Kingsley Uyi Idehen
kidehen.mastodon.social.ap.brid.gy
Kingsley Uyi Idehen
@kidehen.mastodon.social.ap.brid.gy
Founder & CEO, OpenLink Software (#VirtuosoRDBMS, #YouI, #OSDS, creator)

#SSI: ni:///sha-256;xxdJ16bthZ724u0_xHvcNt0_Wu4ABxb56nPT50hNz-Q (denotes a SHA256 […]

[bridged from https://mastodon.social/@kidehen on the fediverse by https://fed.brid.gy/ ]
LLMs + the Model Context Protocol (MCP) are the Yang to the Semantic Web Project's Yin.

We now have a solution to the final hurdle—visualization.

Years of Linked Data work now come alive. I explain this, with demonstrations, in a new newsletter post.

www.linkedin.com/pulse/semant...

#mcp
June 18, 2025 at 11:35 PM
The Model Context Protocol (MCP) brings Unix-style loose coupling to AI Agents.

I built a visual explainer (JSON-LD metadata included) using Google Gemini’s new Canvas feature—with an embedded Knowledge Graph to illustrate.

Check it out […]

[Original post on mastodon.social]
May 30, 2025 at 5:29 PM
What’s going on here?

Prompts are being processed through queries executed against a Knowledge Graph (KG)—all thanks to loose coupling. The target KG could reside locally, live on the Web, or be part of the vast Linked Open Data (LOD) cloud.

#a2a #mcp #virtuosordbms #ai #agentic #genai
May 29, 2025 at 7:13 PM
Architecture? As depicted in the attached image.

BTW -- @Google Gemini can generate pretty accurate diagrams using @drawio XML!

#a2a #mcp #opal #virtuosordbms #ai #agentic
May 29, 2025 at 7:11 PM
A simple GUI-based screencast demo of the @openlink AI Layer (OPAL), showing what’s now possible via MCP + A2A—namely, composing and orchestrating agentic workflows through loosely coupled software.

How?

An Agent Host routes tasks to Agents via A2A. Agents […]

[Original post on mastodon.social]
May 29, 2025 at 7:10 PM
An example of what’s now possible—thanks to our (@openlink) sophisticated MCP Server for JDBC, Oracle’s native JDBC Driver, and Anthropic's Claude Desktop as the MCP client:

A dashboard generated from Oracle’s HR database using the following natural language […]

[Original post on mastodon.social]
May 13, 2025 at 4:33 PM
Here’s another dashboard variant built using Claude Desktop as the MCP client and the virtual Northwind Knowledge Graph, derived from underlying Northwind tables. This edition adds both a Company and Employee dimension […]

[Original post on mastodon.social]
April 7, 2025 at 11:34 PM
This week’s edition of my @linkedin newsletter shines a light on the impact of the Model Context Protocol (MCP) across multiple computing eras—leading right up to today.

We’ve arrived at a moment where loose coupling principles are cool (and super useful) […]

[Original post on mastodon.social]
April 5, 2025 at 4:24 PM
The Model Context Protocol acts as a universal translator between LLMs and data sources, eliminating complex platform-specific requirements. Our new open source MCP server for ODBC (mcp-odbc-server) enables seamless integration of any ODBC-accessible […]

[Video] [Original post on mastodon.social]
March 29, 2025 at 11:00 PM
@medium,

I still don't have an email message or any sense of the location of my export archive. We are now going on 48 hrs since my initial request.

/cc @evhead @biz
March 18, 2025 at 3:53 PM
Here’s a DataTwingler AI Agent configuration in Markdown, designed for interacting with UniProt’s massive Knowledge Graph, which consists of 210 billion machine-computable statements of fact, meticulously curated by domain experts […]

[Original post on mastodon.social]
February 13, 2025 at 6:39 PM
February 6, 2025 at 8:01 PM
Variant of the same demo, but this time courtesy of Private LLM for iOS and macOS.

#ai #genai #llms
February 3, 2025 at 11:19 PM
The pendulum is swinging back toward the edge of the global connectivity mesh we call the #Internet—a familiar cycle, much like the shift from time-shared mainframes to the PC and Mac era.

Microsoft's Phi-4 LLM running on my MacBook Pro (M1), courtesy of LM […]

[Original post on mastodon.social]
February 3, 2025 at 11:18 PM
Quick evaluation test screencast and a tabulated offer analysis for the new GPT-o3 LLM family from #openai.

#genai #ai
January 31, 2025 at 9:32 PM
The latest edition of my newsletter is out!

This week, I focus on a deceptively simple reasoning and inference challenge to compare the capabilities of AI+Compute inference services from #openai, #google, #microsoft, #groq, #alibaba (Qwen), #deepseek, and […]

[Original post on mastodon.social]
January 30, 2025 at 10:05 PM
#google Gemini 2.0 now passes my “deceptively simple” test: generating #sparql queries against the #dbpedia #knowledgegraph.

This marks the first time Gemini LLMs have succeeded in my testing. Ironically, it’s less about core #llm capability and more about […]

[Original post on mastodon.social]
December 20, 2024 at 7:47 PM
Here are live links to the OpenLink AI Layer (#opal) binding to Anthropic's Claude language model demo.

1] [https://netid-qa.openlinksw.com:8443/chat/?chat_id=s-AXhonwExSBCeTe11v64u75fodBgC4vV3qsgQS8HZH64B&t=120#usr-t0zen1zo86i -- animated page.

2] [ […]

[Original post on mastodon.social]
December 18, 2024 at 2:19 PM
Boom!

The OpenLink Software #ai Layer (#opal) now supports AnthropicAI's #claude language models.

See comments for a #datatwingler AI Agent demo executing #sparql and #sql queries via a live #virtuosordbms instance.

Remember, query scope is SPARQL, #odbc […]

[Original post on mastodon.social]
December 18, 2024 at 2:17 PM
Here's the #screencast demo of Grok generating a #sparql query results page for a #dbpedia #knowledgegraph query.
December 15, 2024 at 8:53 PM
New Qwen-QwQ-32 LLM passes my tricky
#dbpedia #sparql query results link test.

Prompt:
Using the DBpedia endpoint, list all movies directed by Spike Lee and encode the sparql query in a clickable link.

Result:
dbpedia.org/sparql?query...

Chat:
https://huggingface.co/spaces/Qwen/QwQ-32B-preview
November 29, 2024 at 9:32 PM
Demonstrating conversational interaction with the
KnowledgeGraph generated from the LinkedIn article processed in the prior post.
Related:

1. linkeddata.uriburner.com/assis…... -- animated page.

2. linkeddata.uriburner.com/assis…... -- entire OpenLink AI […]

[Original post on mastodon.social]
November 27, 2024 at 12:58 AM
How to generate a powerful Knowledge Graph from a LinkedIn article using a Large Language Model (LLM) such as OpenAI’s GPT-4o or GPT-4o-mini.

#ai #genai #usecase #llms #knowledgegraph #howto
November 27, 2024 at 12:58 AM
Check out this #NotebookLM-generated #podcast edition of the #newsletter article:

🎙 http://www.openlinksw.com/data/podcasts/Tackling_Information_Overload_via_GenAI_and_Knowledge_Graphs.mp3

Explore the #ai Agent page view here:
🔗 […]

[Original post on mastodon.social]
November 18, 2024 at 5:13 PM