FastGPT is a knowledge-based platform built on the LLM, offers out-of-the-box data processing and model invocation capabilities, allows for workflow orchestration through Flow visualization!
Go to file
Archer ad7a17bf40
Optimize the project structure and introduce DDD design (#394)
2023-10-12 17:46:37 +08:00
.github Docs: update workflow for building docs image (#384) 2023-10-09 14:32:47 +08:00
.husky perf: ui 2023-06-10 14:01:35 +08:00
.vscode Optimize the file storage structure of the knowledge base (#386) 2023-10-10 22:41:05 +08:00
docSite Optimize the project structure and introduce DDD design (#394) 2023-10-12 17:46:37 +08:00
files perf: markdown more wrap (#365) 2023-10-02 20:19:09 +08:00
packages v4.4.7-2 (#388) 2023-10-11 17:18:43 +08:00
projects/app Optimize the project structure and introduce DDD design (#394) 2023-10-12 17:46:37 +08:00
.dockerignore monorepo packages (#344) 2023-09-24 18:02:09 +08:00
.gitignore Docs: update theme (#368) 2023-10-04 22:25:07 +08:00
.prettierignore doc favicon 2023-09-04 19:45:24 +08:00
.prettierrc.js README 2023-03-28 00:48:24 +08:00
Dockerfile v4.4.5-3 (#357) 2023-09-26 21:17:13 +08:00
LICENSE licence 2023-08-11 22:03:29 +08:00
README.md README (#372) 2023-10-06 21:19:44 +08:00
README_en.md README (#372) 2023-10-06 21:19:44 +08:00
package.json perf: v4.4.6-1 (#364) 2023-09-28 17:30:05 +08:00
pnpm-lock.yaml v4.4.7-2 (#388) 2023-10-11 17:18:43 +08:00
pnpm-workspace.yaml monorepo packages (#344) 2023-09-24 18:02:09 +08:00
shdemo.sh Optimize the file storage structure of the knowledge base (#386) 2023-10-10 22:41:05 +08:00

fastgpt logo

FastGPT

English | 简体中文

FastGPT is a knowledge-based Q&A system built on the LLM, offers out-of-the-box data processing and model invocation capabilities, allows for workflow orchestration through Flow visualization!

cloud document development project license

https://github.com/labring/FastGPT/assets/15308462/7d3a38df-eb0e-4388-9250-2409bd33f6d4

🛸 Use Cloud Services

fastgpt.run

Demo Demo
Demo Demo

💡 Features

  1. Powerful visual workflows: Effortlessly craft AI applications

    • Simple mode on deck - no need for manual arrangement
    • User dialogue pre-guidance
    • Global variables
    • Knowledge base search
    • Dialogue via multiple LLM models
    • Text magic - convert to structured data
    • Extend with HTTP
    • Embed Laf for on-the-fly HTTP module crafting
    • Directions for the next dialogue steps
    • Multiple dialogue paths selection
    • Tracking source file references
    • Custom file reader
  2. Extensive knowledge base preprocessing

    • Reuse and mix multiple knowledge bases
    • Track chunk modifications and deletions
    • Supports manual entries, direct segmentation, and QA split imports
    • Supports URL fetching and batch CSV imports
    • Supports Set unique vector models for knowledge bases
    • Store original files
    • File learning Agent
  3. Multiple effect testing channels

    • Single-point knowledge base search test
    • Feedback references and ability to modify and delete during dialogue
    • Complete context presentation
    • Complete module intermediate value presentation
  4. OpenAPI

    • completions interface (aligned with GPT interface)
    • Knowledge base CRUD
  5. Operational functions

    • Login-free sharing window
    • One-click embedding with Iframe
    • Unified access to dialogue records

👨‍💻 Development

Project tech stack: NextJs + TS + ChakraUI + Mongo + Postgres (Vector plugin)

👀 Others

🤝 Third-party Ecosystem

🌟 Star History

Star History Chart