diff --git a/img/enriching/Image-Description-1.png b/img/enriching/Image-Description-1.png new file mode 100644 index 00000000..07de2a29 Binary files /dev/null and b/img/enriching/Image-Description-1.png differ diff --git a/img/enriching/Image-Description-2.png b/img/enriching/Image-Description-2.png new file mode 100644 index 00000000..41d8c232 Binary files /dev/null and b/img/enriching/Image-Description-2.png differ diff --git a/img/enriching/Image-Description-3.png b/img/enriching/Image-Description-3.png new file mode 100644 index 00000000..ee80633d Binary files /dev/null and b/img/enriching/Image-Description-3.png differ diff --git a/img/enriching/NER-Example.png b/img/enriching/NER-Example.png new file mode 100644 index 00000000..ea057588 Binary files /dev/null and b/img/enriching/NER-Example.png differ diff --git a/img/enriching/Table-Description-1.png b/img/enriching/Table-Description-1.png new file mode 100644 index 00000000..cae5d56c Binary files /dev/null and b/img/enriching/Table-Description-1.png differ diff --git a/img/enriching/Table-Description-2.png b/img/enriching/Table-Description-2.png new file mode 100644 index 00000000..f705cb5f Binary files /dev/null and b/img/enriching/Table-Description-2.png differ diff --git a/ui/enriching/image-descriptions.mdx b/ui/enriching/image-descriptions.mdx index ba7f5732..f338f3b6 100644 --- a/ui/enriching/image-descriptions.mdx +++ b/ui/enriching/image-descriptions.mdx @@ -39,6 +39,14 @@ Line breaks have been inserted here for readability. The output will not contain } ``` +Here are three examples of the descriptions for detected images. These descriptions are generated with GPT-4o by OpenAI: + +![Description of an image showing a scatter plot graph](/img/enriching/Image-Description-1.png) + +![Description of an image showing the Matthews Correlation Coefficient for different VQA datasets](/img/enriching/Image-Description-2.png) + +![Description of an image showing three scatter plots](/img/enriching/Image-Description-3.png) + Any embeddings that are produced after these summaries are generated will be based on the `text` field's contents. ## Generate image descriptions diff --git a/ui/enriching/ner.mdx b/ui/enriching/ner.mdx index 7a10b2d8..1cfa7bdd 100644 --- a/ui/enriching/ner.mdx +++ b/ui/enriching/ner.mdx @@ -96,6 +96,11 @@ entities and their relationship types, using GPT-4o. Note specifically the `enti } ``` +Here is another example of some of the entities, their entity types, and relationships that are recognized for a given paragraph of text. This information +is generated by GPT-4o by OpenAI: + +![Named entity recognition for information in a paragraph of text](/img/enriching/NER-Example.png) + By default, the following entity types are supported for NER: - `PERSON` diff --git a/ui/enriching/table-descriptions.mdx b/ui/enriching/table-descriptions.mdx index b63c515e..2b8ceef0 100644 --- a/ui/enriching/table-descriptions.mdx +++ b/ui/enriching/table-descriptions.mdx @@ -43,6 +43,12 @@ Line breaks have been inserted here for readability. The output will not contain } ``` +Here are two examples of the descriptions for detected tables. These descriptions are generated with GPT-4o by OpenAI: + +![Description of a table with information about endoscopic datasets](/img/enriching/Table-Description-1.png) + +![Description of a table with information about potentiodynamic polarization of stainless steel](/img/enriching/Table-Description-2.png) + The generated table's summary will overwrite any previous contents in the `text` field. The table's original content is available in the `image_base64` field.