URL: chat.ai.college.ucsb.edu
Sign in: UCSB NetID
The model selector is to the right of the message box, on the same row as the microphone. Click the current model's name to open the list. Three flagship models are available:
| Model | When to use it |
|---|---|
| gemma-4-26b-a4b-it | General-purpose work: writing, summarization, brainstorming, email drafting, multi-turn conversation, and image input. Fastest. |
| qwen3.8-27b | STEM and research tasks, very long documents, and code — generation, debugging, review, and technical explanations. |
| gpt-oss-120b | Deep, multi-step reasoning, research synthesis, or any task where you need maximum model capacity and nuanced analysis. |
You can switch models at any point. Each conversation keeps its own model selection. See Choosing the Right Model for more detail.
A note on model size: These are capable open-weight models, but they are smaller than commercial frontier models. See Getting Better Results from Open-Weight Models for tips on getting the most out of them.
Web search is enabled by default. When active, Open WebUI uses an external search engine to retrieve current information and include it with your query.
Click the globe icon in the message input bar (to the left of where you type) to toggle web search for the current conversation. A highlighted icon means search is active.
Data reminder: When web search is enabled, your query is sent to an external search engine. Avoid sensitive or restricted information in search-enabled conversations.
A system prompt is a persistent instruction that shapes every response in a conversation. It's sent to the model before any user message — think of it as setting the model's role, tone, and constraints for the session.
Click the sliders icon in the top-right corner of the window (its tooltip says Controls). The System Prompt field is at the top of the Controls panel. Your instructions take effect on your next message and apply to the current conversation only.
To reuse a prompt, copy it into new conversations as needed, or save it as a Preset (see below).
Good system prompts are specific, concise, and task-oriented. They work best when they define:
Examples:
You are a Python code reviewer. When given code, identify bugs, suggest improvements,
and explain your reasoning. Always include a corrected version of the code.
You are a research assistant for a marine biology lab. Summarize papers clearly
for a non-specialist audience. Use plain language. Avoid jargon unless defined.
You are a writing editor. Review text for clarity, conciseness, and tone.
Return a revised version followed by a brief explanation of the changes made.
Keep responses under 500 words unless the input is very long.
Open WebUI allows you to save system prompts as named presets for reuse. Go to Settings → Presets to create and manage them. Presets can be loaded at the start of any new conversation.
| Focused Retrieval (default) | Full Context | |
|---|---|---|
| How it works | RAG — finds and injects the most relevant chunks based on your query | Injects the entire file into every message, no chunking |
| Best for | Large documents, knowledge bases, multi-file collections | Short files, style guides, files where all content matters |
| Context usage | Low — only top-k chunks | High — entire file every message |
| Risk | May miss content not ranked relevant | Can exceed context window on large files |
If you don't see the toggle, your Open WebUI version may label it differently or place it under a file options menu.
Full Context mode injects the entire file on every message. Before switching:
gemma-4-26b-a4b-it and qwen3.8-27b, 128k tokens for gpt-oss-120b.For files that exceed any model's context window, use a map-reduce approach: summarize in chunks, then combine the partial summaries.
Some models use native function calling, in which case attached knowledge is not injected automatically — the model must call retrieval tools to access it. If the model ignores your attached files:
list_knowledge and query_knowledge_files, or