You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: ui/enriching/image-descriptions.mdx
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -44,15 +44,15 @@ Any embeddings that are produced after these summaries are generated will be bas
44
44
45
45
## Generate image descriptions
46
46
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:
48
48
49
49
<Note>
50
50
You can change a workflow's image description settings only through [Custom](/ui/workflows#create-a-custom-workflow) workflow settings.
51
51
52
52
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).
53
53
</Note>
54
54
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:
Copy file name to clipboardExpand all lines: ui/enriching/ner.mdx
+8-8Lines changed: 8 additions & 8 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -87,21 +87,21 @@ Here is an example of a list of recognized entities and their types using GPT-4o
87
87
88
88
# Generate a list of entities and their types
89
89
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:
91
91
92
92
<Note>
93
93
You can change a workflow's NER settings only through [Custom](/ui/workflows#create-a-custom-workflow) workflow settings.
94
94
95
95
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).
96
96
</Note>
97
97
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
102
102
**Prompt** to run NER on the **Input sample** and shows the results in the **Output**. Look specifically at the `response_json` field for the
103
103
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**.
105
105
106
106
<Note>
107
107
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-
122
122
- Changing any other portions of the default prompt could produce unexpected results.
123
123
</Note>
124
124
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**.
Copy file name to clipboardExpand all lines: ui/enriching/overview.mdx
+5-5Lines changed: 5 additions & 5 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -9,17 +9,17 @@ _Enriching_ adds enhancments to the processed data that Unstructured produces. T
9
9
- Providing a representation of a detected table in HTML markup format. [Learn more](/ui/enriching/table-to-html).
10
10
- Providing a list of recognized entities and their types, through a process known as _named entity recognition_ (NER). [Learn more](/ui/enriching/ner).
11
11
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:
13
13
14
14
<Note>
15
15
You can change enrichment settings only through [Custom](/ui/workflows#create-a-custom-workflow) workflow settings.
16
16
17
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).
18
18
</Note>
19
19
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).
24
24
25
25
To add multiple enrichments, create an additional **Enrichment** node for each enrichment type that you want to add.
Copy file name to clipboardExpand all lines: ui/enriching/table-descriptions.mdx
+6-3Lines changed: 6 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -51,17 +51,20 @@ Any embeddings that are produced after these summaries are generated will be bas
51
51
52
52
## Generate table descriptions
53
53
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:
55
55
56
56
<Note>
57
57
You can change a workflow's table description settings only through [Custom](/ui/workflows#create-a-custom-workflow) workflow settings.
58
58
59
59
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).
60
60
</Note>
61
61
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:
-**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**.
-**Vertex AI (Gemini 2.0 Flash)**. [Learn more](https://cloud.google.com/vertex-ai/generative-ai/docs/gemini-v2).
302
302
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
+
303
306
[Learn more](/ui/enriching/table-descriptions).
304
307
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:
0 commit comments