lose codeless version

defaults.py

@@ -3,7 +3,7 @@ import json
 
 SEED_DATA_PATH = "seed_data.json"
 PIPELINE_PATH = "pipeline.yaml"
-REMOTE_CODE_PATHS = ["defaults.py", "domain.py", "pipeline.py", "requirements.txt"]
+REMOTE_CODE_PATHS = ["requirements.txt"]
 DIBT_PARENT_APP_URL = "https://argilla-domain-specific-datasets-welcome.hf.space/"
 N_PERSPECTIVES = 5
 N_TOPICS = 5

hub.py

@@ -94,7 +94,7 @@ def push_pipeline_to_hub(
     # upload the pipeline to the hub
     hf_api.upload_file(
         path_or_fileobj=pipeline_path,
-        path_in_repo="pipeline.yaml",
+        path_in_repo="pipeline.py",
         token=hub_token,
         repo_id=repo_id,
         repo_type="dataset",
@@ -127,3 +127,25 @@ def push_argilla_dataset_to_hub(
     feedback_dataset = rg.FeedbackDataset.from_argilla(name=name, workspace=workspace)
     local_dataset = feedback_dataset.pull()
     local_dataset.push_to_huggingface(repo_id=repo_id)
+
+
+def push_pipeline_params(
+    pipeline_params,
+    hub_username,
+    hub_token: str,
+    project_name,
+):
+    repo_id = f"{hub_username}/{project_name}"
+    temp_path = mktemp()
+    with open(temp_path, "w") as f:
+        json.dump(pipeline_params, f)
+    # upload the pipeline to the hub
+    hf_api.upload_file(
+        path_or_fileobj=temp_path,
+        path_in_repo="pipeline_params.json",
+        token=hub_token,
+        repo_id=repo_id,
+        repo_type="dataset",
+    )
+
+    print(f"Pipeline params uploaded to {repo_id}")

pages/3_🌱 Generate Dataset.py

@@ -1,6 +1,7 @@
 import streamlit as st
 
 from defaults import ARGILLA_URL
+from hub import push_pipeline_params, push_pipeline_to_hub
 from utils import project_sidebar
 
 st.set_page_config(
@@ -90,6 +91,25 @@ if all(
         argilla_dataset_name,
     ]
 ):
+    push_pipeline_params(
+        pipeline_params={
+            "argilla_api_key": argilla_api_key,
+            "argilla_api_url": argilla_url,
+            "argilla_dataset_name": argilla_dataset_name,
+            "endpoint_base_url": base_url,
+        },
+        hub_username=hub_username,
+        hub_token=hub_token,
+        project_name=project_name,
+    )
+    
+    push_pipeline_to_hub(
+        pipeline_path="pipeline.py",
+        hub_username=hub_username,
+        hub_token=hub_token,
+        project_name=project_name,
+    )
+
     st.markdown(
         "To run the pipeline locally, you need to have the `distilabel` library installed. You can install it using the following command:"
     )
@@ -106,19 +126,18 @@ if all(
 
     st.code(
         f"""
-        # Clone the project and install the requirements
         git clone https://huggingface.co/datasets/{hub_username}/{project_name}
         cd {project_name}
         pip install -r requirements.txt
-        
-        # Run the pipeline
-        python pipeline.py 
-            --argilla-api-key {argilla_api_key} 
-            --argilla-api-url {argilla_url} 
-            --argilla-dataset-name {argilla_dataset_name} 
-            --endpoint-base-url {base_url}
-            --hub-token {st.session_state["hub_token"]}
-        """,
+        """
+    )
+
+    st.markdown("Finally, you can run the pipeline using the following command:")
+
+    st.code(
+        """
+        huggingface-cli login
+        python pipeline.py""",
         language="bash",
     )
     st.markdown(