You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+8Lines changed: 8 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -14,6 +14,7 @@ This repository is a starting point for developers looking to integrate with the
14
14
15
15
*[What's New?](#whats-new)
16
16
*[Data Flywheel](#data-flywheel)
17
+
*[Safer Agentic A](#safer-agentic-ai)
17
18
*[Knowledge Graph RAG](#knowledge-graph-rag)
18
19
*[Agentic Workflows with Llama 3.1](#agentic-workflows-with-llama-31)
19
20
*[RAG with Local NIM Deployment and LangChain](#rag-with-local-nim-deployment-and-langchain)
@@ -42,6 +43,13 @@ This tutorial demonstrates an end-to-end Data Flywheel implementation that uses
42
43
43
44
-[Tool Calling Fine-tuning, Inference, and Evaluation with NVIDIA NeMo Microservices and NIMs](./nemo/data-flywheel/tool-calling)
44
45
46
+
### Safer Agentic AI
47
+
48
+
The following tutorials illustrate how to audit your large language models with NeMo Auditor to identify vulnerabilities to unsafe prompts, and how to run inference with multiple rails in parallel to reduce latency and improve throughput.
49
+
50
+
-[Audit your LLMs](./nemo/NeMo-Auditor/Getting_Started_With_NeMo_Auditor.ipynb)
51
+
-[Inference with Parallel Rails](./nemo/NeMo-Guardrails/Parallel_Rails_Tutorial.ipynb)
52
+
45
53
### Knowledge Graph RAG
46
54
47
55
This example implements a GPU-accelerated pipeline for creating and querying knowledge graphs using RAG by leveraging NIM microservices and the RAPIDS ecosystem to process large-scale datasets efficiently.
0 commit comments