docs: rewrite README with banner, story diagrams + screenshots; harden ingest source-fetch retry

- New README: generated banner, how-it-works + vs-RAG story SVGs, install/terminal
  and dashboard screenshots, Docker quick-start, BYOK, API, SDK, benchmark sections.
- Widen getSourceWithRetry window (~16s) so large sources survive heavy concurrent
  ingestion; UI Ask falls back to the server key when no BYOK key is set.

Author: hallelx2

README.md

@@ -375,14 +375,21 @@ <h3>Model & API key</h3>
 document.getElementById("q").addEventListener("keydown",e=>{ if((e.metaKey||e.ctrlKey)&&e.key==="Enter") ask(); });
 async function ask(){
   if(!activeDoc) return; const q=document.getElementById("q").value.trim(); if(!q) return;
-  if(!getSettings().apiKey){ openSettings(); document.getElementById("setStatus").innerHTML='<span style="color:var(--warn)">Set an API key to ask questions.</span>'; return; }
   const out=document.getElementById("result"), btn=document.getElementById("ask"); btn.disabled=true; pdfDoc=null;
   out.innerHTML=`<div class="res card" style="margin-top:16px"><div class="body"><span class="spin"></span><span class="askhint">Navigating the document…</span></div></div>`;
   const t0=performance.now();
   try{
     const r=await fetch(E("/v1/answer/treewalk"),{method:"POST",headers:{"Content-Type":"application/json",...llmHeaders()},body:JSON.stringify({document_id:activeDoc.id,query:q})});
     const d=await r.json();
-    if(!r.ok){ out.innerHTML=`<div class="res card"><div class="body err">Error: ${esc(d.error||JSON.stringify(d))}</div></div>`; return; }
+    if(!r.ok){
+      const msg=d.error||JSON.stringify(d);
+      if(/no LLM credentials|X-LLM-Api-Key/i.test(msg)){
+        out.innerHTML=""; openSettings();
+        document.getElementById("setStatus").innerHTML='<span style="color:var(--warn)">Set your API key to ask questions.</span>';
+        return;
+      }
+      out.innerHTML=`<div class="res card"><div class="body err">Error: ${esc(msg)}</div></div>`; return;
+    }
     renderResult(d,Math.round(performance.now()-t0));
   }catch(e){ out.innerHTML=`<div class="res card"><div class="body err">${esc(String(e))}</div></div>`; }
   finally{ btn.disabled=false; }

docs/images/banner.png

@@ -556,7 +556,11 @@ func (p *Pipeline) parse(ctx context.Context, parsers *parser.Registry, pl Paylo
 // retried with short backoff rather than failing the whole document.
 // Any non-ErrNotFound error returns immediately.
 func getSourceWithRetry(ctx context.Context, s storage.Storage, key string) (io.ReadCloser, storage.Metadata, error) {
-	const attempts = 6
+	// Up to ~16s of incremental backoff. A large source (multi-MB) written
+	// under heavy concurrent ingestion on a busy/low-disk filesystem can take
+	// several seconds to become visible to this worker; a too-short window
+	// turns that transient into a hard "object not found" failure.
+	const attempts = 16
 	var lastErr error
 	for i := 0; i < attempts; i++ {
 		rc, meta, err := s.Get(ctx, key)
@@ -570,7 +574,7 @@ func getSourceWithRetry(ctx context.Context, s storage.Storage, key string) (io.
 		select {
 		case <-ctx.Done():
 			return nil, storage.Metadata{}, ctx.Err()
-		case <-time.After(time.Duration(i+1) * 150 * time.Millisecond):
+		case <-time.After(time.Duration(i+1) * 125 * time.Millisecond):
 		}
 	}
 	return nil, storage.Metadata{}, lastErr