Update README.md

Signed-off-by: ION606 <ion606@protonmail.com>
This commit is contained in:
2025-09-10 21:50:19 -04:00
parent 96938f4b18
commit 06790d74d9
+4 -4
View File
@@ -55,7 +55,7 @@ This repository wires together a local AI stack built around **Open WebUI**, **O
* **what it is:** a small HTTP server (Bun runtime) that executes pure source code in short-lived, sandboxed containers.
* **why it exists:** lets Open WebUI tools run code safely with tight resource limits (no network, read-only fs, cgroup limits, `--cap-drop=ALL`, `no-new-privileges`).
* **integration contract:** exposes an **OpenAPI schema at `/openapi.json`** and a single POST `/execute` endpoint. Open WebUI can import this as a **tool server**.
* **security posture:** pulls allow-listed base images (gcc, python, node, bun, etc.), mounts only a tmpfs workdir, times out jobs ≈25s, and runs with non-root uid/gid. the container has access to the hosts docker socket *only* to run the sandbox containers.
* **security posture:** pulls allow-listed base images (gcc, python, node, bun, etc.), mounts only a tmpfs workdir, times out jobs ≈25s, and runs with non-root uid/gid. The container has access to the hosts docker socket *only* to run the sandbox containers.
### Browser-use web-ui (`browser/`)
@@ -64,13 +64,13 @@ This repository wires together a local AI stack built around **Open WebUI**, **O
### Cloudflared tunnel (`cloudflared-tunnel-config.yml`)
* maps hostnames (like `mlep.domain.com` for Ollama, `owebui.domain.com` for Open WebUI, and a `tools` host) to the internal services. useful for private, authenticated access without public inbound ports.
* maps hostnames (like `mlep.domain.com` for Ollama, `owebui.domain.com` for Open WebUI, and a `tools` host) to the internal services. Useful for private, authenticated access without public inbound ports.
---
## Why you currently **dont** need an external RAG server
## Why I currently **dont** use an external RAG server
Open WebUI ships with first-class **knowledge / RAG** support: add files/URLs, it chunks + embeds, indexes, retrieves, and automatically **prefixes retrieved context** to the model prompt using a RAG template. for lightweight to mid-sized corpora and single-user/small-team usage, thats often all you need.
Open WebUI ships with pretty good **knowledge / RAG** support: add files/URLs, it chunks + embeds, indexes, retrieves, and automatically **prefixes retrieved context** to the model prompt using a RAG template. For lightweight to mid-sized corpora and single-user/small-team usage, thats often all you need.
**Stay with built-in RAG if most of these are true:**