v2 restructure: Go client, Docker engine, release tooling

- Remove v1 Python CLI (src/kb_search/, tests/, root pyproject.toml, uv.lock, .venv)
- Add Go client with cross-platform build (client/)
- Add FastAPI engine with NVIDIA and multi-stage ROCm Dockerfiles (engine/)
- Add VERSION files for client and engine, wired into builds
- Add release.sh for automated build, tag, release, and Docker push
- Update README with build/release docs and ROCm migration note
- Clean up .gitignore for v2 project structure

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

engine/kb/routes/reindex.py

@@ -0,0 +1,55 @@
+"""Reindex endpoint — re-embed all chunks with the current model."""
+
+import logging
+import struct
+
+from main import app
+from kb.config import cfg
+from kb.database import get_connection, recreate_vec_table
+from kb.embeddings import embed_texts, get_model_dim
+
+logger = logging.getLogger("kb.routes.reindex")
+
+BATCH_SIZE = 256
+
+
+@app.post("/api/v1/reindex")
+async def reindex():
+    dim = get_model_dim()
+
+    conn = get_connection(cfg.db_path)
+    try:
+        # Fetch all chunks
+        rows = conn.execute("SELECT id, text FROM chunks ORDER BY id").fetchall()
+        chunk_ids = [row["id"] for row in rows]
+        chunk_texts = [row["text"] for row in rows]
+
+        logger.info("Reindexing %d chunks with model '%s'", len(chunk_ids), cfg.model)
+
+        # Recreate the vec table
+        recreate_vec_table(conn, dim)
+
+        # Embed and insert in batches
+        for i in range(0, len(chunk_ids), BATCH_SIZE):
+            batch_ids = chunk_ids[i : i + BATCH_SIZE]
+            batch_texts = chunk_texts[i : i + BATCH_SIZE]
+
+            embeddings = embed_texts(batch_texts)
+
+            for chunk_id, embedding in zip(batch_ids, embeddings):
+                blob = struct.pack(f"{len(embedding)}f", *embedding)
+                conn.execute(
+                    "INSERT INTO chunks_vec(embedding, chunk_id) VALUES (?, ?)",
+                    (blob, chunk_id),
+                )
+
+            conn.commit()
+
+        logger.info("Reindex complete: %d chunks", len(chunk_ids))
+
+        return {
+            "chunks_reindexed": len(chunk_ids),
+            "model": cfg.model,
+        }
+    finally:
+        conn.close()