Add datachain job run --repository (#1074)

Author: 0x2b3bfa0

docs/commands/job/run.md

@@ -60,6 +60,11 @@ datachain job run --workers 4 --files utils.py config.json query.py
 datachain job run --env API_KEY=123 --req pandas numpy query.py
 ```
 
+6. Run a job with a repository (will be cloned in the job working directory):
+```bash
+datachain job run --repository https://github.com/iterative/datachain query.py
+```
+
 ## Notes
 
 * Closing the logs command (e.g., with Ctrl+C) will only stop displaying the logs but will not cancel the job execution

file

@@ -0,0 +1 @@
+date

src/datachain/cli/parser/job.py

@@ -13,7 +13,7 @@ def add_jobs_parser(subparsers, parent_parser) -> None:
     )
     jobs_subparser = jobs_parser.add_subparsers(
         dest="cmd",
-        help="Use `datachain auth CMD --help` to display command-specific help",
+        help="Use `datachain job CMD --help` to display command-specific help",
     )
 
     studio_run_help = "Run a job in Studio"
@@ -66,6 +66,11 @@ def add_jobs_parser(subparsers, parent_parser) -> None:
         action="store",
         help="Python version for the job (e.g., 3.9, 3.10, 3.11)",
     )
+    studio_run_parser.add_argument(
+        "--repository",
+        action="store",
+        help="Repository URL to clone before running the job",
+    )
     studio_run_parser.add_argument(
         "--req-file",
         action="store",

src/datachain/remote/studio.py

@@ -387,6 +387,7 @@ def create_job(
         files: Optional[list[str]] = None,
         python_version: Optional[str] = None,
         requirements: Optional[str] = None,
+        repository: Optional[str] = None,
     ) -> Response[JobData]:
         data = {
             "query": query,
@@ -397,6 +398,7 @@ def create_job(
             "files": files,
             "python_version": python_version,
             "requirements": requirements,
+            "repository": repository,
         }
         return self._send_request("datachain/job", data)
 

src/datachain/studio.py

@@ -35,6 +35,7 @@ def process_jobs_args(args: "Namespace"):
             args.workers,
             args.files,
             args.python_version,
+            args.repository,
             args.req,
             args.req_file,
         )
@@ -256,6 +257,7 @@ def create_job(
     workers: Optional[int] = None,
     files: Optional[list[str]] = None,
     python_version: Optional[str] = None,
+    repository: Optional[str] = None,
     req: Optional[list[str]] = None,
     req_file: Optional[str] = None,
 ):
@@ -284,6 +286,7 @@ def create_job(
         query_name=os.path.basename(query_file),
         files=file_ids,
         python_version=python_version,
+        repository=repository,
         requirements=requirements,
     )
     if not response.ok:

tests/test_cli_studio.py

@@ -381,6 +381,8 @@ def test_studio_run(capsys, mocker, tmp_dir):
                     "reqs.txt",
                     "--req",
                     "stupidity",
+                    "--repository",
+                    "https://github.com/iterative/datachain",
                 ]
             )
             == 0
@@ -417,4 +419,5 @@ def test_studio_run(capsys, mocker, tmp_dir):
         "python_version": "3.12",
         "requirements": "pyjokes\nstupidity",
         "team_name": "team_name",
+        "repository": "https://github.com/iterative/datachain",
     }