Accessing Locally Deployed Models on RK3588 Using LangChain

Accessing Locally Deployed Models on RK3588 Using LangChain

In the field of artificial intelligence and natural language processing, utilizing powerful tools and frameworks to interact with locally deployed models is a common and important task. Today, I will share how to use the LangChain framework to access models deployed locally on the RK3588. Background Knowledge Introduction to LangChain LangChain is a powerful Python … Read more

Local Deployment of DeepSeek-R1 Large Model on RK3588 Platform: NPU Edition

Local Deployment of DeepSeek-R1 Large Model on RK3588 Platform: NPU Edition

Using the NPU to run inference on large models can more effectively plan resource allocation, achieving more efficient applications. 1 Preparation Before Deployment To deploy large language models using the NPU on RK3588, the following files need to be prepared in advance, which include the corresponding files for Rockchip’s NPU and the DeepSeek inference model … Read more

Implementing Fast-LIO Robot SLAM Indoor Positioning Algorithm with RK3588, ROS2 Humble, EasyMQoS, and MID360

Implementing Fast-LIO Robot SLAM Indoor Positioning Algorithm with RK3588, ROS2 Humble, EasyMQoS, and MID360

To ensure stable and high-precision outdoor positioning, I started using a 3D LiDAR, the MID360 LiDAR.This LiDAR transmits point cloud data to the host via Ethernet, powered by an external 12V power supply.The implementation mainly includes the following aspects:1. Building the hardware unmanned vehicle platform2. Compiling the MID360 driver and testing it on RK3588-ROS2-Humble3. Compiling … Read more

Tutorial for Deploying DeepSeek Model on RK3588 Linux Platform

Tutorial for Deploying DeepSeek Model on RK3588 Linux Platform

For more content, you can join the Linux system knowledge base package (tutorials + videos + Q&A). Table of Contents 1. Download rknn-llm and DeepSeek model 2. Install RKLLM-Toolkit 2.1 Install miniforge3 tool 2.2 Download miniforge3 installation package 2.3 Install miniforge3 3. Create RKLLM-Toolkit Conda environment 3.1 Enter Conda base environment 3.2 Create a Conda … Read more

Deploying and Testing the DeepSeek Model on the RK3588 Development Board

Deploying and Testing the DeepSeek Model on the RK3588 Development Board

DeepSeek is here! Recently, the rising star in the AI field, DeepSeek (Chinese name: 深度求索), has quickly gained popularity online due to its low-cost and high-performance AI model. Its core is a powerful language model capable of understanding natural language and generating high-quality text. Additionally, DeepSeek is freely available to developers worldwide, accelerating the spread … Read more

Implementation of Function Call Based on RK3588 Large Language Model

Implementation of Function Call Based on RK3588 Large Language Model

The example of function call invocation is as follows: POST /v1/chat/completions HTTP/1.1 Host: api.openai.com Authorization: Bearer YOUR_API_KEY Content-Type: application/json { "model": "gpt-4", "messages": [{"role": "user", "content": "What is the weather like in Beijing today?"}], "tools": [ // Define the tool list { "type": "function", "function": { "name": "get_weather", "description": "Get weather information for a specified … Read more

RK3588-Based rkllm Compatible with OpenAI API

RK3588-Based rkllm Compatible with OpenAI API

Usage: git clone https://github.com/huonwe/rkllm_openai_like_api.gitcd rkllm_openai_like_api Add the required dynamic libraries: sudo cp lib/*.so /usr/lib Installuv: curl -LsSf https://astral.sh/uv/install.sh | sh Installpythondependencies: uv sync Run: uv run server.py By default, the platform is set to rk3588, the model path is models/deepseek-r1-1.5b-w8a8.rkllm, and the listening port is 8080. You can manually specify parameters, such as uv run … Read more

RK3588 Low Latency and Low Bandwidth Video Transmission Solution Enhances Remote Control Capabilities of Unmanned Devices

RK3588 Low Latency and Low Bandwidth Video Transmission Solution Enhances Remote Control Capabilities of Unmanned Devices

Unmanned systems, especially drones and unmanned vehicles, are gradually becoming more prevalent in daily life. For instance, drones are widely used in fields such as power line inspection, pipeline monitoring, pollution control, and forest fire prevention. In the unmanned vehicle sector, applications like the much-discussed “萝卜快跑” (Radish Run) autonomous taxi, anti-terrorism robots, firefighting robots, and … Read more

Combining RK3588J and Domestic FPGA for High-Speed Signal Acquisition and Visualization Solutions!

Combining RK3588J and Domestic FPGA for High-Speed Signal Acquisition and Visualization Solutions!

In this era of the Internet of Things, how can we quickly capture rapidly changing signal data? There is a golden partner solution: the RK3588J is a high-performance processor based on Rockchip RK3588, combined with the flexibility of FPGA, the combination of the two can achieve many innovative applications in the AI era. In terms … Read more

RK3588 vs RK3568 Motherboards: Which is More Suitable for Smart NVR Device Applications?

RK3588 vs RK3568 Motherboards: Which is More Suitable for Smart NVR Device Applications?

Industry Background With the widespread deployment of modern security networks, video surveillance has already integrated into our daily lives: at the Hangzhou Asian Games venues, thousands of smart cameras can simultaneously recognize 20 types of dangerous actions; in a kindergarten security room in Shenzhen, smart monitoring devices are managing high-definition cameras, recording campus footage, and … Read more