Update an Experiment Run

Modify the experiment data, such as name, tags, datasets, and the pipeline used. You can only edit an experiment when its status is draft, you can't edit completed experiments.

📘

You must be an Admin to perform this task.

Update an Experiment Run from the UI

🚧

Coming soon!

In the meantime, you can use SDK or REST API.

  1. Log in to deepset Cloud and go to Experiments.
  2. Find the experiment that you want to update, click the menu to the right of the experiment name, and select Edit.
  3. Modify the experiment run and save your changes.

Update an Experiment Run with a Python SDK

Here's the code you can use. You can also run it in Jupyter Notebooks within deepset Cloud. You need to Generate an API Key first.

import os
from haystack.utils import DeepsetCloudExperiments


# Set the API key and API endpoint:
os.environ["DEEPSET_CLOUD_API_KEY"] = "<your API key>"
os.environ["DEEPSET_CLOUD_API_ENDPOINT"] = "https://api.cloud.deepset.ai/api/v1"

# Update the experiment run. Eval_run_name indicates the evaluation run you want to update,
# and workspace is the workspace this evaluation run is in. 
# The other parameters are the ones you want to modify.
updated_run = DeepsetCloudExperiments.update_run(
  workspace="<your_workspace>", 
  eval_run_name="Experiment1", 
  pipeline_config_name="new_pipeline")


Update an Experiment Run with REST API

Use the Edit Eval Run API endpoint to update the name, tags, pipeline, files, and evaluation set of an experiment run. You need to Generate an API Key first.

curl --request PATCH \
     --url https://api.cloud.deepset.ai/api/v1/workspaces/<YOUR_WORKSPACE>/eval_runs/<EVALUATION_RUN> \
     --header 'Accept: application/json' \
     --header 'Authorization: Bearer <YOUR_API_KEY>' \
     --header 'Content-Type: application/json' \
     --data '
{
     "tags": [
          "tag1"
     ],
     "comment": "Add a comment here",
     "evaluation_set_name": "<your_eval_set>",
     "pipeline_name": "<pipeline_name>"
}
'

Related Links