# LLM-Server

Local AI inference stack: llama.cpp (ROCm) serving Qwen3.8-27B on an AMD Radeon AI PRO R9700, fronted by Open WebUI (RAG + Memory via Qdrant), with Lazytainer auto-suspending the inference container when idle.

See the wayfinder map ([issue #1](https://git.arthurerlich.de/haylan/LLM-Server/issues/1)) for the full architecture rationale and open questions.

## Quickstart

```bash
./scripts/download-model.sh
./scripts/update.sh
```

`update.sh` creates `.env` from `.env.example` if missing, fills in every secret and per-workload virtual key it can generate itself (random secrets via `openssl`, `OPENWEBUI_LITELLM_KEY`/`MEMORY_RETRIEVAL_EMBEDDING_KEY` minted through LiteLLM's own `/key/generate` API, `SEARXNG_LAN_IP` resolved from `search.home` on this host), then pulls/builds/brings up the whole stack. Safe to re-run any time — it only fills in what's still blank and only recreates what changed. See [`docs/proxy-key-onboarding.md`](docs/proxy-key-onboarding.md) if a key mint fails and needs doing by hand.

- Open WebUI: `http://<this-machine>:3000` locally, or `ai.home` / `ai.haylan.ch` once routed through Nginx Proxy Manager — see [`docs/network-access.md`](docs/network-access.md). First signup becomes the admin account (`WEBUI_AUTH` is on).
- llama.cpp's own API is internal-only now — everything routes through the AI proxy below.

Pointing Claude Code CLI, Kimi CLI, or OpenCode CLI at the local endpoint: see [`docs/coding-cli-setup.md`](docs/coding-cli-setup.md).

**Known risk**: Qwen3.8-27B's tool-calling reliability against llama.cpp's Anthropic shim is not yet verified (open upstream parser bugs against its model lineage) — see `docs/research/qwen3.8-27b-tool-calling.md`.

## AI proxy (LiteLLM)

An [AI gateway/proxy](https://git.arthurerlich.de/haylan/LLM-Server/issues/9) fronts llama.cpp: per-workload virtual keys, usage tracking, and a shadow cost estimate ("what this would have cost on Claude Sonnet 5"). `./scripts/update.sh` handles `LITELLM_MASTER_KEY`/`LITELLM_SALT_KEY` and every other secret (see `.env.example`).

- Proxy API: `http://<this-machine>:4000/v1` locally, or `proxy.ai.home` / `proxy.ai.haylan.ch` once routed through NPM — see [`docs/network-access.md`](docs/network-access.md).
- Admin UI (`/ui`, key/budget management): LAN-only — see `docs/network-access.md`.
- Issuing a key for a new workload: [`docs/proxy-key-onboarding.md`](docs/proxy-key-onboarding.md).
- Request priority across workloads: [`docs/proxy-request-priority.md`](docs/proxy-request-priority.md).

Open WebUI and the coding CLIs (see [`docs/coding-cli-setup.md`](docs/coding-cli-setup.md)) route through the proxy now — llama-server has no published host port anymore. **Not yet verified**: none of this has been smoke-tested on real hardware (LiteLLM's priority scheduler in particular is beta — see `docs/proxy-request-priority.md`) — see [issue #17](https://git.arthurerlich.de/haylan/LLM-Server/issues/17).

### Web search, knowledgebase, and memory

The gateway also fronts SearXNG-backed web search and a pgvector-backed knowledgebase (loaded with `data/memory.md` / `data/claude-legacy-memory.md`), wired at the LiteLLM layer so every client gets them, not just Open WebUI — see [`docs/memory-knowledgebase.md`](docs/memory-knowledgebase.md). **Not yet verified on real hardware** — see [issue #24](https://git.arthurerlich.de/haylan/LLM-Server/issues/24).