Skip to content
TrustedRails

Connect Open WebUI to TrustedRails

Open WebUI is a self-hosted, ChatGPT-style web interface for running models. It has built-in support for OpenAI-compatible endpoints, so you can add TrustedRails as a connection and chat with open-source models, with no plugin required.

Prerequisites

Section titled “Prerequisites”

Add TrustedRails as an OpenAI connection

Section titled “Add TrustedRails as an OpenAI connection”

The first account you create in Open WebUI is the workspace admin. As that admin:

  1. Click your avatar (bottom-left) → Admin Panel, then open Settings → Connections.
  2. In the OpenAI API section, click Manage OpenAI API Connections, then the + (Add Connection).
  3. Fill in:
    • API Base URL: https://proxy.trustedrails.com/v1
    • API Key: your TrustedRails key (tr-prx-…)
    • Leave Prefix ID blank.
  4. Click Verify Connection; a success message means Open WebUI reached TrustedRails and fetched the model list.
  5. Save.

The models TrustedRails serves are now available to everyone in the workspace.

To connect just your own account instead of the whole workspace, add the same API Base URL and API Key under Settings → Connections → Direct Connections; no admin access needed.

Pick a model

Section titled “Pick a model”

Start a new chat and open the model selector at the top. TrustedRails's models, fetched from /v1/models, appear in the list. Pick MiniMaxAI/MiniMax-M2.7 (recommended) or zai-org/GLM-5.3-Flash (see Supported Models).

Embeddings for document RAG

Section titled “Embeddings for document RAG”

Open WebUI embeds your uploaded documents and knowledge bases locally by default, on the machine it runs on. You can offload that to TrustedRails's embedding model instead (see Embeddings & RAG):

  1. Open Admin Panel → Settings → Documents.
  2. Set Embedding Model Engine to OpenAI and fill in the fields that appear:
    • API Base URL: https://proxy.trustedrails.com/v1
    • API Key: your TrustedRails key
  3. Set Embedding Model to BAAI/bge-m3 (type it in; this field is not a dropdown).
  4. Optionally raise Embedding Batch Size to speed up indexing of large documents.
  5. Save.

From now on, documents you upload to chats and knowledge bases, and your RAG queries against them, are embedded through TrustedRails.

Switch the engine before uploading your documents: vectors from different embedding models don't mix. If you change it later, re-index existing collections with Reindex Knowledge Base Vectors (bottom of the same Documents page).

Verify

Section titled “Verify”

Send a message in the chat. A reply confirms Open WebUI is reaching TrustedRails through your key.

To check the RAG path, upload a small text file to a chat and ask about its contents; an answer grounded in the file confirms documents are embedded through TrustedRails.

Troubleshooting

Section titled “Troubleshooting”
  • No models in the selector: re-open Admin Panel → Settings → Connections, click Verify Connection, and confirm the API Base URL is https://proxy.trustedrails.com/v1 and the connection is enabled.
  • 401 / invalid API key: wrong or paused key. Create a fresh one from Create a TrustedRails API Key.
  • Document upload fails after switching the embedding engine: the Embedding Model must be exactly BAAI/bge-m3; a chat model or a typo fails at indexing time. Also re-index old collections after any engine/model change (Reindex Knowledge Base Vectors).