[Webcrawler] Avoid null bytes in tags (#8993)

Description --- Fixes issue from [thread](https://dust4ai.slack.com/archives/C05F84CFP0E/p1732793680391139) (in addition to PR #8869) Risks --- na Deploy --- connectors
dust-tt · Nov 28, 2024 · bae9884 · bae9884
1 parent 29b3891
commit bae9884
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/connectors/src/connectors/webcrawler/temporal/activities.ts b/connectors/src/connectors/webcrawler/temporal/activities.ts
@@ -327,7 +327,7 @@ export async function crawlWebsiteByConnectorId(connectorId: ModelId) {
               }),
               documentUrl: request.url,
               timestampMs: new Date().getTime(),
-              tags: [`title:${pageTitle}`],
+              tags: [`title:${stripNullBytes(pageTitle)}`],
               parents: getParentsForPage(request.url, false),
               upsertContext: {
                 sync_type: "batch",