Merge branch 'main' into feat/vector-store-migrate

semantica/cli.py

@@ -3714,19 +3714,61 @@ def store_stats(cli_ctx: CLIContext, backend: str, fmt: str, local_json: bool) -
     _run_with_error_handling(_action)
 
 
+_MIGRATE_SUPPORTED_BACKENDS = {"faiss", "sqlite", "pgvector"}
+_MIGRATE_BATCH_SIZE = 500
+
+
+def _migrate_backend_config(vs_cfg: Dict[str, Any], backend: str) -> Dict[str, Any]:
+    """Resolve per-backend config out of the vector_store config section.
+
+    Supports both a per-backend nested shape (``vector_store.faiss.dimension``)
+    and the common flat single-backend shape (``vector_store.backend`` +
+    sibling keys), since either can appear depending on how many backends a
+    user has configured.
+    """
+    nested = vs_cfg.get(backend)
+    if isinstance(nested, dict):
+        return dict(nested)
+    if vs_cfg.get("backend") == backend:
+        return {k: v for k, v in vs_cfg.items() if k != "backend"}
+    return {}
+
+
+def _require_faiss_index_path(cfg: Dict[str, Any], role: str) -> str:
+    """FAISS has no server to hold state between commands: a fresh FAISSStore
+    starts empty and nothing outside the process persists it, so migration
+    needs an explicit on-disk index to read from or write to."""
+    index_path = cfg.get("index_path")
+    if not index_path:
+        raise click.ClickException(
+            f"faiss as migration {role} requires 'index_path' in the vector_store "
+            f"config (vector_store.faiss.index_path or vector_store.index_path "
+            f"when faiss is the configured backend)."
+        )
+    return index_path
+
+
 @store.command("migrate")
 @click.option("--from", "from_backend", required=True)
 @click.option("--to", "to_backend", required=True)
 @click.option("--namespace", default=None)
 @click.option("--dry-run", "local_dry", is_flag=True, default=False)
+@click.option("--json", "local_json", is_flag=True, default=False)
 @click.pass_obj
 def store_migrate(cli_ctx: CLIContext, from_backend: str, to_backend: str,
-                  namespace: Optional[str], local_dry: bool) -> None:
+                  namespace: Optional[str], local_dry: bool, local_json: bool) -> None:
     """Migrate data between backends.
 
+    Direct migration is only wired up between faiss, sqlite, and pgvector -
+    these are the backends whose storage contract supports paging through
+    every stored vector. Migrating to or from qdrant, pinecone, milvus, or
+    weaviate still needs the export/reindex workaround below, since each of
+    those needs its own enumeration design (Qdrant scroll, Pinecone list,
+    etc.) that hasn't been built yet.
+
     \b
     Example:
-      semantica store migrate --from faiss --to qdrant --namespace production --dry-run
+      semantica store migrate --from faiss --to sqlite --namespace production --dry-run
     """
     cli_ctx = _require_ctx(cli_ctx)
 
@@ -3734,13 +3776,76 @@ def store_migrate(cli_ctx: CLIContext, from_backend: str, to_backend: str,
         if _is_dry(cli_ctx, local_dry):
             _dry(cli_ctx, "migrate", from_backend=from_backend, to_backend=to_backend)
             return
-        raise click.ClickException(
+
-            f"Direct backend migration ({from_backend} → {to_backend}) is not yet supported "
+        if from_backend not in _MIGRATE_SUPPORTED_BACKENDS or to_backend not in _MIGRATE_SUPPORTED_BACKENDS:
-            "by the vector store layer. To migrate, export your data first:\n"
+            raise click.ClickException(
-            "  semantica export --format parquet --output dump.parquet\n"
+                f"Direct backend migration ({from_backend} → {to_backend}) is only supported "
-            f"  semantica embed index dump.parquet --store {to_backend}"
+                f"between {', '.join(sorted(_MIGRATE_SUPPORTED_BACKENDS))}. To migrate involving "
-            + (f" --namespace {namespace}" if namespace else "")
+                "another backend, export your data first:\n"
-        )
+                "  semantica export --format parquet --output dump.parquet\n"
+                f"  semantica embed index dump.parquet --store {to_backend}"
+                + (f" --namespace {namespace}" if namespace else "")
+            )
+
+        from .vector_store import VectorStore
+
+        vs_cfg = cli_ctx.config.to_dict().get("vector_store", {}) or {}
+        source_cfg = _migrate_backend_config(vs_cfg, from_backend)
+        dest_cfg = _migrate_backend_config(vs_cfg, to_backend)
+
+        source_index_path = None
+        if from_backend == "faiss":
+            source_index_path = _require_faiss_index_path(source_cfg, "source")
+        dest_index_path = None
+        if to_backend == "faiss":
+            dest_index_path = _require_faiss_index_path(dest_cfg, "destination")
+
+        source = VectorStore(backend=from_backend, config=source_cfg)
+        if source_index_path:
+            source._backend_store.load_index(source_index_path)
+
+        source_dimension = getattr(source._backend_store, "dimension", None)
+        if source_dimension and "dimension" not in dest_cfg:
+            dest_cfg["dimension"] = source_dimension
+
+        dest = VectorStore(backend=to_backend, config=dest_cfg)
+        if dest_index_path and Path(dest_index_path).exists():
+            dest._backend_store.load_index(dest_index_path)
+
+        migrated = 0
+        vectors_batch: List[Any] = []
+        metadata_batch: List[Dict[str, Any]] = []
+        ids_batch: List[str] = []
+
+        def _flush() -> None:
+            nonlocal migrated
+            if not vectors_batch:
+                return
+            dest.store_vectors(list(vectors_batch), list(metadata_batch), ids=list(ids_batch))
+            migrated += len(vectors_batch)
+            vectors_batch.clear()
+            metadata_batch.clear()
+            ids_batch.clear()
+
+        for item in source.iter_vectors(batch_size=_MIGRATE_BATCH_SIZE):
+            meta = dict(item.get("metadata") or {})
+            if namespace and "namespace" not in meta:
+                meta["namespace"] = namespace
+            vectors_batch.append(item["vector"])
+            metadata_batch.append(meta)
+            ids_batch.append(item["id"])
+            if len(vectors_batch) >= _MIGRATE_BATCH_SIZE:
+                _flush()
+        _flush()
+
+        if dest_index_path and migrated:
+            dest._backend_store.save_index(dest_index_path)
+
+        result = {"from": from_backend, "to": to_backend, "migrated": migrated}
+        if _is_json(cli_ctx, local_json):
+            _jecho(result)
+        else:
+            _ok(cli_ctx, f"Migrated {migrated} vectors from {from_backend} to {to_backend}")
 
     _run_with_error_handling(_action)
 

semantica/vector_store/faiss_store.py

@@ -66,12 +66,32 @@ class FAISSIndex:
         self.metadata: Dict[str, Dict[str, Any]] = {}
 
     def add_vectors(self, vectors: np.ndarray, ids: Optional[List[str]] = None):
-        """Add vectors to index."""
+        """
+        Add vectors to index.
+
+        Skips any id already present in vector_ids rather than appending a
+        second physical vector under the same id. FAISS indices here don't
+        support removing or replacing a single vector in place, so an
+        "update" isn't possible; without this check, re-running an add for
+        ids that already exist (e.g. retrying an interrupted migration)
+        would silently duplicate vectors under the same id on every retry.
+        """
         if ids is None:
             ids = [f"vec_{i}" for i in range(len(vectors))]
 
-        self.index.add(vectors.astype(np.float32))
+        new_rows = []
-        self.vector_ids.extend(ids)
+        new_ids = []
+        existing = set(self.vector_ids)
+        for row, vec_id in zip(vectors, ids):
+            if vec_id in existing:
+                continue
+            new_rows.append(row)
+            new_ids.append(vec_id)
+            existing.add(vec_id)
+
+        if new_rows:
+            self.index.add(np.array(new_rows, dtype=np.float32))
+            self.vector_ids.extend(new_ids)
 
     def search(
         self, query_vectors: np.ndarray, k: int = 10
@@ -305,6 +325,12 @@ class FAISSStore:
         """
         Add vectors to index.
 
+        Any id that already exists in the index is skipped rather than
+        stored as a second physical vector under the same id (see
+        FAISSIndex.add_vectors), so calling this again with ids from a
+        previous call is safe and doesn't accumulate duplicates. Metadata
+        for those ids is still updated.
+
         Args:
             vectors: List of vectors or numpy array
             ids: Vector IDs
@@ -312,7 +338,8 @@ class FAISSStore:
             **options: Additional options
 
         Returns:
-            List of vector IDs
+            List of vector IDs (including ids that were already present
+            and therefore not re-added as new vectors)
         """
         num_vectors = len(vectors) if isinstance(vectors, (list, np.ndarray)) else 1
         tracking_id = self.progress_tracker.start_tracking(
@@ -526,6 +553,30 @@ class FAISSStore:
 
         return results
 
+    def scan_vectors(self, offset: int = 0, limit: int = 100) -> List[Dict[str, Any]]:
+        """
+        Page through stored vectors in insertion order.
+
+        Args:
+            offset: Number of vectors to skip
+            limit: Maximum number of vectors to return
+
+        Returns:
+            List of result dicts with 'id', 'metadata', and 'vector'
+        """
+        if self.index is None or limit <= 0:
+            return []
+
+        ids_page = self.index.vector_ids[offset:offset + limit]
+        return [
+            {
+                "id": vector_id,
+                "metadata": self.get_metadata(vector_id) or {},
+                "vector": self.get_vector(vector_id),
+            }
+            for vector_id in ids_page
+        ]
+
     def get_stats(self) -> Dict[str, Any]:
         """Get index statistics."""
         if self.index is None:

semantica/vector_store/pgvector_store.py

@@ -656,6 +656,52 @@ class PgVectorStore:
             self.logger.warning(f"Failed to get metadata for {vector_id}: {e}")
             return None
 
+    def scan_vectors(self, offset: int = 0, limit: int = 100) -> List[Dict[str, Any]]:
+        """
+        Page through stored vectors ordered by id.
+
+        Args:
+            offset: Number of rows to skip
+            limit: Maximum number of rows to return
+
+        Returns:
+            List of result dicts with 'id', 'metadata', and 'vector'
+        """
+        if not PSYCOPG3_AVAILABLE and not PSYCOPG2_AVAILABLE:
+            raise ProcessingError(
+                "Neither psycopg3 nor psycopg2 is available. "
+                "Install with: pip install psycopg[binary] or psycopg2-binary"
+            )
+
+        if limit <= 0:
+            return []
+
+        scan_sql = psycopg_sql.SQL("""
+            SELECT id, vector, metadata
+            FROM {}
+            ORDER BY id
+            LIMIT %s OFFSET %s
+        """).format(psycopg_sql.Identifier(self.table_name))
+
+        with self._get_connection() as conn:
+            try:
+                cur = conn.cursor()
+                cur.execute(scan_sql, (limit, offset))
+                rows = cur.fetchall()
+                cur.close()
+
+                results = []
+                for row in rows:
+                    vec_id, vec, meta = row
+                    results.append({
+                        "id": vec_id,
+                        "metadata": meta if isinstance(meta, dict) else json.loads(meta) if meta else {},
+                        "vector": np.array(vec) if vec is not None else None,
+                    })
+                return results
+            except Exception as e:
+                raise ProcessingError(f"Failed to scan vectors: {str(e)}") from e
+
     def filter_by_metadata(
         self, filters: Dict[str, Any], limit: int = 10
     ) -> List[Dict[str, Any]]:

semantica/vector_store/sqlite_vec_store.py

@@ -616,6 +616,49 @@ class SQLiteVecStore:
             self.logger.warning(f"Failed to get metadata for {vector_id}: {e}")
             return None
 
+    def scan_vectors(self, offset: int = 0, limit: int = 100) -> List[Dict[str, Any]]:
+        """
+        Page through stored vectors ordered by id.
+
+        Args:
+            offset: Number of rows to skip
+            limit: Maximum number of rows to return
+
+        Returns:
+            List of result dicts with 'id', 'metadata', and 'vector'
+        """
+        if limit <= 0:
+            return []
+
+        query_sql = f"""
+            SELECT id, embedding, metadata
+            FROM {self.table_name}
+            ORDER BY id
+            LIMIT ? OFFSET ?
+        """
+
+        with self._lock, self._get_connection() as conn:
+            try:
+                cur = conn.cursor()
+                cur.execute(query_sql, (limit, offset))
+                rows = cur.fetchall()
+                cur.close()
+
+                results = []
+                for row in rows:
+                    vec_id, embedding_blob, meta_json = row
+                    vec = None
+                    if embedding_blob:
+                        vec = np.frombuffer(embedding_blob, dtype=np.float32).copy()
+                    results.append({
+                        "id": vec_id,
+                        "metadata": json.loads(meta_json) if meta_json else {},
+                        "vector": vec,
+                    })
+                return results
+            except Exception as e:
+                raise ProcessingError(f"Failed to scan vectors: {str(e)}") from e
+
     def filter_by_metadata(
         self, filters: Dict[str, Any], limit: int = 10
     ) -> List[Dict[str, Any]]:

semantica/vector_store/vector_store.py

@@ -824,6 +824,64 @@ class VectorStore:
         else:
             raise NotImplementedError(f"Backend store {type(self._backend_store).__name__} does not implement get_metadata")
 
+    def scan_vectors(self, offset: int = 0, limit: int = 100) -> List[Dict[str, Any]]:
+        """
+        Page through stored vectors, backend-agnostic.
+
+        Follows the get_vector()/get_metadata() precedent (#843): the inmemory
+        backend pages its local dict directly, a persistent backend delegates
+        to a scan_vectors() on the wrapped store when available, and one that
+        cannot enumerate its contents raises NotImplementedError rather than
+        silently returning an empty page.
+
+        Args:
+            offset: Number of vectors to skip
+            limit: Maximum number of vectors to return
+
+        Returns:
+            List of result dicts with 'id', 'metadata', and 'vector'
+        """
+        if limit <= 0:
+            return []
+
+        if self.backend == "inmemory":
+            ids_page = list(self.vectors.keys())[offset:offset + limit]
+            return [
+                {
+                    "id": vec_id,
+                    "metadata": self.metadata.get(vec_id, {}),
+                    "vector": self.vectors.get(vec_id),
+                }
+                for vec_id in ids_page
+            ]
+        elif self._backend_store and hasattr(self._backend_store, "scan_vectors"):
+            return self._backend_store.scan_vectors(offset=offset, limit=limit)
+        else:
+            raise NotImplementedError(
+                f"Backend store {type(self._backend_store).__name__} does not "
+                "implement scan_vectors(). Add a scan_vectors() method to the "
+                "backend store adapter to enable enumeration for this backend."
+            )
+
+    def iter_vectors(self, batch_size: int = 500):
+        """
+        Iterate over every stored vector, one page at a time.
+
+        Args:
+            batch_size: Number of vectors to fetch per underlying scan_vectors() call
+
+        Yields:
+            Result dicts with 'id', 'metadata', and 'vector', in scan order
+        """
+        offset = 0
+        while True:
+            page = self.scan_vectors(offset=offset, limit=batch_size)
+            if not page:
+                return
+            for item in page:
+                yield item
+            offset += len(page)
+
     def count(self) -> int:
         """Return the number of vectors in the store, backend-agnostic.
 

tests/test_cli_commands.py

@@ -1359,6 +1359,101 @@ class TestStore:
         result = runner.invoke(cli_module.main, ["store", "migrate", "--from", "faiss"])
         assert result.exit_code != 0
 
+    def test_migrate_refuses_unsupported_backend_pair(self, runner):
+        result = runner.invoke(cli_module.main, ["store", "migrate",
+                                      "--from", "faiss", "--to", "qdrant"])
+        assert result.exit_code != 0
+        assert "faiss, pgvector, sqlite" in result.output
+
+    def _fake_migrate_store_module(self, source_items, stored, dest_configs=None):
+        class _FakeBackendStore:
+            def __init__(self, dimension=None):
+                self.dimension = dimension
+
+        class _FakeStore:
+            def __init__(self, backend, config=None, **kw):
+                self.backend = backend
+                self._config = config or {}
+                dim = self._config.get("dimension")
+                self._backend_store = _FakeBackendStore(dimension=dim)
+                if dest_configs is not None:
+                    dest_configs[backend] = dict(self._config)
+
+            def iter_vectors(self, batch_size=500):
+                if self.backend == "sqlite":
+                    yield from source_items
+                    return
+                return
+                yield  # pragma: no cover - makes this a generator for other backends
+
+            def store_vectors(self, vectors, metadata, ids=None):
+                for vec_id, meta in zip(ids, metadata):
+                    stored[vec_id] = meta
+
+        return _fake_module(VectorStore=_FakeStore)
+
+    def test_migrate_runs_between_supported_backends(self, runner, monkeypatch):
+        source_items = [
+            {"id": "a", "vector": [0.1, 0.2], "metadata": {"tag": "x"}},
+            {"id": "b", "vector": [0.3, 0.4], "metadata": {}},
+        ]
+        stored = {}
+        fake_vs = self._fake_migrate_store_module(source_items, stored)
+        monkeypatch.setitem(__import__("sys").modules, "semantica.vector_store", fake_vs)
+
+        result = runner.invoke(cli_module.main, ["store", "migrate",
+                                      "--from", "sqlite", "--to", "pgvector",
+                                      "--namespace", "prod", "--json"])
+        _ok(result)
+        data = _json_output(result)
+        assert data == {"from": "sqlite", "to": "pgvector", "migrated": 2}
+        assert stored == {"a": {"tag": "x", "namespace": "prod"}, "b": {"namespace": "prod"}}
+
+    def test_migrate_reports_zero_for_empty_source(self, runner, monkeypatch):
+        stored = {}
+        fake_vs = self._fake_migrate_store_module([], stored)
+        monkeypatch.setitem(__import__("sys").modules, "semantica.vector_store", fake_vs)
+
+        result = runner.invoke(cli_module.main, ["store", "migrate",
+                                      "--from", "sqlite", "--to", "pgvector", "--json"])
+        _ok(result)
+        assert _json_output(result)["migrated"] == 0
+        assert stored == {}
+
+    def test_migrate_inherits_source_dimension_into_dest(self, runner, monkeypatch):
+        source_items = [{"id": "a", "vector": [0.1, 0.2, 0.3], "metadata": {}}]
+        stored = {}
+        dest_configs: dict = {}
+        fake_vs = self._fake_migrate_store_module(source_items, stored, dest_configs)
+        monkeypatch.setitem(__import__("sys").modules, "semantica.vector_store", fake_vs)
+        monkeypatch.setattr(
+            cli_module.Config, "to_dict",
+            lambda self: {"vector_store": {"sqlite": {"dimension": 3}, "pgvector": {}}},
+        )
+
+        result = runner.invoke(cli_module.main, ["store", "migrate",
+                                      "--from", "sqlite", "--to", "pgvector", "--json"])
+        _ok(result)
+        assert dest_configs["pgvector"].get("dimension") == 3
+
+    def test_migrate_faiss_source_requires_index_path(self, runner, monkeypatch):
+        fake_vs = _fake_module(VectorStore=lambda **kw: MagicMock())
+        monkeypatch.setitem(__import__("sys").modules, "semantica.vector_store", fake_vs)
+
+        result = runner.invoke(cli_module.main, ["store", "migrate",
+                                      "--from", "faiss", "--to", "sqlite"])
+        assert result.exit_code != 0
+        assert "index_path" in result.output
+
+    def test_migrate_faiss_dest_requires_index_path(self, runner, monkeypatch):
+        fake_vs = _fake_module(VectorStore=lambda **kw: MagicMock())
+        monkeypatch.setitem(__import__("sys").modules, "semantica.vector_store", fake_vs)
+
+        result = runner.invoke(cli_module.main, ["store", "migrate",
+                                      "--from", "sqlite", "--to", "faiss"])
+        assert result.exit_code != 0
+        assert "index_path" in result.output
+
     def test_flush_requires_confirm(self, runner):
         result = runner.invoke(cli_module.main, ["store", "flush"])
         assert result.exit_code != 0

tests/vector_store/test_faiss_index.py

@@ -3,7 +3,7 @@ from unittest.mock import MagicMock
 import numpy as np
 import pytest
 
-from semantica.vector_store.faiss_store import FAISSIndex
+from semantica.vector_store.faiss_store import FAISSIndex, FAISSStore
 
 
 def test_get_vector_reconstructs_from_flat_l2_index():
@@ -120,3 +120,90 @@ def test_get_vector_reconstructs_from_real_ivfflat_index_without_prior_direct_ma
     result = index.get_vector("vec_target")
 
     np.testing.assert_allclose(result, vectors[3], atol=1e-6)
+
+
+def _store_with_fake_index(ids, metadata_by_id=None):
+    backend_index = MagicMock()
+    backend_index.reconstruct.side_effect = lambda idx: [float(idx)] * 3
+    index = FAISSIndex(backend_index, dimension=3)
+    index.vector_ids = list(ids)
+    index.metadata = dict(metadata_by_id or {})
+
+    store = FAISSStore(dimension=3)
+    store.index = index
+    return store
+
+
+def test_scan_vectors_returns_all_across_pages():
+    store = _store_with_fake_index(["a", "b", "c", "d", "e"])
+
+    seen_ids = []
+    offset = 0
+    while True:
+        page = store.scan_vectors(offset=offset, limit=2)
+        if not page:
+            break
+        seen_ids.extend(p["id"] for p in page)
+        offset += len(page)
+
+    assert seen_ids == ["a", "b", "c", "d", "e"]
+
+
+def test_scan_vectors_includes_vector_and_metadata():
+    store = _store_with_fake_index(["a"], {"a": {"tag": "only"}})
+
+    page = store.scan_vectors(offset=0, limit=10)
+
+    assert len(page) == 1
+    assert page[0]["id"] == "a"
+    assert page[0]["metadata"] == {"tag": "only"}
+    np.testing.assert_array_equal(page[0]["vector"], np.array([0.0, 0.0, 0.0], dtype=np.float32))
+
+
+def test_scan_vectors_no_index_returns_empty_list():
+    store = FAISSStore(dimension=3)
+    assert store.scan_vectors(offset=0, limit=10) == []
+
+
+def test_scan_vectors_zero_limit_returns_empty_list():
+    store = _store_with_fake_index(["a"])
+    assert store.scan_vectors(offset=0, limit=0) == []
+
+
+def test_scan_vectors_offset_past_end_returns_empty_list():
+    store = _store_with_fake_index(["a"])
+    assert store.scan_vectors(offset=100, limit=10) == []
+
+
+def test_add_vectors_retry_with_same_ids_does_not_duplicate():
+    """Re-running add_vectors with ids already in the index (e.g. retrying
+    an interrupted migration) must not create a second physical vector
+    under the same id."""
+    backend_index = MagicMock()
+    store = FAISSStore(dimension=3)
+    store.index = FAISSIndex(backend_index, dimension=3)
+
+    vectors = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9], [10, 11, 12]], dtype=np.float32)
+    ids = ["a", "b", "c", "d"]
+
+    store.add_vectors(vectors, ids=ids, metadata=[{"i": i} for i in range(4)])
+    assert store.count() == 4
+
+    store.add_vectors(vectors, ids=ids, metadata=[{"i": i} for i in range(4)])
+
+    assert store.count() == 4
+    assert store.index.vector_ids == ids
+
+
+def test_add_vectors_retry_with_partial_overlap_only_adds_new_ids():
+    backend_index = MagicMock()
+    store = FAISSStore(dimension=3)
+    store.index = FAISSIndex(backend_index, dimension=3)
+
+    store.add_vectors(np.array([[1, 2, 3], [4, 5, 6]], dtype=np.float32), ids=["a", "b"])
+    store.add_vectors(np.array([[1, 2, 3], [7, 8, 9]], dtype=np.float32), ids=["a", "c"])
+
+    assert store.index.vector_ids == ["a", "b", "c"]
+    second_call_vectors = backend_index.add.call_args[0][0]
+    assert second_call_vectors.shape[0] == 1
+    np.testing.assert_array_equal(second_call_vectors[0], np.array([7, 8, 9], dtype=np.float32))

tests/vector_store/test_pgvector_store.py

@@ -467,6 +467,48 @@ class TestPgVectorStoreDelete:
         assert success is True
 
 
+class TestPgVectorStoreScan:
+    """Test scan_vectors pagination."""
+
+    def test_scan_returns_all_vectors_across_pages(self, store):
+        vectors = [np.random.rand(128).astype(np.float32) for _ in range(5)]
+        ids = store.add(vectors, [{"index": i} for i in range(5)])
+
+        seen_ids = []
+        offset = 0
+        while True:
+            page = store.scan_vectors(offset=offset, limit=2)
+            if not page:
+                break
+            seen_ids.extend(p["id"] for p in page)
+            offset += len(page)
+
+        assert set(seen_ids) == set(ids)
+        assert len(seen_ids) == 5
+
+    def test_scan_page_includes_vector_and_metadata(self, store):
+        vectors = [np.random.rand(128).astype(np.float32)]
+        ids = store.add(vectors, [{"tag": "only"}])
+
+        page = store.scan_vectors(offset=0, limit=10)
+
+        assert len(page) == 1
+        assert page[0]["id"] == ids[0]
+        assert page[0]["metadata"] == {"tag": "only"}
+        assert page[0]["vector"] is not None
+
+    def test_scan_empty_store_returns_empty_list(self, store):
+        assert store.scan_vectors(offset=0, limit=10) == []
+
+    def test_scan_zero_limit_returns_empty_list(self, store):
+        store.add([np.random.rand(128).astype(np.float32)])
+        assert store.scan_vectors(offset=0, limit=0) == []
+
+    def test_scan_offset_past_end_returns_empty_list(self, store):
+        store.add([np.random.rand(128).astype(np.float32)])
+        assert store.scan_vectors(offset=100, limit=10) == []
+
+
 class TestPgVectorStoreIndex:
     """Test index creation operations."""
 

tests/vector_store/test_sqlite_vec_store.py

@@ -415,6 +415,48 @@ class TestSQLiteVecStoreStats:
         assert stats["vector_count"] == 4
 
 
+class TestSQLiteVecStoreScan:
+    """Test scan_vectors pagination."""
+
+    def test_scan_returns_all_vectors_across_pages(self, store):
+        vectors = [np.random.rand(128).astype(np.float32) for _ in range(5)]
+        ids = store.add(vectors, [{"index": i} for i in range(5)])
+
+        seen_ids = []
+        offset = 0
+        while True:
+            page = store.scan_vectors(offset=offset, limit=2)
+            if not page:
+                break
+            seen_ids.extend(p["id"] for p in page)
+            offset += len(page)
+
+        assert set(seen_ids) == set(ids)
+        assert len(seen_ids) == 5
+
+    def test_scan_page_includes_vector_and_metadata(self, store):
+        vectors = [np.random.rand(128).astype(np.float32)]
+        ids = store.add(vectors, [{"tag": "only"}])
+
+        page = store.scan_vectors(offset=0, limit=10)
+
+        assert len(page) == 1
+        assert page[0]["id"] == ids[0]
+        assert page[0]["metadata"] == {"tag": "only"}
+        assert page[0]["vector"] is not None
+
+    def test_scan_empty_store_returns_empty_list(self, store):
+        assert store.scan_vectors(offset=0, limit=10) == []
+
+    def test_scan_zero_limit_returns_empty_list(self, store):
+        store.add([np.random.rand(128).astype(np.float32)])
+        assert store.scan_vectors(offset=0, limit=0) == []
+
+    def test_scan_offset_past_end_returns_empty_list(self, store):
+        store.add([np.random.rand(128).astype(np.float32)])
+        assert store.scan_vectors(offset=100, limit=10) == []
+
+
 class TestSQLiteVecStoreFilterByMetadata:
     """Test filter_by_metadata, including list-valued metadata handling."""
 

tests/vector_store/test_vector_manager_persistent.py

@@ -120,6 +120,78 @@ class VectorStoreCountTests(unittest.TestCase):
         self.assertIn("count()", msg)
 
 
+# ---------------------------------------------------------------------------
+# VectorStore.scan_vectors() / iter_vectors() dispatch tests
+# ---------------------------------------------------------------------------
+
+class _ScanningBackendStore:
+    """Fake persistent backend store that supports scan_vectors()."""
+
+    def __init__(self, items):
+        self._items = items
+
+    def scan_vectors(self, offset=0, limit=100):
+        return self._items[offset:offset + limit]
+
+
+class _NonScanningBackendStore:
+    """Fake persistent backend store without any scan capability."""
+
+
+class VectorStoreScanVectorsTests(unittest.TestCase):
+    """VectorStore.scan_vectors() / iter_vectors() backend-agnostic accessors."""
+
+    def setUp(self):
+        self.vectors = [np.array([1.0, 0.0]), np.array([0.0, 1.0]), np.array([1.0, 1.0])]
+        self.metadata = [{"type": "a"}, {"type": "b"}, {"type": "c"}]
+
+    def test_scan_inmemory_pages_through_all_vectors(self):
+        store = VectorStore(backend="inmemory", dimension=2)
+        ids = store.store_vectors(self.vectors, self.metadata)
+
+        page1 = store.scan_vectors(offset=0, limit=2)
+        page2 = store.scan_vectors(offset=2, limit=2)
+
+        self.assertEqual([p["id"] for p in page1], ids[:2])
+        self.assertEqual([p["id"] for p in page2], ids[2:])
+        self.assertEqual(page2[0]["metadata"], {"type": "c"})
+
+    def test_scan_inmemory_empty_store(self):
+        store = VectorStore(backend="inmemory", dimension=2)
+        self.assertEqual(store.scan_vectors(offset=0, limit=10), [])
+
+    def test_scan_zero_limit_returns_empty_list(self):
+        store = VectorStore(backend="inmemory", dimension=2)
+        store.store_vectors(self.vectors, self.metadata)
+        self.assertEqual(store.scan_vectors(offset=0, limit=0), [])
+
+    def test_scan_delegates_to_backend_store(self):
+        items = [{"id": "a", "metadata": {}, "vector": None}]
+        store = VectorStore(backend="inmemory", dimension=2)
+        store.backend = "faiss"
+        store._backend_store = _ScanningBackendStore(items)
+        self.assertEqual(store.scan_vectors(offset=0, limit=10), items)
+
+    def test_scan_raises_not_implemented_without_backend_support(self):
+        store = VectorStore(backend="inmemory", dimension=2)
+        store.backend = "faiss"
+        store._backend_store = _NonScanningBackendStore()
+        with self.assertRaises(NotImplementedError):
+            store.scan_vectors(offset=0, limit=10)
+
+    def test_iter_vectors_walks_every_page(self):
+        store = VectorStore(backend="inmemory", dimension=2)
+        ids = store.store_vectors(self.vectors, self.metadata)
+
+        collected = list(store.iter_vectors(batch_size=2))
+
+        self.assertEqual([item["id"] for item in collected], ids)
+
+    def test_iter_vectors_empty_store_yields_nothing(self):
+        store = VectorStore(backend="inmemory", dimension=2)
+        self.assertEqual(list(store.iter_vectors(batch_size=2)), [])
+
+
 # ---------------------------------------------------------------------------
 # VectorManager tests — inmemory backend
 # ---------------------------------------------------------------------------