datachain 0.19.2__tar.gz → 0.20.1__tar.gz

{datachain-0.19.2 → datachain-0.20.1}/.github/workflows/tests-studio.yml

@@ -98,6 +98,7 @@ 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-0.19.2 → datachain-0.20.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.19.2
+Version: 0.20.1
 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==1.16.0; extra == "dev"
+Requires-Dist: mypy==1.16.1; extra == "dev"
 Requires-Dist: types-python-dateutil; extra == "dev"
 Requires-Dist: types-pytz; extra == "dev"
 Requires-Dist: types-PyYAML; extra == "dev"

{datachain-0.19.2 → datachain-0.20.1}/docs/commands/job/run.md

@@ -24,7 +24,7 @@ This command runs a job in Studio using the specified query file. You can config
 * `--team TEAM` - Team to run job for (default: from config)
 * `--env-file ENV_FILE` - File with environment variables for the job
 * `--env ENV` - Environment variables in KEY=VALUE format
-* `--cluster-id CLUSTER_ID` - Compute cluster ID to run the job on
+* `--cluster CLUSTER` - Compute cluster to run the job on
 * `--workers WORKERS` - Number of workers for the job
 * `--files FILES` - Additional files to include in the job
 * `--python-version PYTHON_VERSION` - Python version for the job (e.g., 3.9, 3.10, 3.11)

datachain-0.20.1/docs/guide/env.md

@@ -0,0 +1,18 @@
+# Environment Variables
+
+List of environment variables used to configure DataChain behavior.
+
+### Core Configuration
+
+- `DATACHAIN_ROOT_DIR` – Specifies the root directory where DataChain will create the `.datachain` folder to store its internal data. (default: the current working directory).
+- `DATACHAIN_SYSTEM_CONFIG_DIR` – Overrides the system-wide configuration directory (default depends on the platform).
+- `DATACHAIN_GLOBAL_CONFIG_DIR` – Overrides the user's global configuration directory (default depends on the platform).
+- `DATACHAIN_NO_ANALYTICS` – Disables telemetry.
+
+### Studio Integration
+
+- `DATACHAIN_STUDIO_URL` – Custom Studio URL.
+- `DATACHAIN_STUDIO_TOKEN` – Authentication token for Studio.
+- `DATACHAIN_STUDIO_TEAM` – Studio team name.
+
+Note: Some environment variables are used internally and may not be documented here. For the most up-to-date list, refer to the source code.

{datachain-0.19.2 → datachain-0.20.1}/docs/guide/index.md

@@ -10,3 +10,4 @@ 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-0.19.2 → datachain-0.20.1}/mkdocs.yml

@@ -105,6 +105,7 @@ 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-0.19.2 → datachain-0.20.1}/pyproject.toml

@@ -108,7 +108,7 @@ tests = [
 ]
 dev = [
   "datachain[docs,tests]",
-  "mypy==1.16.0",
+  "mypy==1.16.1",
   "types-python-dateutil",
   "types-pytz",
   "types-PyYAML",

{datachain-0.19.2 → datachain-0.20.1}/src/datachain/__init__.py

@@ -1,3 +1,4 @@
+from datachain.lib import namespaces, projects
 from datachain.lib.data_model import DataModel, DataType, is_chain_type
 from datachain.lib.dc import (
     C,
@@ -67,7 +68,9 @@ __all__ = [
     "is_chain_type",
     "listings",
     "metrics",
+    "namespaces",
     "param",
+    "projects",
     "read_csv",
     "read_database",
     "read_dataset",