AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.
Rust agent-memoryai-agentsbm25claude-codeclicode-searchcursordatabaseelasticsearchfull-text-searchhybrid-searchjsonllocal-firstmcpmcp-servermodel-context-protocolragrustsearch-enginevector-search
polish(docs-site): quickstart no longer claims turbo-ingest tokenizes in parallel (#1539)
xerj-org80cba1d4c7b3
diff --git a/landing/docs/quickstart.html b/landing/docs/quickstart.htmlindex 324ca3352..a525bcb54 100644--- a/landing/docs/quickstart.html+++ b/landing/docs/quickstart.html@@ -254,7 +254,7 @@ $ xerj autoindex ~/my-project # picks up XERJ_API_KEY, or take --api-key<}'</pre><h2>3 · Ingest at line rate</h2>- <p>Two ingest paths. <code class="inline">turbo-ingest</code> takes NDJSON and parallel-tokenizes across cores.</p>+ <p>Two ingest paths: the Elasticsearch-compatible <code class="inline">_bulk</code> on port 9200, and the native <code class="inline">turbo-ingest</code> used here, which takes a JSON array of documents and writes each batch to the WAL in one call.</p><pre class="code">$ curl -sX POST http://localhost:8080/v1/indices/logs/turbo-ingest \-H 'Content-Type: application/x-ndjson' \--data-binary @nginx.jsonl</pre>