From 5a28d2a1ede2f1dd492aa4793d2d35e069104ddb Mon Sep 17 00:00:00 2001
From: Robin <auc2yz7ab@mozmail.com>
Date: Thu, 6 Mar 2025 08:47:14 +0100
Subject: [PATCH] docs: Update Polars Cloud interactive workflow examples
 (#21609)

---
 .../polars-cloud/run/interactive-batch.md     | 32 +++++++++----------
 docs/source/polars-cloud/run/workflow.md      | 24 ++++++--------
 .../python/polars-cloud/interactive-batch.py  |  5 ++-
 3 files changed, 27 insertions(+), 34 deletions(-)

diff --git a/docs/source/polars-cloud/run/interactive-batch.md b/docs/source/polars-cloud/run/interactive-batch.md
index bc22c5126a0e..f65045257a02 100644
--- a/docs/source/polars-cloud/run/interactive-batch.md
+++ b/docs/source/polars-cloud/run/interactive-batch.md
@@ -50,21 +50,25 @@ The initial query remains the same. In the compute context the parameter `intera
 to `True`.
 
 When calling `.collect()` on your remote query execution, the output is written to a temporary
-location. These intermediate result files are automatically deleted after several hours. You can see
-the location of this folder when printing the query results.
+location. These intermediate result files are automatically deleted after several hours. The output
+of the remote query is a LazyFrame.
 
-Users can call `.lazy()` on the result and continue working with the previous result.
+```python
+print(type(res1))
+```
+
+```
+<class 'polars.lazyframe.frame.LazyFrame'>
+```
+
+If you want to inspect the results you can call collect again.
 
 ```python
-print(res1)
+print(res1.collect())
 ```
 
 ```text
-total_stages: 1
-finished_stages: 1
-total_rows: 4
-location: ['s3://polars-cloud-<workspace_id>/query_outputs/<query_id>/<random id>.parquet']
-head:
+shape: (4, 3)
 ┌────────────────┬────────────┬───────────┐
 │ name           ┆ birth_year ┆ bmi       │
 │ ---            ┆ ---        ┆ ---       │
@@ -77,20 +81,16 @@ head:
 └────────────────┴────────────┴───────────┘
 ```
 
-To continue your query we can read the result to a new LazyFrame and continue your exploration.
+To continue your exploration you can use the returned LazyFrame to build another query.
 
 {{code_block('polars-cloud/interactive-batch','interactive-next',[])}}
 
 ```python
-print(res2)
+print(res2.collect())
 ```
 
 ```text
-total_stages: 1
-finished_stages: 1
-total_rows: 2
-location: ['s3://polars-cloud-<workspace_id>/query_outputs/<query_id>/<random id>.parquet']
-head:
+shape: (2, 3)
 ┌──────────────┬────────────┬───────────┐
 │ name         ┆ birth_year ┆ bmi       │
 │ ---          ┆ ---        ┆ ---       │
diff --git a/docs/source/polars-cloud/run/workflow.md b/docs/source/polars-cloud/run/workflow.md
index d767fa78ee2d..cdb77ef9e6c7 100644
--- a/docs/source/polars-cloud/run/workflow.md
+++ b/docs/source/polars-cloud/run/workflow.md
@@ -18,7 +18,7 @@ demonstrate the workflow. Here we will create the LazyFrame ourselves, but it co
 ```python
 import polars as pl
 
-lf = pl.DataFrame(
+lf = pl.LazyFrame(
     {
         "region": [
             "Australia",
@@ -102,8 +102,7 @@ import polars_cloud as pc
 ctx = pc.ComputeContext(
     workspace="environmental-analysis",
     memory=32,
-    cpus=8,
-    cluster_size=4
+    cpus=8
 )
 
 query.remote(ctx).sink_parquet("s3://bucket/result.parquet")
@@ -119,21 +118,16 @@ ctx = pc.ComputeContext(
     workspace="environmental-analysis",
     memory=32,
     cpus=8,
-    cluster_size=4,
     interactive=True,  # set interactive to True
 )
 
-result = query.remote(ctx).collect().await_result()
+result = query.remote(ctx).collect()
 
-print(result)
+print(result.collect())
 ```
 
 ```text
-total_stages: 1
-finished_stages: 1
-total_rows: 4
-location: ['s3://polars-cloud-xxx-xxx-xxx-xxx-eddc267994b8/query_outputs/22079a94-6424-4dc1-b1d7-3ea0dc4cafcc/7e966528-4238-4b34-aa52-6242be285723.parquet']
-head:
+shape: (4, 6)
 ┌───────────────┬─────────────┬──────────┬───────────┬────────────────────┬───────────┐
 │ region        ┆ temperature ┆ humidity ┆ burn_area ┆ vegetation_density ┆ fire_risk │
 │ ---           ┆ ---         ┆ ---      ┆ ---       ┆ ---                ┆ ---       │
@@ -147,15 +141,15 @@ head:
 ```
 
 We can call `.collect()` instead of `.sink_parquet()`. This will store your results to a temporary
-location which can be used to further iterate upon. To continue on the result from `collect` simply
-call `lazy` and you can get back a `LazyFrame` for further analysis.
+location which can be used to further iterate upon. A LazyFrame is returned that can be used in the
+next steps of the workflow.
 
 ```python
 res2 = (
-    result.lazy()
+    result
     .filter(pl.col("fire_risk") > 1)
     .sink_parquet("s3://bucket/output-interactive.parquet")
 )
 ```
 
-Finally, the results of your interactive workflow can be written to S3.
+The result of your interactive workflow can be written to S3.
diff --git a/docs/source/src/python/polars-cloud/interactive-batch.py b/docs/source/src/python/polars-cloud/interactive-batch.py
index 90d66e372695..c56770be12c8 100644
--- a/docs/source/src/python/polars-cloud/interactive-batch.py
+++ b/docs/source/src/python/polars-cloud/interactive-batch.py
@@ -42,19 +42,18 @@
     (pl.col("weight") / (pl.col("height") ** 2)).alias("bmi"),
 ).sort(by="bmi")
 
-res1 = lf.remote(ctx).collect().await_result()
+res1 = lf.remote(ctx).collect()
 
 # --8<-- [end:interactive]
 
 # --8<-- [start:interactive-next]
 res2 = (
-    res1.lazy()
+    res1
     .filter(
         pl.col("birth_year").is_in([1983, 1985]),
     )
     .remote(ctx)
     .collect()
-    .await_result()
 )
 # --8<-- [end:interactive-next]
 """