perf: batch page embeddings via /api/embed and upsert before pruning stale points

- embed_batch now issues one batched /api/embed request (the old loop
  made one /api/embeddings round-trip per chunk) with a per-text
  fallback that preserves None-for-failed semantics
- update_from_page embeds all chunks in that single call and stores
  them in one Qdrant batch upsert (upsert_points)
- reindex order reversed: upsert new points first, then prune stale ids
  (deterministic uuid5 ids make overwrite safe) so a mid-way failure no
  longer leaves the page with zero vectors
- VectorUpdateSummary gains status (success/partial/failed) and
  chunks_skipped; all-embeddings-failed keeps old vectors and reports
  failure instead of success=True

Measured on a 7-chunk page ingest (local server, llm_tester):
~375ms -> ~181ms median over 3 runs.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QbFZyDvYksazX6nYQYZ67L

src/clients/ollama_client.py

@@ -33,6 +33,7 @@ class OllamaClient:
         self.base_url = base_url.rstrip("/")
         self.model = model
         self.embeddings_url = f"{self.base_url}/api/embeddings"
+        self.embed_url = f"{self.base_url}/api/embed"
         self.generate_url = f"{self.base_url}/api/generate"
         self.tags_url = f"{self.base_url}/api/tags"
         self.client = httpx.AsyncClient(timeout=120.0)  # Embeddings can be slow
@@ -106,8 +107,37 @@ class OllamaClient:
             >>> len(embeddings)
             3
         """
-        embeddings = []
+        if not texts:
+            return []
 
+        # Single batched request via Ollama's /api/embed (the old
+        # implementation looped one /api/embeddings call per text).
+        try:
+            response = await self.client.post(
+                self.embed_url,
+                json={"model": self.model, "input": texts}
+            )
+            response.raise_for_status()
+            data = response.json()
+            embeddings = data.get("embeddings")
+
+            if embeddings is not None and len(embeddings) == len(texts):
+                if show_progress:
+                    logger.info(f"Batched embedding complete: {len(embeddings)}/{len(texts)}")
+                return embeddings
+
+            logger.warning(
+                f"Batched embed returned {len(embeddings or [])} vectors for "
+                f"{len(texts)} inputs, falling back to per-text embedding"
+            )
+        except Exception as e:
+            logger.warning(
+                f"Batched embed failed ({e}), falling back to per-text embedding"
+            )
+
+        # Fallback: per-text embedding preserves partial-success semantics
+        # (None entries for texts that failed to embed).
+        embeddings = []
         for i, text in enumerate(texts):
             if show_progress and i % 10 == 0:
                 logger.info(f"Embedding progress: {i}/{len(texts)}")

src/models/vector.py

@@ -67,6 +67,8 @@ class VectorUpdateSummary(BaseModel):
     chunks_created: int = Field(default=0, description="New chunks created")
     chunks_updated: int = Field(default=0, description="Existing chunks updated")
     chunks_deleted: int = Field(default=0, description="Old chunks deleted")
+    chunks_skipped: int = Field(default=0, description="Chunks skipped (embedding failed)")
+    status: str = Field(default="success", description="'success', 'partial' (some chunks skipped), or 'failed'")
     total_chunks: int = Field(default=0, description="Total chunks for this page")
     embedding_dim: int = Field(default=768, description="Embedding dimensionality")
     processing_time_ms: float = Field(..., description="Processing time in milliseconds")

src/services/vector_service.py

@@ -154,50 +154,79 @@ class VectorService:
             chunks = self._chunk_text(content)
             logger.info(f"Split page {page_id} into {len(chunks)} chunks")
 
-            # Delete existing chunks for this page
-            deleted_count = await self.qdrant.delete_by_filter(
-                collection_name=collection_name,
-                filter_conditions={"page_id": page_id}
-            )
+            # Generate ALL embeddings in one batched /api/embed call
+            # (previously one sequential Ollama round-trip per chunk)
+            embeddings = await self.ollama.embed_batch(chunks)
 
-            # Generate embeddings and upsert chunks
-            chunks_created = 0
-            for idx, chunk_text in enumerate(chunks):
-                # Generate deterministic UUID from page_id and chunk_index
-                chunk_id = str(uuid.uuid5(uuid.NAMESPACE_DNS, f"page_{page_id}_chunk_{idx}"))
-
-                # Generate embedding
-                embedding = await self.ollama.embed(chunk_text)
+            # Build points; deterministic uuid5 IDs mean re-upserting the
+            # same page overwrites its previous chunks in place.
+            points = []
+            chunks_skipped = 0
+            embedding_dim = 768
+            for idx, (chunk_text, embedding) in enumerate(zip(chunks, embeddings)):
                 if not embedding:
-                    logger.error(f"Failed to generate embedding for chunk {chunk_id}")
+                    chunks_skipped += 1
+                    logger.error(f"Failed to generate embedding for page {page_id} chunk {idx}")
                     continue
 
-                # Prepare metadata
-                metadata = {
-                    "page_id": page_id,
-                    "page_title": title,
-                    "page_path": path,
-                    "chunk_index": idx,
-                    "chunk_text": chunk_text,
-                    "user": user
-                }
+                embedding_dim = len(embedding)
+                chunk_id = str(uuid.uuid5(uuid.NAMESPACE_DNS, f"page_{page_id}_chunk_{idx}"))
+                points.append({
+                    "id": chunk_id,
+                    "vector": embedding,
+                    "payload": {
+                        "page_id": page_id,
+                        "page_title": title,
+                        "page_path": path,
+                        "chunk_index": idx,
+                        "chunk_text": chunk_text,
+                        "user": user
+                    }
+                })
 
-                # Upsert to Qdrant
-                success = await self.qdrant.upsert_vector(
+            # Upsert BEFORE deleting stale points. The old order (delete all,
+            # then embed+upsert one by one) left the page with ZERO vectors if
+            # anything failed mid-way; now old vectors survive until the new
+            # ones are safely stored.
+            chunks_created = 0
+            if points:
+                chunks_created = await self.qdrant.upsert_points(
                     collection_name=collection_name,
-                    vector_id=chunk_id,
-                    vector=embedding,
-                    payload=metadata
+                    points=points
                 )
 
-                if success:
-                    chunks_created += 1
+            # Prune stale points from a previous version of the page (chunk
+            # indexes beyond the new count, or indexes whose new embedding
+            # failed). Only prune if the new upsert actually stored points —
+            # a fully failed embedding pass must not wipe the old vectors.
+            deleted_count = 0
+            if points:
+                new_ids = {p["id"] for p in points}
+                existing = await self.qdrant.scroll_all_points(
+                    collection_name=collection_name,
+                    filter_conditions={"page_id": page_id},
+                    with_payload=False
+                )
+                stale_ids = [pt["id"] for pt in existing if pt["id"] not in new_ids]
+                if stale_ids:
+                    deleted_count = await self.qdrant.delete_by_ids(
+                        collection_name=collection_name,
+                        point_ids=stale_ids
+                    )
 
             processing_time_ms = (time.time() - start_time) * 1000
 
+            if chunks_created == 0:
+                status = "failed"
+            elif chunks_skipped > 0:
+                status = "partial"
+            else:
+                status = "success"
+
             logger.info(
                 f"Updated vectors for page {page_id}: "
-                f"{chunks_created} chunks created, {deleted_count} old chunks deleted"
+                f"{chunks_created} chunks created, {chunks_skipped} skipped, "
+                f"{deleted_count} stale chunks deleted ({status})"
             )
 
             return VectorUpdateSummary(
@@ -205,10 +234,16 @@ class VectorService:
                 page_title=title,
                 chunks_created=chunks_created,
                 chunks_deleted=deleted_count,
+                chunks_skipped=chunks_skipped,
                 total_chunks=chunks_created,
-                embedding_dim=len(embedding) if embedding else 768,
+                embedding_dim=embedding_dim,
                 processing_time_ms=processing_time_ms,
-                success=True
+                success=chunks_created > 0,
+                status=status,
+                error_message=(
+                    f"{chunks_skipped}/{len(chunks)} chunk embeddings failed"
+                    if chunks_skipped else None
+                )
             )
 
         except Exception as e: