a2d7dab296
- docker-compose: 3 services (gateway, mcpo, webui) with proper wiring - Open WebUI connects to Kiro Gateway for LLM, mcpo for MCP tools - TOOL_SERVER_CONNECTIONS auto-discovers Jira, Aha, Context7 - Simplified mcporter.json (env vars from container, not JSON) - env.example consolidated with all keys - SETUP.md rewritten with architecture diagram - Pipelines deprecated (mcpo replaces custom Python shims) - Added docs/reltio-forge.md
80 lines
2.7 KiB
Markdown
80 lines
2.7 KiB
Markdown
# Open WebUI Integration
|
|
|
|
The PM Factory uses Open WebUI as the browser-based frontend for non-technical PMs. It connects to Kiro Gateway for LLM intelligence and mcpo for tool access (Jira, Aha!, Gainsight).
|
|
|
|
## Architecture
|
|
|
|
```
|
|
Browser (PM)
|
|
↕
|
|
Open WebUI (:3000)
|
|
├── LLM → Kiro Gateway (:8000/v1) → Claude/GPT/etc
|
|
└── Tools → mcpo (:3001) → MCP Servers
|
|
├── atlassian (Jira)
|
|
├── aha (Aha! roadmaps)
|
|
└── context7 (docs lookup)
|
|
```
|
|
|
|
## Quick Start
|
|
|
|
```bash
|
|
cp env.example .env # Fill in your API keys
|
|
docker compose up -d
|
|
```
|
|
|
|
Open http://localhost:3000. Log in with the admin email/password from your `.env`.
|
|
|
|
## How It Works
|
|
|
|
1. **Kiro Gateway** provides an OpenAI-compatible `/v1/chat/completions` endpoint. Open WebUI talks to it like any OpenAI provider.
|
|
|
|
2. **mcpo** reads `config/mcporter.json` and exposes each MCP server as an OpenAPI endpoint. Open WebUI discovers tools automatically via `TOOL_SERVER_CONNECTIONS`.
|
|
|
|
3. **No pipelines needed.** The old `pipelines/` directory contained custom Python shims that shelled out to mcporter. With mcpo, Open WebUI calls MCP tools natively through OpenAPI. The pipelines are deprecated.
|
|
|
|
## First-Time Setup
|
|
|
|
### 1. Jira OAuth
|
|
|
|
Atlassian uses OAuth, not API keys. After `docker compose up`:
|
|
|
|
```bash
|
|
docker exec -it pm-mcpo mcporter auth atlassian
|
|
```
|
|
|
|
Follow the browser prompt to authorize. This is a one-time step per machine.
|
|
|
|
### 2. Aha! + Gainsight
|
|
|
|
These use API keys set in `.env`. No extra auth step needed.
|
|
|
|
### 3. Verify Tools
|
|
|
|
Open http://localhost:3001/docs to see all available MCP tools exposed by mcpo. Each server has its own route:
|
|
|
|
- http://localhost:3001/atlassian/docs — Jira tools
|
|
- http://localhost:3001/aha/docs — Aha! tools
|
|
- http://localhost:3001/context7/docs — Documentation lookup
|
|
|
|
In Open WebUI, go to Settings → Tools to confirm all three servers are connected.
|
|
|
|
## Model Preset
|
|
|
|
Import `preset.json` via Workspace → Models → Import. This loads the PM Factory system prompt with Transparent Factory tenets baked in.
|
|
|
|
## Knowledge Base
|
|
|
|
Upload these files as a Knowledge collection in Open WebUI:
|
|
|
|
- `skills/epics-standards/references/` — Epic templates and checklists
|
|
- `skills/gainsight-px/SKILL.md` — Analytics reference
|
|
- `docs/reltio-forge.md` — Reltio Forge velocity standard
|
|
|
|
Then attach the collection to the PM Factory model preset.
|
|
|
|
## Customization
|
|
|
|
- **Add MCP servers:** Edit `config/mcporter.json`, restart mcpo
|
|
- **Change LLM:** Update `OPENAI_API_KEY` and gateway config in `.env`
|
|
- **Custom CSS:** Edit `openwebui/custom.css` (mounted into the container)
|