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!
fastgpt.mp4
-
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
- Tracking source file references
- Custom file reader
- Modules are packaged into plug-ins to achieve reuse
-
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
-
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
-
OpenAPI
- completions interface (aligned with GPT interface)
- Knowledge base CRUD
-
Operational functions
- Login-free sharing window
- One-click embedding with Iframe
- Unified access to dialogue records
Project tech stack: NextJs + TS + ChakraUI + Mongo + Postgres (Vector plugin)
-
⚡ Deployment
Give it a 2-4 minute wait after deployment as it sets up the database. Initially, it might be a tad slow since we're using the basic settings.
- FastGPT FAQ
- Docker Deployment Tutorial Video
- Official Account Integration Video Tutorial
- FastGPT Knowledge Base Demo
- Laf: 3-minute quick access to third-party applications
- Sealos: Rapid deployment of cluster applications
- One API: Multi-model management, supports Azure, Wenxin Yiyuan, etc.
- TuShan: Build a backend management system in 5 minutes