NeuCharFramework (NCF)
  • NCF - NeuCharFramework
  • Projects

    • Preparation
    • NcfPackageSources Source Guide
    • DynamicWebApiEngine
    • Deployment
    • MCP (Model Context Protocol) Module
    • Senparc.AI
  • AIKernel Local Fine-Tuning
  • Help

    • Online Resources
    • Q&A Community
    • QQ Group (147054579)
    • Senparc WeChat SDK
  • Gitee
  • GitHub
  • English
  • 简体中文
GitHub
  • NCF - NeuCharFramework
  • Projects

    • Preparation
    • NcfPackageSources Source Guide
    • DynamicWebApiEngine
    • Deployment
    • MCP (Model Context Protocol) Module
    • Senparc.AI
  • AIKernel Local Fine-Tuning
  • Help

    • Online Resources
    • Q&A Community
    • QQ Group (147054579)
    • Senparc WeChat SDK
  • Gitee
  • GitHub
  • English
  • 简体中文
GitHub
  • Source Development

    • NcfPackageSources Beginner Quickstart (60 Minutes)
    • NcfPackageSources Source Guide
    • Project Relationships, Synchronization, and Release
    • Version Upgrade Notes
    • NcfPackageSources_Include_NcfSimulatedSite.sln Project Map
  • XNCF Source Analysis

    • NCF Capability Source Deep Dive (Practical)
    • XNCF Extension Library Guide (Senparc.Xncf.xxx)
    • XNCF Module Documentation Map
    • Senparc.Web and Admin
    • XncfBuilder Isolated Development: Source Analysis
  • Admin Feature Guides

    • Admin help directory and short notes
    • Admin logs and diagnostics
    • AdminChat conversations, Harness and attachments
    • AdminChat Memory and Conversation Settings
    • NeuBell outbound WebHook management
    • NeuCharPivot boards, aggregation and access
    • MCP Manager: published services and client connections
    • AIKernel models, vectors and usage
    • AIKernel Local Fine-Tuning
    • KnowledgeBase ingestion and recall tests
    • PromptRange ranges, testing and model settings
    • Skill import, testing and publication
    • FileManager assets and upload policies
    • AgentsManager agent management
    • AgentsManager 3D Status View
    • AgentsManager: HIL and NeuChar Workflow Integration
    • NeuChar Workflow: Operations and {{= ... }} Expressions
    • Workspace and AdminChat
    • Sandbox session management and environment setup
    • DynamicData tables, layouts and pages
    • SenMapic crawl tasks and results
    • Weixin official accounts and followers
    • Personal Weixin Bot and Admin integration
  • NCF Library Source Analysis

    • Senparc.Ncf.Core
    • Senparc.Ncf.Database (Database Foundation)
    • Senparc.Ncf.Repository
    • Senparc.Ncf.Service
    • Senparc.Ncf.SMS
    • Senparc.Ncf.Mvc.UI
    • Senparc.Ncf.Log
    • Senparc.Ncf.Utility
    • Senparc.Ncf.XncfBase
    • Senparc.Ncf.AreaBase
    • Senparc.Ncf.DatabasePlant
  • Core Interface Source Analysis

    • IXncfRegister Interface (Current)

PromptRange ranges, testing and model settings

PromptRange dashboard

Home shows update time, overview cards, usage trends, model distribution, top Prompts, range health and risk indicators. Refresh reloads statistics; Workbench opens editing/testing. Popular-item links select the relevant range or lane. The dashboard is not an editor. Average score, usage count and health have different definitions; missing data is neither a perfect score nor proof of no provider charges.

Prompt workbench

Select a range, lane and model; edit the prompt and request parameters, run a test, then inspect results, scores and versions. Model capabilities determine text/image/audio input and output regions; text-generation settings do not apply to every model. Optimization, mind maps, agent creation and plugins import/export are separate actions, not saving the current test result. The Select range help explains range/lane management only; model configuration has its own section below.

Selecting ranges and lanes

This help belongs to the top-left selection area. Select or create a range first, then select its lane. Lane selection is unavailable without a range. Dropdown actions rename/delete objects; lanes also offer comparison and setting/resetting names. Check unsaved edits before switching and compare versions before overwriting or deleting. Nearby plugins import/export handles plugin data; it is not a backup of all system configuration.

PromptRange model settings

Configure the models used for prompt testing and evaluation, then verify the selected model in the prompt page. Distinguish model configuration from the prompt text and from knowledge-base embeddings. Model access and credentials still depend on the configured provider.

AdminChat system prompt range

AdminChat's built-in default SystemMessage is stored as the AdminChat.SystemMessage PromptRange. The range is initialized on first use, and the selected published version is the highest-scoring current version. Use the AdminChat settings link to open the range editor, then publish and score versions there. This default prompt is separate from each user's personal or tenant-wide SystemMessage.

Edit this page on GitHub
Last Updated:
Contributors: JeffreySu
Prev
KnowledgeBase ingestion and recall tests
Next
Skill import, testing and publication