Update stack docs: add Member Portal + SearXNG, document web search + RAG status

README.md

@@ -29,8 +29,10 @@ The Inference Cooperative runs a self-hosted stack on [Cloudron](https://cloudro
 
 | Component | Purpose | URL |
 |-----------|---------|-----|
-| **LibreChat** | Member-facing chat interface | chat.inference.coop |
+| **LibreChat** | Member-facing chat interface (with web search) | chat.inference.coop |
 | **LiteLLM** | AI gateway — keys, metering, model routing | gateway.inference.coop |
+| **Member Portal** | Membership middleware — onboarding, key provisioning, Loomio sync | portal.inference.coop |
+| **SearXNG** | Self-hosted web search (feeds LibreChat's search tool) | search.inference.coop |
 | **Gitea** | Git hosting (code + docs) | git.inference.coop |
 | **Loomio** | Member governance | forum.inference.coop |
 | **Open Collective** | Membership billing + fiscal sponsorship | opencollective.com/inference-cooperative |
@@ -44,6 +46,11 @@ The gateway currently exposes two models:
 - **DeepSeek V4 Flash** — default model, best for agentic tasks
 - **GPT-OSS 120B** — lightweight fallback
 
+### Features
+
+- **Web search** — LibreChat's search tool is pinned by default, backed by a self-hosted SearXNG instance (no external search API).
+- **File uploads (RAG)** — planned; requires an embedding model (not yet available on the current backend).
+
 ### Privacy
 
 Privacy is a core value. The current LLM backend (Ollama Cloud) is a policy-based privacy model. The roadmap is to move to [TEE-protected inference (via Tinfoil)](https://tinfoil.sh/inference), which provides architectural—not just policy—privacy guarantees.