SC26AI agents lab + dinner on the river · Nov 17
Parallel Works
View as Markdown
Share:

Chat

Chat provides a full-featured chat interface for interacting with large language models directly within ACTIVATE. You can have conversations with AI models from multiple providers, attach files for context, let Chat look up and manage your ACTIVATE resources with tools, branch conversations to explore different approaches, and share conversations with your team.

Feature may not be available on all platforms

Chat requires at least one AI provider to be configured. If you do not see the Chat option in your ACTIVATE account, contact your administrator.

Access Methods

You can interact with Chat in three ways:

  • Web UI: Open AI > Chat in the sidebar navigation to use the full-featured chat interface with file attachments, tools, conversation branching, and message history.
  • CLI: Run pw code for an AI coding agent in your terminal. Unlike Chat, its sessions are stored locally on your machine, not in your account. See pw code.
  • API: Send requests to the OpenAI-compatible API endpoint at /api/openai/v1/chat/completions for programmatic access through the AI gateway. See AI Keys for authentication and model ID format.

Capabilities

  • Multi-provider support: Chat with models from your own providers, providers shared with you, Organization providers, and models served from your own sessions.
  • File attachments: Attach documents and images to your messages for additional context. Each file can be up to 25 MB, with up to 10 files per message.
  • Tools: Chat can look up your clusters, runs, sessions, storage, costs, and allocations while it answers, and can start, stop, or create resources after you allow each change.
  • Conversation branching: Edit previous messages or regenerate responses to create conversation branches. Navigate between alternative replies to compare different approaches.
  • Sharing and collaboration: Share conversations with your organization or with groups for read-only viewing or collaboration.
  • Reasoning models: Use reasoning models and read their thinking process alongside the answer.
  • Streaming responses: Responses stream in real time as the model generates them, so you can read output as it arrives.

Related Documentation