# Working with Knowledge Graph (.ttl) for Retrieved Augmented Generation purpose

**URL:** <https://community.stardog.com/t/working-with-knowledge-graph-ttl-for-retrieved-augmented-generation-purpose/4930>\
**Category:** Support\
**Created:** [May 16, 2024, 2:35pm UTC](https://community.stardog.com/t/working-with-knowledge-graph-ttl-for-retrieved-augmented-generation-purpose/4930 "2024-05-16T14:35:02Z")\
**Posts on this page:** 8\
**Page:** 1

<div class="post-metadata">

**Author:** ![AlexisP](https://avatars.discourse-cdn.com/v4/letter/a/eada6e/32.png) [@AlexisP](https://community.stardog.com/u/AlexisP)\
**Post date:** [May 16, 2024, 2:35pm UTC](https://community.stardog.com/t/working-with-knowledge-graph-ttl-for-retrieved-augmented-generation-purpose/4930/1 "2024-05-16T14:35:02Z")

</div>

Hi everyone,

This topic is more a general discussion, as i'm looking for experiences or opinions.

Have you ever used a knowledge graph hosted on Stardog to set up a RAG. More specifically, as a external data source on which the LLM relies to answer a question?

My question concerns the interpretability of a Knowledge Graph into something that the LLM can understand (a collection of triplets, for example).

---

<div class="post-metadata">

**Author:** ![zachary.whitley](https://yyz2.discourse-cdn.com/flex030/user_avatar/community.stardog.com/zachary.whitley/32/94_2.png) [@zachary.whitley](https://community.stardog.com/u/zachary.whitley)\
**Post date:** [May 19, 2024, 9:11am UTC](https://community.stardog.com/t/working-with-knowledge-graph-ttl-for-retrieved-augmented-generation-purpose/4930/2 "2024-05-19T09:11:43Z")

</div>

If you're talking RAG and Stardog you should start with their new Voicebox feature and what they're calling Safety RAG. [Safety RAG: Improving AI Safety by Extending AI&#39;s Data Reach | Stardog](https://www.stardog.com/blog/safety-rag-improving-ai-safety-by-extending-ais-data-reach/)

If you're taking about backing a RAG based LLM solution in general take a look at the work done by Microsoft Research on GraphRAG [GraphRAG: Unlocking LLM discovery on narrative private data - Microsoft Research](https://www.microsoft.com/en-us/research/blog/graphrag-unlocking-llm-discovery-on-narrative-private-data/)

On a somewhat related topic that I just came across this, llama3 in a single Java file! [GitHub - mukel/llama3.java: Practical Llama 3 inference in Java](https://github.com/mukel/llama3.java)

---

<div class="post-metadata">

**Author:** ![AlexisP](https://avatars.discourse-cdn.com/v4/letter/a/eada6e/32.png) [@AlexisP](https://community.stardog.com/u/AlexisP)\
**Post date:** [May 21, 2024, 7:46am UTC](https://community.stardog.com/t/working-with-knowledge-graph-ttl-for-retrieved-augmented-generation-purpose/4930/3 "2024-05-21T07:46:34Z")

</div>

Your answer is very informative, it's great.

The link to Github is great, that's the kind of thing I was looking for.

Thanks a lot!

---

<div class="post-metadata">

**Author:** ![zachary.whitley](https://yyz2.discourse-cdn.com/flex030/user_avatar/community.stardog.com/zachary.whitley/32/94_2.png) [@zachary.whitley](https://community.stardog.com/u/zachary.whitley)\
**Post date:** [May 21, 2024, 2:11pm UTC](https://community.stardog.com/t/working-with-knowledge-graph-ttl-for-retrieved-augmented-generation-purpose/4930/4 "2024-05-21T14:11:20Z")

</div>

You're very welcome. I think Stardog is a much overlooked platform for not only using AI but for AIOps. I'm going to hop in my Time Machine and head back to this [SimplePhotoAnnotation - W3C Wiki](https://www.w3.org/wiki/SimplePhotoAnnotation) Check out the time stamp at the bottom. 2005!

---

<div class="post-metadata">

**Author:** ![system](https://canada1.discourse-cdn.com/flex030/uploads/stardog/original/2X/e/ed66b48a616f505106a4acde3c9cee7e6da9bc67.svg) [@system](https://community.stardog.com/u/system)\
**Post date:** [November 13, 2024, 3:23am UTC](https://community.stardog.com/t/working-with-knowledge-graph-ttl-for-retrieved-augmented-generation-purpose/4930/5 "2024-11-13T03:23:06Z")

</div>



---

<div class="post-metadata">

**Author:** ![system](https://canada1.discourse-cdn.com/flex030/uploads/stardog/original/2X/e/ed66b48a616f505106a4acde3c9cee7e6da9bc67.svg) [@system](https://community.stardog.com/u/system)\
**Post date:** [June 6, 2025, 3:26am UTC](https://community.stardog.com/t/working-with-knowledge-graph-ttl-for-retrieved-augmented-generation-purpose/4930/6 "2025-06-06T03:26:01Z")

</div>



---

<div class="post-metadata">

**Author:** ![system](https://canada1.discourse-cdn.com/flex030/uploads/stardog/original/2X/e/ed66b48a616f505106a4acde3c9cee7e6da9bc67.svg) [@system](https://community.stardog.com/u/system)\
**Post date:** [January 24, 2026, 7:01am UTC](https://community.stardog.com/t/working-with-knowledge-graph-ttl-for-retrieved-augmented-generation-purpose/4930/7 "2026-01-24T07:01:21Z")

</div>



---

<div class="post-metadata">

**Author:** ![system](https://canada1.discourse-cdn.com/flex030/uploads/stardog/original/2X/e/ed66b48a616f505106a4acde3c9cee7e6da9bc67.svg) [@system](https://community.stardog.com/u/system)\
**Post date:** [September 29, 2026, 2:26pm UTC](https://community.stardog.com/t/working-with-knowledge-graph-ttl-for-retrieved-augmented-generation-purpose/4930/8 "2026-09-29T14:26:29Z")

</div>


