Building a Private Knowledge Base with FastGPT, ChatGLM, Ollama, and M3E Embeddings
Hardware Requirements
The following configurations are for reference only:
ChatGLM3-6B + M3E: NVIDIA RTX 3060 12GB or higher
Qwen:4B + M3E: NVIDIA RTX 3060 12GB or higher
Qwen:2B + M3E: NVIDIA GTX 1660 6GB or higher
Larger models require better GPU performance. Extremely small models can run on low-end CPUs, but inference accuracy will be poo ...
Posted on Fri, 15 May 2026 11:00:07 +0000 by elementaluk
Local Deployment of FastGPT + One-API + ChatGLM3-6B Knowledge Base
1. Local Model Setup
Required Repositories & Resources:
ChatGLM3-6B code: https://github.com/THUDM/ChatGLM3
FastGPT: https://github.com/labring/FastGPT
Vector model M3E (deploy via Docker): https://huggingface.co/moka-ai/m3e-base
Anaconda3 installer: https://mirrors.tuna.tsinghua.edu.cn/anaconda/archive/
Create Conda Environment
conda cre ...
Posted on Fri, 15 May 2026 00:19:05 +0000 by DaveEverFade
Building a Personal Knowledge Assistant with LangChain and Gradio
This implementation creates a personal knowledge assistant by integrating LangChain for retrieval-augmented generation with a Gradio-based user interface. The system allows users to query a custom knowledge base while optionally enabling contextual retrieval to enhance response accuracy and reduce model hallucinations.
Environment Setup
Python ...
Posted on Thu, 14 May 2026 19:56:45 +0000 by kimbeejo