{% extends "admin/_layout.html" %} {% from "_macros.html" import icon %} {% set section = "connections" %} {% block title %}Connections - LLeMbas{% endblock %} {% block heading %}Connections{% endblock %} {% block admin_content %}

Any endpoint that speaks the OpenAI HTTP API: OpenAI itself, or a local runner such as LM Studio, vLLM, llama.cpp or Ollama. LLeMbas asks each one for its model list and offers those models in the chat picker.

{% if message %}
{{ message }}
{% endif %}

Add a connection

With or without the trailing /v1 — both are accepted.

Encrypted before it is stored, and never sent back to the browser. Leave empty for endpoints that need no key.

Configured connections {{ connections|length }}

{% if not connections %}
{{ icon("server", "empty__mark") }}

Nothing configured yet. Add a connection above and its models appear here.

{% endif %}
{% for connection in connections %} {% with masked = masked[connection.id], model_count = model_counts[connection.id] %} {% include "admin/_connection_row.html" %} {% endwith %} {% endfor %}
{% endblock %}