Add URL and content ingestion (Milestone 6)

- Add URL fetching with HTML-to-text extraction
- Add basic PDF text extraction
- Add smart content chunking with overlap
- Add deduplication via content checksums
- Add auto-linking to semantically related nodes
- Add CLI commands: ingest, clip
- Add MCP tools: memory_ingest, memory_clip
This commit is contained in:
2026-02-03 11:00:28 +01:00
parent 67b1e3b481
commit c65a5bb03a
6 changed files with 655 additions and 0 deletions

View File

@@ -18,6 +18,7 @@ import { captureCommand, captureHookCommand, configCommand } from './commands/ca
import { contextCommand, contextHookCommand } from './commands/context';
import { indexCommand } from './commands/index-cmd';
import { journalCommand, journalAliasCommand, quickCaptureCommand } from './commands/journal';
import { ingestCommand, clipCommand } from './commands/ingest';
import { closeDb } from '../core/db';
const program = new Command();
@@ -50,6 +51,8 @@ program.addCommand(indexCommand);
program.addCommand(journalCommand);
program.addCommand(journalAliasCommand);
program.addCommand(quickCaptureCommand);
program.addCommand(ingestCommand);
program.addCommand(clipCommand);
program.hook('postAction', () => {
closeDb();