From 7f87c3267be036523a9970a95becbe971d2bd872 Mon Sep 17 00:00:00 2001
From: Owen Bodley <owen.bodley@benchling.com>
Date: Sat, 26 Jul 2025 20:37:43 +0200
Subject: [PATCH] feat: add 2 new examples which show 2 ways to fetch the
 number of correct sequences in documents

---
 examples/fetch_status_chart.py                | 20 ++++++++
 examples/run_extract_job.py                   |  2 +-
 .../run_report_job_to_summarize_documents.py  | 46 +++++++++++++++++++
 3 files changed, 67 insertions(+), 1 deletion(-)
 create mode 100644 examples/fetch_status_chart.py
 create mode 100644 examples/run_report_job_to_summarize_documents.py

diff --git a/examples/fetch_status_chart.py b/examples/fetch_status_chart.py
new file mode 100644
index 0000000..047fed0
--- /dev/null
+++ b/examples/fetch_status_chart.py
@@ -0,0 +1,20 @@
+from pipebio.pipebio_client import PipebioClient
+
+client = PipebioClient(url='https://app.pipebio.com')
+
+# Set document id to get the status chart for.
+# NOTE: This document must be annotated or you will not get a good result back.
+document_id = 'ent_TozXnaXkMVhEjFm9'
+
+result = client.session.get(f'sequences/charts/StatusPieChart?documentId={document_id}')
+
+data = result.json()
+
+# Below are some examples of how to interact with the data returned from the StatusPieChart endpoint.
+correct_count = data['status']['CORRECT']
+assert correct_count == 131
+
+incorrect_count = data['status']['INCORRECT']
+assert incorrect_count == 6
+
+assert data['total'] == correct_count + incorrect_count
\ No newline at end of file
diff --git a/examples/run_extract_job.py b/examples/run_extract_job.py
index 78e448d..918185e 100644
--- a/examples/run_extract_job.py
+++ b/examples/run_extract_job.py
@@ -20,7 +20,7 @@
 # Run an extract job and put the results in the new_folder we just created.
 job_id = client.jobs.create(
     shareable_id=shareable_id,
-    name='Extract job from API',
+    name='Extract job from SDK',
     job_type=JobType.ExtractJob,
     # Either hard code input entity ids or get these from the output_entity_ids from a previous job.
     input_entity_ids=[document_id],
diff --git a/examples/run_report_job_to_summarize_documents.py b/examples/run_report_job_to_summarize_documents.py
new file mode 100644
index 0000000..1c11ad0
--- /dev/null
+++ b/examples/run_report_job_to_summarize_documents.py
@@ -0,0 +1,46 @@
+import os
+from pipebio.pipebio_client import PipebioClient
+from pipebio.models.job_type import JobType
+
+client = PipebioClient(url='https://app.pipebio.com')
+shareable_id = os.environ['TARGET_SHAREABLE_ID']
+folder_id = os.environ['TARGET_FOLDER_ID']
+
+document_id = 'ent_PbyAluxijmJfNXph'
+
+# Summarise 1 or more documents using a summary job.
+job_id = client.jobs.create(
+    shareable_id=shareable_id,
+    name='Summary job from SDK',
+    job_type=JobType.SummaryJob,
+    # Include 1 or more document ids here to summarize in one go.
+    input_entity_ids=[document_id],
+    params={
+        "targetFolderId": folder_id
+    },
+    poll_jobs=True
+)
+
+# Fetch the job.
+job = client.jobs.get(job_id)
+
+# Get the id of the report that was created.
+output_id = next(e['id'] for e in job['outputEntities'])
+
+# Fetch the summary report we just created.
+response = client.session.get(f'entities/{output_id}/attachments/Report')
+result = response.json()
+annotation_summary = next(item for item in result['data']['items'] if item['title'].startswith('Analysis results for'))
+
+# Print the results.
+# e.g:
+#   Id: SRR11974622
+#   Total reads: 1059733
+#   Correct annotated: 320376
+#   Correct annotated percent: 30.2317659259455
+for row in annotation_summary['data']['rows']:
+    for col in annotation_summary['data']['columns']:
+        header = col['headerName']
+        field = col['field']
+        value = row[field]
+        print(f'{header}: {value}')