Partner Certified Addon

This addon is provided by Maretha.io, and validated as a Nuxeo Partner Premier Certified Addon. Any bugs or improvements should be reported to the partner (please do not fill any Nuxeo Jira ticket related to this addon). You are also responsible for confirming adherence to your company's policies regarding the use of OpenAI technology.

Description

This add-on integrates with OpenAI's summarization API to condense extensive text documents into succinct summaries.

OpenAI API key

You must obtain an OpenAI API key to use it and you must set this key in nuxeo.conf:

• openai.token=[YOUR-API-TOKEN-HERE]

Usage

Harnessing the power of Nuxeo bulk actions and the Producer/Consumer pattern, the add-on operates by splitting each uploaded text document into individual pages. Each of these pages is then summarized independently, with the summary for each page generated in an asynchronous manner for maximum efficiency. Once all pages have been processed, the individual summaries are assembled to form a comprehensive summary of the entire document.

Technical details

The addon includes a feature flag that controls the automatic generation of summaries when a document is uploaded. By default, the "feature.summary.auto.generation.enabled" property is set to "true", meaning that summaries are automatically created upon document ingestion.

However, if you prefer more control over the process, you can set this property to "false". In this case, summaries won't be automatically created. Instead, users can manually request the generation of a summary for a specific document at their convenience. This is as simple as clicking a button in the user interface. This flexibility allows you to customize the summarization process to best fit your needs.

Configuration

The following properties can also be configured:

• summary.extraction.enable.mime-types=text/plain,application/pdf,application/msword,application/vnd.openxmlformats-officedocument.wordprocessingml.document
• summary.extraction.openai.url=https://api.openai.com/v1/completions
• summary.extraction.openai.model=text-davinci-003
• summary.extraction.openai.temperature=0.3
• summary.extraction.openai.max-tokens=200
• summary.extraction.openai.top-p=1
• summary.extraction.openai.frequency-penalty=0

• summary.extraction.openai.presence-penalty=0

• summary.extraction.http.max-retries=3

• summary.extraction.http.sec-delay=10

• summary.extraction.http.sec-max-delay=60

• summaryStreams.bucketSize=5

• summaryStreams.batchSize=1
• summaryStreams.concurrency=3

• summaryStreams.partition=6

• feature.summary.auto.generation.enabled=true