Did you know Diffbot has a Natural Language API? Not only is it capable of extracting entities but also the relationships between entities in any body of text.

Use the NL API to build Knowledge Graphs from large corpora, or highly personalized news monitoring pipelines.

And starting right now, you can explore the Natural Language API in the dashboard without code. Give it a go at https://app.diffbot.com/natural-language/

We're excited to introduce a free plan for Diffbot. The free plan will replace our 2 week trial and include a generous helping of monthly credits for startups and hobbyists to get started without worrying about a monthly bill.

What's included in the free plan?

• Access to Extract, Knowledge Graph (DQL & Enhance), and Natural Language Processing
• 10,000 monthly credits
• API and Dashboard access

To get started, sign up for an account here.

🐣 Each egg contains a clue to the next.
👀 Eggs are only visible in entities on the Dashboard (link in comment), not via API.
🔍 This is not school. Google/ChatGPT/query all you want.
🥇 First person to eggstract all 16 easter eggs will win a lifetime personal plan and the swaggiest Diffbot swag.

Your first clue — "The Easter Bunny was first mentioned in an essay by this German physician."

Notes:

• Searching on the dashboard does not consume credits
• Sign up for a fresh trial if your trial has expired

We've recently expanded coverage of 'secForms' back to 1994 (pre XBRL introduced in 2005). Over the coming weeks and months, you will see these data flowing into organization profiles. To view examples of secForms already in the graph search for organizations that have secForms (type:Organization has:secForms)

We've added type:Research to the graph. Each entity is a journal article or research publication from a validated source. Data will continue to flow for the next month or so as we integrate all of the available metadata from OpenAlex.org. Future phases will combine OpenAlex metadata with the full text of the publication extracted from HTML or PDF (when it is publicly available to access) and will include data provenance and fair use details. Try a search for journal articles that include AI in the title: type:Research title:"AI" sortBy:date

If you prefer reading long-form content on RSS readers, you're gonna love this free tool.

We built a fast JSON to CSV converter that supports automatic list detection, a column selection UI, and offline mode. Try it out here.

Diffbot's ChatGPT plugin is available to everyone free of charge. The only requirement is a subscription to ChatGPT Plus for access to plugins. Get the Diffbot plugin by searching for "Diffbot" in the ChatGPT plugin store under the GPT-4 tab. Click here to find Diffbot on ChatGPT.

The NL API now has the ability to summarize text. Summarization in the NL API uses the Diffbot LLM for fast inference. There is no truncation. Long documents are broken into chunks and summarized individually. A final summary is generated from these chunk summaries.

See the NL API summarization demo here.

Enhance will now generate Coverage Reports in the background rather than during the execution of the bulkjob to speed up completion of bulkjobs. Previously, users could download the report immediately following completion of the bulkjob. Users should now poll the bulkjob status to ensure that the coverage report is generated. Status is available under content.reports[].status and should have the value of COMPLETE to indicate that the report is generated.

The changes are described here: https://docs.diffbot.com/reference/bulkjobstatus
*Please note that this change DOES NOT affect the behavior of bulkjob results - only the coverage report.