Customizing for Your Use Case

Configure Supermemory’s behavior for your specific application

Configure how Supermemory processes and retrieves content for your specific use case.

Filter Prompts

Tell Supermemory what content matters during ingestion. This helps filter and prioritize what gets indexed.

// Example: Brand guidelines assistant
await client.settings.update({
  shouldLLMFilter: true,
  filterPrompt: `You are ingesting content for Brand.ai's brand guidelines system.

    Index:
    - Official brand values and mission statements
    - Approved tone of voice guidelines
    - Logo usage and visual identity docs
    - Approved messaging and taglines

    Skip:
    - Draft documents and work-in-progress
    - Outdated brand materials (pre-2024)
    - Internal discussions about brand changes
    - Competitor analysis docs`
});

Personal Assistant

filterPrompt: `Personal AI assistant. Prioritize recent content, action items,
and personal context. Exclude spam and duplicates.`

Customer Support

filterPrompt: `Customer support agent. Prioritize verified solutions, official docs,
and resolved tickets. Exclude internal discussions and PII.`

Legal Assistant

filterPrompt: `Legal research assistant. Prioritize precedents, current regulations,
and approved contract language. Exclude privileged communications.`

Finance Agent

filterPrompt: `Financial analysis assistant. Prioritize latest reports, verified data,
and regulatory filings. Exclude speculative data and MNPI.`

Healthcare

filterPrompt: `Healthcare information assistant. Prioritize evidence-based guidelines
and FDA-approved info. Exclude PHI and outdated recommendations.`

Developer Docs

filterPrompt: `Developer documentation assistant. Prioritize current APIs, working
examples, and best practices. Exclude deprecated APIs and test fixtures.`

---

Chunk Size

Control how documents are split into searchable pieces. Smaller chunks = more precise retrieval but less context per result.

await client.settings.update({
  chunkSize: 512  // -1 for default
});

Use Case	Chunk Size	Why
Citations & references	256-512	Precise source attribution
Q&A / Support	512-1024	Balanced context
Long-form analysis	1024-2048	More context per chunk
Default	-1	Supermemory’s optimized default

Smaller chunks generate more memories per document. Larger chunks provide more context but may reduce precision.

---

Connector Branding

Show “Log in to YourApp” instead of “Log in to Supermemory” when users connect external services.

Google Drive

1. Create OAuth credentials in Google Cloud Console
2. Redirect URI: https://api.supermemory.ai/v3/connections/google-drive/callback

await client.settings.update({
  googleDriveCustomKeyEnabled: true,
  googleDriveClientId: "your-client-id.apps.googleusercontent.com",
  googleDriveClientSecret: "your-client-secret"
});

Notion

1. Create integration at Notion Developers
2. Redirect URI: https://api.supermemory.ai/v3/connections/notion/callback

await client.settings.update({
  notionCustomKeyEnabled: true,
  notionClientId: "your-notion-client-id",
  notionClientSecret: "your-notion-client-secret"
});

OneDrive

1. Register app in Azure Portal
2. Redirect URI: https://api.supermemory.ai/v3/connections/onedrive/callback

await client.settings.update({
  onedriveCustomKeyEnabled: true,
  onedriveClientId: "your-azure-app-id",
  onedriveClientSecret: "your-azure-client-secret"
});

---

API Reference

// Get current settings
const settings = await client.settings.get();

// Update settings
await client.settings.update({
  shouldLLMFilter: true,
  filterPrompt: "...",
  chunkSize: 512
});

Settings are organization-wide. Changes apply to new content only—existing memories aren’t reprocessed.