diff --git a/swh/indexer/ctags.py b/swh/indexer/ctags.py
--- a/swh/indexer/ctags.py
+++ b/swh/indexer/ctags.py
@@ -5,12 +5,12 @@
 
 import json
 import subprocess
-from typing import Any, Dict, Iterator, List, Optional, Union
+from typing import Any, Dict, Iterator, List, Optional
 
 from swh.core.config import merge_configs
+from swh.indexer.storage import Sha1
 from swh.indexer.storage.model import ContentCtagsRow
 from swh.model import hashutil
-from swh.model.model import Revision
 
 from .indexer import ContentIndexer, write_to_temp
 
@@ -92,7 +92,7 @@
         )
 
     def index(
-        self, id: Union[bytes, Dict, Revision], data: Optional[bytes] = None, **kwargs
+        self, id: Sha1, data: Optional[bytes] = None, **kwargs
     ) -> List[ContentCtagsRow]:
         """Index sha1s' content and store result.
 
diff --git a/swh/indexer/fossology_license.py b/swh/indexer/fossology_license.py
--- a/swh/indexer/fossology_license.py
+++ b/swh/indexer/fossology_license.py
@@ -5,13 +5,12 @@
 
 import logging
 import subprocess
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Optional
 
 from swh.core.config import merge_configs
 from swh.indexer.storage.interface import IndexerStorageInterface, PagedResult, Sha1
 from swh.indexer.storage.model import ContentLicenseRow
 from swh.model import hashutil
-from swh.model.model import Revision
 
 from .indexer import ContentIndexer, ContentPartitionIndexer, write_to_temp
 
@@ -83,7 +82,7 @@
         self.working_directory = self.config["workdir"]
 
     def index(
-        self, id: Union[bytes, Dict, Revision], data: Optional[bytes] = None, **kwargs
+        self, id: Sha1, data: Optional[bytes] = None, **kwargs
     ) -> List[ContentLicenseRow]:
         """Index sha1s' content and store result.
 
@@ -100,7 +99,6 @@
             - indexer_configuration_id (int): tool used to compute the output
 
         """
-        assert isinstance(id, bytes)
         assert data is not None
         with write_to_temp(
             filename=hashutil.hash_to_hex(id),  # use the id as pathname
diff --git a/swh/indexer/indexer.py b/swh/indexer/indexer.py
--- a/swh/indexer/indexer.py
+++ b/swh/indexer/indexer.py
@@ -16,6 +16,7 @@
 from swh.indexer.storage import INDEXER_CFG_KEY, PagedResult, Sha1, get_indexer_storage
 from swh.indexer.storage.interface import IndexerStorageInterface
 from swh.model import hashutil
+from swh.model.model import Revision, Sha1Git
 from swh.objstorage.exc import ObjNotFoundError
 from swh.objstorage.factory import get_objstorage
 from swh.scheduler import CONFIG as SWH_CONFIG
@@ -57,10 +58,15 @@
 }
 
 
+TId = TypeVar("TId")
+"""type of the ids of index()ed objects."""
+TData = TypeVar("TData")
+"""type of the objects passed to index()."""
 TResult = TypeVar("TResult")
+"""return type of index()"""
 
 
-class BaseIndexer(Generic[TResult], metaclass=abc.ABCMeta):
+class BaseIndexer(Generic[TId, TData, TResult], metaclass=abc.ABCMeta):
     """Base class for indexers to inherit from.
 
     The main entry point is the :func:`run` function which is in
@@ -216,7 +222,7 @@
         else:
             return []
 
-    def index(self, id, data: Optional[bytes] = None, **kwargs) -> List[TResult]:
+    def index(self, id: TId, data: Optional[TData], **kwargs) -> List[TResult]:
         """Index computation for the id and associated raw data.
 
         Args:
@@ -231,7 +237,7 @@
         """
         raise NotImplementedError()
 
-    def filter(self, ids: List[bytes]) -> Iterator[bytes]:
+    def filter(self, ids: List[TId]) -> Iterator[TId]:
         """Filter missing ids for that particular indexer.
 
         Args:
@@ -263,7 +269,7 @@
         return {}
 
 
-class ContentIndexer(BaseIndexer[TResult], Generic[TResult]):
+class ContentIndexer(BaseIndexer[Sha1, bytes, TResult], Generic[TResult]):
     """A content indexer working on a list of ids directly.
 
     To work on indexer partition, use the :class:`ContentPartitionIndexer`
@@ -275,9 +281,7 @@
 
     """
 
-    def run(
-        self, ids: Union[List[bytes], bytes, str], policy_update: str, **kwargs
-    ) -> Dict:
+    def run(self, ids: List[Sha1], policy_update: str, **kwargs) -> Dict:
         """Given a list of ids:
 
         - retrieve the content from the storage
@@ -324,7 +328,7 @@
         return summary
 
 
-class ContentPartitionIndexer(BaseIndexer[TResult], Generic[TResult]):
+class ContentPartitionIndexer(BaseIndexer[Sha1, bytes, TResult], Generic[TResult]):
     """A content partition indexer.
 
     This expects as input a partition_id and a nb_partitions. This will then index the
@@ -493,7 +497,7 @@
         return summary
 
 
-class OriginIndexer(BaseIndexer[TResult], Generic[TResult]):
+class OriginIndexer(BaseIndexer[str, None, TResult], Generic[TResult]):
     """An object type indexer, inherits from the :class:`BaseIndexer` and
     implements Origin indexing using the run method
 
@@ -549,7 +553,7 @@
         return results
 
 
-class RevisionIndexer(BaseIndexer[TResult], Generic[TResult]):
+class RevisionIndexer(BaseIndexer[Sha1Git, Revision, TResult], Generic[TResult]):
     """An object type indexer, inherits from the :class:`BaseIndexer` and
     implements Revision indexing using the run method
 
@@ -560,7 +564,7 @@
 
     """
 
-    def run(self, ids: Union[str, bytes], policy_update: str) -> Dict:
+    def run(self, ids: List[Sha1Git], policy_update: str) -> Dict:
         """Given a list of sha1_gits:
 
         - retrieve revisions from storage
@@ -579,15 +583,15 @@
         revision_ids = [
             hashutil.hash_to_bytes(id_) if isinstance(id_, str) else id_ for id_ in ids
         ]
-        for rev in self.storage.revision_get(revision_ids):
+        for (rev_id, rev) in zip(revision_ids, self.storage.revision_get(revision_ids)):
             if not rev:
+                # TODO: call self.index() with rev=None?
                 self.log.warning(
-                    "Revisions %s not found in storage"
-                    % list(map(hashutil.hash_to_hex, ids))
+                    "Revision %s not found in storage", hashutil.hash_to_hex(rev_id)
                 )
                 continue
             try:
-                results.extend(self.index(rev))
+                results.extend(self.index(rev_id, rev))
             except Exception:
                 if not self.catch_exceptions:
                     raise
diff --git a/swh/indexer/metadata.py b/swh/indexer/metadata.py
--- a/swh/indexer/metadata.py
+++ b/swh/indexer/metadata.py
@@ -23,14 +23,14 @@
 from swh.indexer.metadata_detector import detect_metadata
 from swh.indexer.metadata_dictionary import MAPPINGS
 from swh.indexer.origin_head import OriginHeadIndexer
-from swh.indexer.storage import INDEXER_CFG_KEY
+from swh.indexer.storage import INDEXER_CFG_KEY, Sha1
 from swh.indexer.storage.model import (
     ContentMetadataRow,
     OriginIntrinsicMetadataRow,
     RevisionIntrinsicMetadataRow,
 )
 from swh.model import hashutil
-from swh.model.model import Revision
+from swh.model.model import Revision, Sha1Git
 
 REVISION_GET_BATCH_SIZE = 10
 ORIGIN_GET_BATCH_SIZE = 10
@@ -71,7 +71,11 @@
         )
 
     def index(
-        self, id, data: Optional[bytes] = None, log_suffix="unknown revision", **kwargs
+        self,
+        id: Sha1,
+        data: Optional[bytes] = None,
+        log_suffix="unknown revision",
+        **kwargs,
     ) -> List[ContentMetadataRow]:
         """Index sha1s' content and store result.
 
@@ -162,7 +166,9 @@
             )
         )
 
-    def index(self, id, data=None, **kwargs) -> List[RevisionIntrinsicMetadataRow]:
+    def index(
+        self, id: Sha1Git, data: Optional[Revision], **kwargs
+    ) -> List[RevisionIntrinsicMetadataRow]:
         """Index rev by processing it and organizing result.
 
         use metadata_detector to iterate on filenames
@@ -171,7 +177,8 @@
         - if multiple file detected -> translation needed at revision level
 
         Args:
-          rev: revision model object from storage
+          id: sha1_git of the revision
+          data: revision model object from storage
 
         Returns:
             dict: dictionary representing a revision_intrinsic_metadata, with
@@ -182,9 +189,8 @@
             - metadata: dict of retrieved metadata
 
         """
-        rev = id
+        rev = data
         assert isinstance(rev, Revision)
-        assert data is None
 
         try:
             root_dir = rev.directory
@@ -343,7 +349,7 @@
                 self.log.warning("Missing head revision of origin %r", origin.url)
                 continue
 
-            for rev_metadata in self.revision_metadata_indexer.index(rev):
+            for rev_metadata in self.revision_metadata_indexer.index(rev.id, rev):
                 # There is at most one rev_metadata
                 orig_metadata = OriginIntrinsicMetadataRow(
                     from_revision=rev_metadata.id,
diff --git a/swh/indexer/mimetype.py b/swh/indexer/mimetype.py
--- a/swh/indexer/mimetype.py
+++ b/swh/indexer/mimetype.py
@@ -3,14 +3,13 @@
 # License: GNU General Public License version 3, or any later version
 # See top-level LICENSE file for more information
 
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Optional
 
 import magic
 
 from swh.core.config import merge_configs
 from swh.indexer.storage.interface import IndexerStorageInterface, PagedResult, Sha1
 from swh.indexer.storage.model import ContentMimetypeRow
-from swh.model.model import Revision
 
 from .indexer import ContentIndexer, ContentPartitionIndexer
 
@@ -68,7 +67,7 @@
         self.config = merge_configs(DEFAULT_CONFIG, self.config)
 
     def index(
-        self, id: Union[bytes, Dict, Revision], data: Optional[bytes] = None, **kwargs
+        self, id: Sha1, data: Optional[bytes] = None, **kwargs
     ) -> List[ContentMimetypeRow]:
         """Index sha1s' content and store result.
 
@@ -84,7 +83,6 @@
             - encoding: encoding in bytes
 
         """
-        assert isinstance(id, bytes)
         assert data is not None
         properties = compute_mimetype_encoding(data)
         return [
diff --git a/swh/indexer/origin_head.py b/swh/indexer/origin_head.py
--- a/swh/indexer/origin_head.py
+++ b/swh/indexer/origin_head.py
@@ -5,7 +5,7 @@
 
 import logging
 import re
-from typing import Any, Dict, List, Optional, Tuple, Union
+from typing import Any, Dict, List, Tuple, Union
 
 import click
 
@@ -15,7 +15,7 @@
 from swh.storage.algos.snapshot import snapshot_get_all_branches
 
 
-class OriginHeadIndexer(OriginIndexer[Optional[Dict]]):
+class OriginHeadIndexer(OriginIndexer[Dict]):
     """Origin-level indexer.
 
     This indexer is in charge of looking up the revision that acts as the
@@ -34,13 +34,15 @@
 
     # Dispatch
 
-    def index(self, origin_url):
+    def index(self, id: str, data: None = None, **kwargs) -> List[Dict]:
+        origin_url = id
         visit_and_status = origin_get_latest_visit_status(
             self.storage, origin_url, allowed_statuses=["full"], require_snapshot=True
         )
         if not visit_and_status:
             return []
         visit, visit_status = visit_and_status
+        assert visit_status.snapshot is not None
         snapshot = snapshot_get_all_branches(self.storage, visit_status.snapshot)
         if snapshot is None:
             return []
diff --git a/swh/indexer/tests/test_indexer.py b/swh/indexer/tests/test_indexer.py
--- a/swh/indexer/tests/test_indexer.py
+++ b/swh/indexer/tests/test_indexer.py
@@ -3,7 +3,7 @@
 # License: GNU General Public License version 3, or any later version
 # See top-level LICENSE file for more information
 
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Optional
 from unittest.mock import Mock
 
 import pytest
@@ -15,7 +15,6 @@
     RevisionIndexer,
 )
 from swh.indexer.storage import PagedResult, Sha1
-from swh.model.model import Revision
 
 from .utils import BASE_TEST_CONFIG
 
@@ -28,7 +27,7 @@
     USE_TOOLS = False
 
     def index(
-        self, id: Union[bytes, Dict, Revision], data: Optional[bytes] = None, **kwargs
+        self, id: Any, data: Optional[Any] = None, **kwargs
     ) -> List[Dict[str, Any]]:
         raise _TestException()