# New Blog: Build a Knowledge Graph-based Agent With Llama 3.1, NVIDIA NIM, and LangChain

**URL:** <https://community.neo4j.com/t/new-blog-build-a-knowledge-graph-based-agent-with-llama-3-1-nvidia-nim-and-langchain/69162>\
**Category:** Community Content & Blogs\
**Created:** [August 9, 2024, 5:08pm UTC](https://community.neo4j.com/t/new-blog-build-a-knowledge-graph-based-agent-with-llama-3-1-nvidia-nim-and-langchain/69162 "2024-08-09T17:08:44Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![alexander.erdl](https://sea1.discourse-cdn.com/flex021/user_avatar/community.neo4j.com/alexander.erdl/32/27386_2.png) [@alexander.erdl](https://community.neo4j.com/u/alexander.erdl)\
**Post date:** [August 9, 2024, 5:08pm UTC](https://community.neo4j.com/t/new-blog-build-a-knowledge-graph-based-agent-with-llama-3-1-nvidia-nim-and-langchain/69162/1 "2024-08-09T17:08:44Z")

</div>

Created using ChatGPT Use Llama 3.1 native function-calling capabilities to retrieve structured data from a knowledge graph to power your RAG applications

While most people focus on retrieval-augmented generation (RAG) over unstructured text, such as company documents or documentation, I am pretty bullish on retrieval systems over structured information, particularly knowledge graphs. There has been a lot of excitement about GraphRAG, specifically Microsoft’s implementation. However, in thei...

Read it: [Build a Knowledge Graph-based Agent With Llama 3.1, NVIDIA NIM, and LangChain](https://neo4j.com/developer-blog/knowledge-graph-llama-nvidia-langchain/)