Wiring Page Assist to Ollama and a Cloud Gateway: Setup, Four Workflows, and the Gotchas

Description and use

Page Assist streamlines LLM interactions by consolidating copy‑paste into a sidebar. Configuring local Ollama or cloud AIHubMix, selecting an embedding model, and leveraging four workflows enable quick long‑page summarization, text rewriting, knowledge‑base queries, and automated page actions.

Problem

Copying text from a web page into a chat interface is tedious; Page Assist consolidates this into a sidebar or full‑tab UI, but requires local or cloud model configuration and embedding setup.

Outcome

Page Assist becomes a fully functional LLM‑powered assistant with local or cloud models, supporting long‑page summarization, text rewriting, knowledge base queries, and automated page actions.

Workflow

• Start Ollama on default port and open Page Assist
• If 403 CORS error, set OLLAMA_ORIGINS="*" or enable custom origin URL in settings
• Add AIHubMix from preset list: Settings → OpenAI Compatible API → Add Provider, select AIHubMix, paste API key, save
• Select chat models in Model List dialog, tick chat models, set type to Chat Model, save
• Choose an embedding model: Settings → RAG Settings → Embedding Model, tick an embedding model such as gemini-embedding-001, set type to Embedding Model, save
• Use the four workflows: 1) Chat with Website (choose embedding or full context), 2) Copilot right‑click prompts (custom templates), 3) Knowledge Base (add PDFs, docs, etc.), 4) Page Action/MCP (configure remote server or local MCP)

Evidence

Page Assist collapses that loop into a sidebar (Ctrl+Shift+Y) and a full-tab web UI (Ctrl+Shift+L).

Source

If you get a 403 on send, it's CORS. Page Assist rewrites headers automatically only for http://127.0.0.1:* and http://localhost:*.

Source

AIHubMix returns chat and embedding models in the same /models list.

Source