Obsidian
Configure Obsidian for your enterprise and verify the request in your console logs.
Configuration
Use your enterprise HTTPS gateway URL, an API key scoped to this tool and a model ID that supports the protocol. The address below comes from this gateway’s public configuration. Find an eligible model
- Install and enable the Copilot community plugin in Obsidian. Open its BYOK settings and choose Add a Provider → Custom.
- Choose an OpenAI-compatible provider, enter the Base URL and enterprise API key, then add the authorized chat model ID.
- For vault retrieval, configure a separately authorized embedding model and verify /v1/embeddings.
| API protocol | Address to enter |
|---|---|
| Chat Completions | Base URLhttps://tokenpyxis.com/v1 |
Verification
Select the model in the Copilot chat panel and try a message without attachments before testing vault retrieval.
Check the model, timestamp and token usage in the enterprise console logs. If the tool shows a request ID, look it up directly. See reconciliation steps
Troubleshooting
If chat works but indexing fails, check the embedding model and its permissions. For a cross-origin error, check the plugin’s connection mode and the gateway’s origin settings.
