSystem(),
@@ -76,9 +76,9 @@ class Cache:  # noqa: PLW1641
     async def download(
         self, file: "File", client: "Client", callback: Optional[Callback] = None
     ) -> None:
+        from_path = f"{file.source}/{file.path}"
         from dvc_objects.fs.utils import tmp_fname
 
-        from_path = file.get_uri()
         odb_fs = self.odb.fs
         tmp_info = odb_fs.join(self.odb.tmp_dir, tmp_fname())  # type: ignore[arg-type]
         size = file.size