Skip to content

armgit / xerj

Public Imported from GitHub
0

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.

polish(docs-site): drop stale 'kNN serving is exact' from the hnsw_m example (#1536)

xerj-org5915bbb6eb6b
diff --git a/landing/docs/config.html b/landing/docs/config.html
index 33bd8f31f..d7f4d3cc2 100644
--- a/landing/docs/config.html
+++ b/landing/docs/config.html
@@ -294,7 +294,7 @@ default_analyzer = "standard" # accepted, not wired — see the table</pre>
<p>Vector search settings. Unfiltered kNN is served by a <strong>persisted HNSW graph with exact rescoring</strong> (measured recall@10 1.00 on the official bench query); filtered kNN and SQ8 fields run the exact scan. The <code class="inline">hnsw_*</code> keys are accepted and validated but not yet wired: the graph builds with fixed M=16 / ef_construction=200, and the query-time beam width comes from the request's <code class="inline">num_candidates</code> (floored at 800). Quantization trades recall for scoring precision, not for memory — see <code class="inline">default_quantization</code> below and <a href="https://github.com/xerj-org/xerj/issues/392">#392</a>.</p>
<pre class="code">[vector]
default_metric = "cosine" # accepted, not wired — similarity comes from the mapping
-hnsw_m = 16 # accepted for compat; kNN serving is exact
+hnsw_m = 16 # accepted, not wired — the graph builds with M=16
hnsw_ef_construction = 200 # accepted for compat; no effect on results
hnsw_ef_search = 100 # accepted for compat; no effect on results
default_quantization = "none" # "scalar8" = int8 precision, 1–2% recall loss.