Skip to content

Commit a652670

Browse files
authored
UI: Enrichment nodes - new UI experience (#559)
1 parent edf7bb4 commit a652670

File tree

6 files changed

+41
-23
lines changed

6 files changed

+41
-23
lines changed

ui/enriching/image-descriptions.mdx

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -44,15 +44,15 @@ Any embeddings that are produced after these summaries are generated will be bas
4444

4545
## Generate image descriptions
4646

47-
To generate image descriptions, in the **Task** drop-down list of an **Enrichment** node in a workflow, specify the following:
47+
To generate image descriptions, in an **Enrichment** node in a workflow, specify the following:
4848

4949
<Note>
5050
You can change a workflow's image description settings only through [Custom](/ui/workflows#create-a-custom-workflow) workflow settings.
5151

5252
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).
5353
</Note>
5454

55-
Select **Image Description**, and then choose one of the following provider (and model) combinations to use:
55+
Select **Image**, and then choose one of the following provider (and model) combinations to use:
5656

5757
- **OpenAI (GPT-4o)**. [Learn more](https://openai.com/index/hello-gpt-4o/).
5858
- **Anthropic (Claude 3.5 Sonnet)**. [Learn more](https://www.anthropic.com/news/claude-3-5-sonnet).

ui/enriching/ner.mdx

Lines changed: 8 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -87,21 +87,21 @@ Here is an example of a list of recognized entities and their types using GPT-4o
8787

8888
# Generate a list of entities and their types
8989

90-
To generate a list of recognized entities and their types, in the **Task** drop-down list of an **Enrichment** node in a workflow, specify the following:
90+
To generate a list of recognized entities and their types, in an **Enrichment** node in a workflow, specify the following:
9191

9292
<Note>
9393
You can change a workflow's NER settings only through [Custom](/ui/workflows#create-a-custom-workflow) workflow settings.
9494

9595
Entities are only recognized when the **Partitioner** node in a workflow is also set to use the **High Res** partitioning strategy. [Learn more](/ui/partitioning).
9696
</Note>
9797

98-
1. Select **Named Entity Recognition (NER)**. By default, OpenAI's GPT-4o will follow a default set of instructions (called a _prompt_) to perform NER using a set of predefined entity types.
99-
2. To use Anthropic's Claude 3.5 Sonnet to perform NER instead, or to customize the prompt, click **Edit**.
100-
3. To switch to using Anthropic's Claude 3.5 Sonnet, click **Anthropic (Claude 3.5 Sonnet)**.
101-
4. To experiment with running the default prompt against some sample data, click **Run Prompt**. The selected **Model** uses the
98+
1. Select **Text**.
99+
2. For **Model**, select either **OpenAI (GPT-4o)** or **Anthropic (Claude 3.5 Sonnet)**.
100+
3. The selected model will follow a default set of instructions (called a _prompt_) to perform NER using a set of predefined entity types. To experiment
101+
with running the default prompt against some sample data, click **Edit**, and then click **Run Prompt**. The selected **Model** uses the
102102
**Prompt** to run NER on the **Input sample** and shows the results in the **Output**. Look specifically at the `response_json` field for the
103103
entities that were recognized and their types.
104-
5. To customize the prompt, change the contents of **Prompt**.
104+
4. To customize the prompt, change the contents of **Prompt**.
105105

106106
<Note>
107107
For best results, Unstructured strongly recommends that you limit your changes only to certain portions of the default prompt, specifically:
@@ -122,6 +122,6 @@ To generate a list of recognized entities and their types, in the **Task** drop-
122122
- Changing any other portions of the default prompt could produce unexpected results.
123123
</Note>
124124

125-
6. To experiment with different data, change the contents of **Input sample**. For best results, Unstructured strongly recommends that the JSON structure in **Input sample** be preserved.
126-
7. When you are satisfied with the **Model** and **Prompt** that you want to use, click **Save**.
125+
5. To experiment with different data, change the contents of **Input sample**. For best results, Unstructured strongly recommends that the JSON structure in **Input sample** be preserved.
126+
6. When you are satisfied with the **Model** and **Prompt** that you want to use, click **Save**.
127127

ui/enriching/overview.mdx

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -9,17 +9,17 @@ _Enriching_ adds enhancments to the processed data that Unstructured produces. T
99
- Providing a representation of a detected table in HTML markup format. [Learn more](/ui/enriching/table-to-html).
1010
- Providing a list of recognized entities and their types, through a process known as _named entity recognition_ (NER). [Learn more](/ui/enriching/ner).
1111

12-
To add an enrichment, in the **Task** drop-down list of an **Enrichment** node in a workflow, select one of the following enrichment types:
12+
To add an enrichment, in an **Enrichment** node in a workflow, select one of the following enrichment types:
1313

1414
<Note>
1515
You can change enrichment settings only through [Custom](/ui/workflows#create-a-custom-workflow) workflow settings.
1616

1717
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-
- **Image Description** to provide a summarized description of the contents of each detected image. [Learn more](/ui/enriching/image-descriptions).
21-
- **Table Description** to provide a summarized description of the contents of each detected table. [Learn more](/ui/enriching/table-descriptions).
22-
- **Table to HTML** to provide a representation of each detected table in HTML markup format. [Learn more](/ui/enriching/table-to-html).
23-
- **Named Entity Recognition (NER)** to provide a list of recognized entities and their types. [Learn more](/ui/enriching/ner).
20+
- **Image** to provide a summarized description of the contents of each detected image. [Learn more](/ui/enriching/image-descriptions).
21+
- **Table** to provide a summarized description of the contents of each detected table. [Learn more](/ui/enriching/table-descriptions).
22+
- **Table** can also provide a representation of each detected table in HTML markup format. [Learn more](/ui/enriching/table-to-html).
23+
- **Text** to provide a list of recognized entities and their types by using a technique called _named entity recognition_ (NER). [Learn more](/ui/enriching/ner).
2424

2525
To add multiple enrichments, create an additional **Enrichment** node for each enrichment type that you want to add.

ui/enriching/table-descriptions.mdx

Lines changed: 6 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -51,17 +51,20 @@ Any embeddings that are produced after these summaries are generated will be bas
5151

5252
## Generate table descriptions
5353

54-
To generate table descriptions, in the **Task** drop-down list of an **Enrichment** node in a workflow, specify the following:
54+
To generate table descriptions, in an **Enrichment** node in a workflow, specify the following:
5555

5656
<Note>
5757
You can change a workflow's table description settings only through [Custom](/ui/workflows#create-a-custom-workflow) workflow settings.
5858

5959
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).
6060
</Note>
6161

62-
Select **Table Description**, and then choose one of the following provider (and model) combinations to use:
62+
Select **Table**, and then choose one of the following provider (and model) combinations to use:
6363

6464
- **OpenAI (GPT-4o)**. [Learn more](https://openai.com/index/hello-gpt-4o/).
6565
- **Anthropic (Claude 3.5 Sonnet)**. [Learn more](https://www.anthropic.com/news/claude-3-5-sonnet).
6666
- **Amazon Bedrock (Claude 3.5 Sonnet)**. [Learn more](https://aws.amazon.com/bedrock/claude/).
67-
- **Vertex AI (Gemini 2.0 Flash)**. [Learn more](https://cloud.google.com/vertex-ai/generative-ai/docs/gemini-v2).
67+
- **Vertex AI (Gemini 2.0 Flash)**. [Learn more](https://cloud.google.com/vertex-ai/generative-ai/docs/gemini-v2).
68+
69+
Make sure after you choose the provider and model, that **Table Description** is also displayed. If **Table Description** and **Table to HTML** are both
70+
displayed, be sure to select **Table Description**.

ui/enriching/table-to-html.mdx

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -62,7 +62,9 @@ Line breaks have been inserted here for readability. The output will not contain
6262

6363
## Generate table-to-HTML output
6464

65-
To generate table-to-HTML output, in the **Task** drop-down list of an **Enrichment** node in a workflow, select **Table to HTML**.
65+
To generate table-to-HTML output, in an **Enrichment** node in a workflow, for **Model**, select **OpenAI (GPT-4o)**.
66+
67+
Make sure after you choose this provider and model, that **Table to HTML** is also selected.
6668

6769
<Note>
6870
You can change a workflow's table description settings only through [Custom](/ui/workflows#create-a-custom-workflow) workflow settings.

ui/workflows.mdx

Lines changed: 17 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -282,9 +282,9 @@ import PlatformPartitioningStrategies from '/snippets/general-shared-text/platfo
282282

283283
</Accordion>
284284
<Accordion title="Enrichment node">
285-
For **Task**, choose one of the following:
285+
Choose one of the following:
286286

287-
- **Image Description** to summarize images. Also select one of the following provider (and model) combinations to use:
287+
- **Image** to summarize images. Also select one of the following provider (and model) combinations to use:
288288

289289
- **OpenAI (GPT-4o)**. [Learn more](https://openai.com/index/hello-gpt-4o/).
290290
- **Anthropic (Claude 3.5 Sonnet)**. [Learn more](https://www.anthropic.com/news/claude-3-5-sonnet).
@@ -293,20 +293,33 @@ import PlatformPartitioningStrategies from '/snippets/general-shared-text/platfo
293293

294294
[Learn more](/ui/enriching/image-descriptions).
295295

296-
- **Table Description** to summarize tables. Also select one of the following provider (and model) combinations to use:
296+
- **Table** to summarize tables. Also select one of the following provider (and model) combinations to use:
297297

298298
- **OpenAI (GPT-4o)**. [Learn more](https://openai.com/index/hello-gpt-4o/).
299299
- **Anthropic (Claude 3.5 Sonnet)**. [Learn more](https://www.anthropic.com/news/claude-3-5-sonnet).
300300
- **Amazon Bedrock (Claude 3.5 Sonnet)**. [Learn more](https://aws.amazon.com/bedrock/claude/).
301301
- **Vertex AI (Gemini 2.0 Flash)**. [Learn more](https://cloud.google.com/vertex-ai/generative-ai/docs/gemini-v2).
302302

303+
Make sure after you choose the provider and model, that **Table Description** is also displayed. If **Table Description** and **Table to HTML** are both
304+
displayed, be sure to select **Table Description**.
305+
303306
[Learn more](/ui/enriching/table-descriptions).
304307

305-
- **Table to HTML** to convert tables to HTML. Also select one of the following provider (and model) combinations to use:
308+
- **Table** to convert tables to HTML. Also select one of the following provider (and model) combinations to use:
306309

307310
- **OpenAI (GPT-4o)**. [Learn more](https://openai.com/index/hello-gpt-4o/).
308311

312+
Make sure after you choose this provider and model, that **Table to HTML** is also selected.
313+
309314
[Learn more](/ui/enriching/table-to-html).
315+
316+
- **Text** to generate a list of recognized entities and their types by using a technique called _named entity recognition_ (NER).
317+
Also select one of the following provider (and model) combinations to use:
318+
319+
- **OpenAI (GPT-4o)**. [Learn more](https://openai.com/index/hello-gpt-4o/).
320+
- **Anthropic (Claude 3.5 Sonnet)**. [Learn more](https://www.anthropic.com/news/claude-3-5-sonnet).
321+
322+
[Learn more](/ui/enriching/ner).
310323

311324
</Accordion>
312325
<Accordion title="Embedder node">

0 commit comments

Comments
 (0)