You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
55 lines
2.5 KiB
Markdown
55 lines
2.5 KiB
Markdown
---
|
|
title: Using Nvidia NIM API Key in LobeChat
|
|
description: Learn how to configure and use Nvidia NIM AI models in LobeChat, obtain an API key, and start a conversation.
|
|
tags:
|
|
- LobeChat
|
|
- Nvidia NIM
|
|
- API Key
|
|
- Web UI
|
|
---
|
|
|
|
# Using Nvidia NIM in LobeChat
|
|
|
|
<Image alt={'Using Nvidia NIM in LobeChat'} cover src={'https://github.com/user-attachments/assets/539349dd-2c16-4f42-b525-cca74e113541'} />
|
|
|
|
[NVIDIA NIM](https://developer.nvidia.com/nim) is part of NVIDIA AI Enterprise and is designed to accelerate the deployment of generative AI applications through microservices. It provides a set of easy-to-use inference microservices that can run on any cloud, data center, or workstation, supporting NVIDIA GPU acceleration.
|
|
|
|
This document will guide you on how to access and use AI models provided by Nvidia NIM in LobeChat:
|
|
|
|
<Steps>
|
|
### Step 1: Obtain Nvidia NIM API Key
|
|
|
|
- First, visit the [Nvidia NIM console](https://build.nvidia.com/explore/discover) and complete the registration and login.
|
|
- On the `Models` page, select the model you need, such as Deepseek-R1.
|
|
|
|
<Image alt={'Select Model'} inStep src={'https://github.com/user-attachments/assets/b49ed0c1-d6bf-4f46-b9df-5f7c730afaa3'} />
|
|
|
|
- On the model details page, click "Build with this NIM".
|
|
- In the pop-up dialog, click the `Generate API Key` button.
|
|
|
|
<Image alt={'Get API Key'} inStep src={'https://github.com/user-attachments/assets/5321f987-2c64-4211-8549-bd30ca9b59b9'} />
|
|
|
|
- Copy and save the created API Key.
|
|
|
|
<Callout type={'warning'}>
|
|
Please store the key securely as it will only appear once. If you accidentally lose it, you will need to create a new key.
|
|
</Callout>
|
|
|
|
### Step 2: Configure Nvidia NIM in LobeChat
|
|
|
|
- Visit the `Application Settings` -> `AI Service Provider` interface in LobeChat.
|
|
- Find the settings item for `Nvidia NIM` in the list of providers.
|
|
|
|
<Image alt={'Fill in the Nvidia NIM API Key'} inStep src={'https://github.com/user-attachments/assets/dfc45807-2ed6-43eb-af4c-47df66dfff7d'} />
|
|
|
|
- Enable the Nvidia NIM service provider and fill in the obtained API key.
|
|
- Select an Nvidia NIM model for your assistant and start the conversation.
|
|
|
|
<Image alt={'Select Nvidia NIM Model'} inStep src={'https://github.com/user-attachments/assets/cb4ba5fe-c223-4b9f-a662-de93e4a536d1'} />
|
|
|
|
<Callout type={'warning'}>
|
|
You may need to pay the API service provider during use, please refer to Nvidia NIM's related fee policies.
|
|
</Callout>
|
|
</Steps>
|
|
|
|
Now you can use the models provided by Nvidia NIM to have conversations in LobeChat. |