Skip to content

Commit 25485f6

Browse files
authored
Image/table enrichments work only with High Res partitioning (#639)
1 parent 07cb48b commit 25485f6

12 files changed

+81
-6
lines changed

api-reference/workflow/workflows.mdx

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -977,6 +977,8 @@ In the request body, specify the settings for the workflow. For the specific set
977977

978978
## Custom workflow DAG nodes
979979

980+
import EnrichmentImagesTablesHiResOnly from '/snippets/general-shared-text/enrichment-images-tables-hi-res-only.mdx';
981+
980982
If `WorkflowType` is set to `CUSTOM` (for the Python SDK), or if `workflow_type` is set to `custom` (for `curl` or Postman), you must also specify the settings for the workflow's
981983
directed acyclic graph (DAG) nodes. These nodes' settings are specified in the `workflow_nodes` array.
982984

@@ -986,6 +988,9 @@ directed acyclic graph (DAG) nodes. These nodes' settings are specified in the `
986988
`workflow_nodes` array.
987989
- You can specify [Partitioner](#partitioner-node), [Chunker](#chunker-node),
988990
[Enrichment](#enrichment-node), and [Embedder](#embedder-node) nodes.
991+
992+
<EnrichmentImagesTablesHiResOnly />
993+
989994
- The order of the nodes in the `workflow_nodes` array will be the same order that these nodes appear in the DAG,
990995
with the first node in the array added directly after the **Source** node. The **Destination** node
991996
follows the last node in the array.
@@ -1421,8 +1426,14 @@ An **Enrichment** node has a `type` of `prompter`.
14211426

14221427
[Learn about the available enrichments](/ui/enriching/overview).
14231428

1429+
<EnrichmentImagesTablesHiResOnly />
1430+
14241431
#### Image Description task
14251432

1433+
import EnrichmentImageSummaryHiResOnly from '/snippets/general-shared-text/enrichment-image-summary-hi-res-only.mdx';
1434+
1435+
<EnrichmentImageSummaryHiResOnly />
1436+
14261437
<AccordionGroup>
14271438
<Accordion title="Python SDK">
14281439
```python
@@ -1455,6 +1466,10 @@ Allowed values for `<subtype>` include:
14551466

14561467
#### Table Description task
14571468

1469+
import EnrichmentTableSummaryHiResOnly from '/snippets/general-shared-text/enrichment-table-summary-hi-res-only.mdx';
1470+
1471+
<EnrichmentTableSummaryHiResOnly />
1472+
14581473
<AccordionGroup>
14591474
<Accordion title="Python SDK">
14601475
```python
@@ -1487,6 +1502,10 @@ Allowed values for `<subtype>` include:
14871502

14881503
#### Table to HTML task
14891504

1505+
import EnrichmentTableToHTMLHiResOnly from '/snippets/general-shared-text/enrichment-table-to-html-hi-res-only.mdx';
1506+
1507+
<EnrichmentTableToHTMLHiResOnly />
1508+
14901509
<AccordionGroup>
14911510
<Accordion title="Python SDK">
14921511
```python
Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,7 @@
1+
<Warning>
2+
Image summary descriptions are generated only when the **Partitioner** node in a workflow is set to use the **High Res** [partitioning strategy](/ui/partitioning) and
3+
the workflow also contains an image description enrichment node.
4+
5+
Setting the **Partitioner** node to use **Auto**, **VLM**, or **Fast** in a workflow that also contains an image description enrichment node
6+
will not produce any image summary descriptions, and it could also cause the workflow to stop running or produce unexpected results.
7+
</Warning>
Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,7 @@
1+
<Warning>
2+
Image summary descriptions, table summary descriptions, and table-to-HTML output is generated only when the **Partitioner** node in a workflow is set to use the **High Res** [partitioning strategy](/ui/partitioning) and
3+
the workflow also contains an image description, table description, or table-to-HTML enrichment node.
4+
5+
Setting the **Partitioner** node to use **Auto**, **VLM**, or **Fast** in a workflow that also contains an image description, table description, or table-to-HTML enrichment node
6+
will not generate any image summary descriptions, table summary descriptions, or table-to-HTML output, and it could also cause the workflow to stop running or produce unexpected results.
7+
</Warning>
Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,7 @@
1+
<Warning>
2+
Table summary descriptions are generated only when the **Partitioner** node in a workflow is set to use the **High Res** [partitioning strategy](/ui/partitioning) and
3+
the workflow also contains a table description enrichment node.
4+
5+
Setting the **Partitioner** node to use **Auto**, **VLM**, or **Fast** in a workflow that also contains a table description enrichment node
6+
will not produce any table summary descriptions, and it could also cause the workflow to stop running or produce unexpected results.
7+
</Warning>
Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,7 @@
1+
<Warning>
2+
Table-to-HTML generation happens only when the **Partitioner** node in a workflow is set to use the **High Res** [partitioning strategy](/ui/partitioning) and
3+
the workflow also contains a table-to-HTML enrichment node.
4+
5+
Setting the **Partitioner** node to use **Auto**, **VLM**, or **Fast** in a workflow that also contains a table-to-HTML enrichment node
6+
will not generate any table-to-HTML output, and it could also cause the workflow to stop running or produce unexpected results.
7+
</Warning>

snippets/quickstarts/single-file-ui.mdx

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -59,6 +59,7 @@ allowfullscreen
5959
></iframe>
6060

6161
import GetStartedSimpleUIOnly from '/snippets/general-shared-text/get-started-simple-ui-only.mdx';
62+
import EnrichmentImagesTablesHiResOnly from '/snippets/general-shared-text/enrichment-images-tables-hi-res-only.mdx';
6263

6364
<Steps>
6465
<Step title="Sign up and sign in">
@@ -137,6 +138,9 @@ import GetStartedSimpleUIOnly from '/snippets/general-shared-text/get-started-si
137138
- Add an **Enrichment** node after the **Chunker** node, to apply enrichments to the chunked data such as image summaries, table summaries, table-to-HTML transforms, and
138139
named entity recognition (NER). To do this, click the add (**+**) button to the right of the **Chunker** node, and then click **Enrich > Enrichment**.
139140
Click the new **Enrichment** node and specify its settings. For help, click the **FAQ** button in the **Enrichment** node's pane. [Learn more about enrichments and enrichment settings](/ui/enriching/overview).
141+
142+
<EnrichmentImagesTablesHiResOnly />
143+
140144
- Add an **Embedder** node after the **Enrichment** node, to generate vector embeddings for performing vector-based searches. To do this, click the add (**+**) button to the
141145
right of the **Enrichment** node, and then click **Transform > Embedder**. Click the new **Embedder** node and specify its settings. For help, click the **FAQ** button
142146
in the **Embedder** node's pane. [Learn more about embedding and embedding settings](/ui/embedding).

ui/enriching/image-descriptions.mdx

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -43,14 +43,17 @@ Any embeddings that are produced after these summaries are generated will be bas
4343

4444
## Generate image descriptions
4545

46+
import EnrichmentImageSummaryHiResOnly from '/snippets/general-shared-text/enrichment-image-summary-hi-res-only.mdx';
47+
4648
To generate image descriptions, in an **Enrichment** node in a workflow, specify the following:
4749

4850
<Note>
4951
You can change a workflow's image description settings only through [Custom](/ui/workflows#create-a-custom-workflow) workflow settings.
5052

51-
Image summaries are generated only when the **Partitioner** node in a workflow is also set to use the **High Res** partitioning strategy. [Learn more](/ui/partitioning).
5253
</Note>
5354

55+
<EnrichmentImageSummaryHiResOnly />
56+
5457
Select **Image**, and then choose one of the following provider (and model) combinations to use:
5558

5659
- **OpenAI (GPT-4o)**. [Learn more](https://openai.com/index/hello-gpt-4o/).

ui/enriching/overview.mdx

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,8 @@
22
title: Overview
33
---
44

5+
import EnrichmentImagesTablesHiResOnly from '/snippets/general-shared-text/enrichment-images-tables-hi-res-only.mdx';
6+
57
_Enriching_ adds enhancments to the processed data that Unstructured produces. These enrichments include:
68

79
- Providing a summarized description of the contents of a detected image. [Learn more](/ui/enriching/image-descriptions).
@@ -13,10 +15,10 @@ To add an enrichment, in an **Enrichment** node in a workflow, select one of the
1315

1416
<Note>
1517
You can change enrichment settings only through [Custom](/ui/workflows#create-a-custom-workflow) workflow settings.
16-
17-
Enrichments work only when the **Partitioner** node in a workflow is also set to use the **High Res** partitioning strategy. [Learn more](/ui/partitioning).
1818
</Note>
1919

20+
<EnrichmentImagesTablesHiResOnly />
21+
2022
- **Image** to provide a summarized description of the contents of each detected image. [Learn more](/ui/enriching/image-descriptions).
2123
- **Table** to provide a summarized description of the contents of each detected table. [Learn more](/ui/enriching/table-descriptions).
2224
- **Table** can also provide a representation of each detected table in HTML markup format. [Learn more](/ui/enriching/table-to-html).

ui/enriching/table-descriptions.mdx

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -50,14 +50,17 @@ Any embeddings that are produced after these summaries are generated will be bas
5050

5151
## Generate table descriptions
5252

53+
import EnrichmentTableSummaryHiResOnly from '/snippets/general-shared-text/enrichment-table-summary-hi-res-only.mdx';
54+
5355
To generate table descriptions, in an **Enrichment** node in a workflow, specify the following:
5456

5557
<Note>
5658
You can change a workflow's table description settings only through [Custom](/ui/workflows#create-a-custom-workflow) workflow settings.
5759

58-
Table summaries are generated only when the **Partitioner** node in a workflow is also set to use the **High Res** partitioning strategy. [Learn more](/ui/partitioning).
5960
</Note>
6061

62+
<EnrichmentTableSummaryHiResOnly />
63+
6164
Select **Table**, and then choose one of the following provider (and model) combinations to use:
6265

6366
- **OpenAI (GPT-4o)**. [Learn more](https://openai.com/index/hello-gpt-4o/).

ui/enriching/table-to-html.mdx

Lines changed: 5 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -62,12 +62,15 @@ Line breaks have been inserted here for readability. The output will not contain
6262

6363
## Generate table-to-HTML output
6464

65+
import EnrichmentTableToHTMLHiResOnly from '/snippets/general-shared-text/enrichment-table-to-html-hi-res-only.mdx';
66+
6567
To generate table-to-HTML output, in an **Enrichment** node in a workflow, for **Model**, select **OpenAI (GPT-4o)**.
6668

6769
Make sure after you choose this provider and model, that **Table to HTML** is also selected.
6870

6971
<Note>
7072
You can change a workflow's table description settings only through [Custom](/ui/workflows#create-a-custom-workflow) workflow settings.
7173

72-
Table-to-HTML output is generated only when the **Partitioner** node in a workflow is set to use the **High Res** partitioning strategy. [Learn more](/ui/partitioning).
73-
</Note>
74+
</Note>
75+
76+
<EnrichmentTableToHTMLHiResOnly />

0 commit comments

Comments
 (0)