Keywords: Python, FastAPI, LLM, Entity Resolution, Excel Automation, Composable Pipeline, Database Normalization.
Composable pipeline engine: web research, LLM reasoning, and intelligent ranking — with or without a term database
Type in Excel, get results in real-time. Works standalone or with a term database.
- Installation Guide - Setup for end users and IT admins
- Setup Guide - How to use the add-in
- Developer Guide - Modify the codebase, VS Code setup
- Troubleshooting - Common issues & solutions
- Pipeline Composability Spec - Cross-repo pipeline interface (nodes, pipelines, discovery)
The backend exposes processing steps as a JSON contract (GET /pipeline) — nodes with typed configs, named pipelines, and tunable parameters. Already consumed by the frontend and by PromptPotter for automated parameter sweeps.
Only fuzzy_matching and token_matching require a session (indexed terms). Research nodes (web_search, entity_profiling, llm_ranking, llm_only) work session-free — compose any query-in, structured-answer-out pipeline from available nodes.
- Session-free research - Web search + entity profiling + LLM ranking on any query
- Database identifier assignment - Match free-form names to standardized identifiers (requires session)
- Classification & entity linking - Assign categories, normalize product names, material codes
Built for scale: Tested against 11,750+ database identifiers with expert-level disambiguation for Life Cycle Assessment (LCA) workflows.
- Zero-Click Setup - Drop config file, start working immediately
- Transparent Decisions - Ranked candidates with confidence scores, sources, and full audit trail
- Direct Prompt - Custom LLM queries with fuzzy validation against your terms
- Visual Feedback - Color-coded cells show match quality at a glance
- Multi-User Ready - IP-based auth with hot-reload
- Microsoft Excel (Desktop or Microsoft 365)
- Python 3.9+ (for backend server)
- LLM API key (Groq recommended, OpenAI supported)
👉 Download from GitHub Releases
Download termnorm-deploy-vX.X.X.zip - contains everything you need:
- ✅ Pre-built frontend (
dist/) - ✅ Python backend (
backend-api/) - ✅ Manifest files
- ✅ Configuration templates
Setup:
- Extract to your desired location (e.g.,
C:\TermNorm-excel\) - Run
start-server-py-LLMs.batto start the backend - Install the add-in:
- Microsoft 365: Upload
manifest-cloud.xmlvia Home → Add-ins → Upload My Add-in - Desktop Excel: Requires network deployment - see Installation Guide
- Microsoft 365: Upload
Manual backend setup (alternative)
cd backend-api
python -m venv .venv
.\.venv\Scripts\activate
pip install -r requirements.txt
setx GROQ_API_KEY "your_api_key_here"
python -m uvicorn main:app --reloadDesktop Excel cannot use the simple cloud upload method. Instead, it requires hosting the add-in on an internal web server (IIS) and distributing the manifest via network shared folder. Users then configure their Trust Center to access the shared catalog.
This process involves:
- Extracting the release package (
termnorm-deploy-v1.xx.xx.zip) - Deploying to IIS (Windows Server)
- Setting up network share for manifest distribution
- Configuring Trust Center on each user's Excel
📖 Complete deployment guide with step-by-step instructions
Composable pipeline engine with an Excel frontend. Nodes compose into named pipelines — see Pipeline Composability for session requirements.
Want to modify this codebase? Check out the comprehensive developer guide:
Covers:
- ✅ VS Code Office Add-ins Developer Kit setup
- ✅ Full installation from source (git clone or download)
- ✅ Frontend development (UI customization)
- ✅ Backend development (Python server)
- ✅ Building and deployment
- ✅ Pipeline configuration (
GET /pipeline) with nodes, named pipelines, and tunable parameters - ✅ Debugging tips and best practices
Learn Excel Add-ins:
git clone https://github.com/runfish5/TermNorm-excel.git
cd TermNorm-excel
npm install # Downloads ~900MB to node_modules/ (required for development)
npm run dev-server # Frontend dev server
# Open another terminal
cd backend-api
python -m venv .venv && .\.venv\Scripts\activate
pip install -r requirements.txt
python -m uvicorn main:app --reload # Backend serverPress F5 in VS Code with Office Add-ins Developer Kit to start debugging in Excel!
Note: The ~1GB local directory size (mostly node_modules/) is normal for development. End users who download the deployment package don't need any of this.