BISHENG: Open Source LLM DevOps Platform for Building Enterprise AI Applications

General Introduction

BISHENG is an open source LLM (Large Language Model) DevOps platform designed for next generation enterprise AI applications. The platform provides powerful and comprehensive features including generative AI workflows, RAG (Retrieval Augmented Generation), Intelligent Agents, Unified Model Management, Evaluation, SFT (fine-tuning), dataset management, enterprise-grade system management, and Observability, etc. Designed to support complex enterprise application scenarios, BISHENG is already being adopted by many industry-leading organizations and Fortune 500 companies. The platform's high-precision document parsing models have been trained on five years of high-quality data and are capable of recognizing printed text, handwritten text, rare characters, tables and layout analysis. Users can privately deploy BISHENG for free to enjoy its powerful features and community support.

I saw this project a long time ago and recently saw that the iteration is barely mature enough to be released, so the question arises, why not go with the better Dify or FAST?

Function List

• Generative AI workflows
• Retrieval Augmentation Generation (RAG)
• Intelligent Agents
• Unified Model Management
• Model Evaluation
• Fine tuning (SFT)
• Data set management
• Enterprise-level systems management
• observability
• Highly accurate document parsing
• Multi-agent collaboration
• Fixed Layout Report Generation
• Comparison of policy updates
• Customer service assistance
• Meeting record generation
• Resume Screening
• Call log analysis
• Unstructured data governance
• Knowledge mining
• data analysis

Using Help

Installation process

1. system requirements::
   • CPU: 8 cores or more
   • Memory: 32GB or more
   • Docker: version 19.03.9+
   • Docker Compose: version 1.25.1+
2. Installation steps::
   • Clone the BISHENG code base: bash
git clone https://github.com/dataelement/bisheng.git
cd bisheng/docker

   • If the system does not have the git command, you can download the zip file of the BISHENG code: bash
wget https://github.com/dataelement/bisheng/archive/refs/heads/main.zip
unzip main.zip && cd bisheng-main/docker

   • Start BISHENG: bash
docker-compose up -d

   • After the startup is complete, visit in your browserhttp://IP:3001, go to the login page and register users. By default, the first registered user will be the system administrator.

Function Operation Guide

1. Generative AI workflows::
   • Once in the platform, select the Generative AI Workflow module.
   • Configure workflows based on requirements, including data input, model selection, and output formats.
   • By clicking the "Start" button, the system will automatically execute the workflow and generate the results.
2. Retrieval Augmentation Generation (RAG)::
   • Select the "RAG" module from the main screen.
   • Enter a search keyword or question and the system will retrieve relevant information from the database and generate an answer.
   • Users can adjust the search parameters and generation settings as needed.
3. Intelligent Agents::
   • Select the Intelligent Agent module to configure agent tasks and parameters.
   • The system supports multi-agent collaboration. Users can set multiple agents to work simultaneously to improve efficiency.
   • Upon completion of the agent's task, the system generates a detailed report and analyzes the results.
4. Unified Model Management::
   • Access the Model Management module to view and manage all deployed models.
   • Users can upload new models, update existing models or delete unwanted models.
   • The system provides model evaluation and fine-tuning functions to help users optimize model performance.
5. Highly accurate document parsing::
   • Select the "Document Parsing" module and upload the documents to be parsed.
   • The system supports a wide range of document formats, including PDF, Word, images and more.
   • Once parsing is complete, users can view the parsing results and export them to the desired format.

common problems

• How to update BISHENG?
  • Enter the BISHENG installation directory and execute the following command:

  git pull
  docker-compose down
  docker-compose up -d
  

  • The system will automatically download the latest version and restart.
• How do I deal with problems encountered during installation or use?
  • Users can visit BISHENG's GitHub page for FAQs and community support.
  • You can also join BISHENG's discussion group to exchange experiences and solutions with other users.

The layman's guide to getting started with AI

Help you learn how to utilize AI tools at a low cost and from a zero base.AI, like office software, is an essential skill for everyone. Mastering AI will give you an edge in your job search and half the effort in your future work and studies.

View Details>