adeelahmad · Oct 9, 2026 · Oct 7, 2026 · Oct 9, 2026 · Oct 9, 2026
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -4,6 +4,9 @@ The backend (`fastapi_backend`) and the frontend (`nextjs-frontend`) are version
 
 ## Unreleased
 
+- **Camera RAW and HEIC photos.** DNG, CR2, CR3, NEF, ARW, ORF, RAF, RW2, HEIC and HEIF can be uploaded and scanned
+  when anytopdf is here or a conversion node is set: anytopdf reads them, and RAW photos get the new Camera RAW photo
+  content type. Without anytopdf, Lens says what reading them needs ([anytopdf](docs/configuration.md#anytopdf)).
 - **Capture many web pages at once.** Import › Web page › Many pages at once takes pasted links, a browser's
   bookmark export or Chrome's Bookmarks file. Each link is captured like a single page, and its bookmark folders
   become its tags. Links already captured in the namespace are left as they are

diff --git a/docs/configuration.md b/docs/configuration.md
@@ -240,6 +240,12 @@ that makes documents, photos and media into searchable PDFs. Lens uses it as a c
   to 1 MB at most and its PDF to 2 GB, and a PDF that doesn't start like one is refused. **Check it** in Settings →
   Documents asks the node for a job with Lens's token and says whether it answered and took it.
 
+**Camera RAW and HEIC photos** (.dng, .cr2, .cr3, .nef, .arw, .orf, .raf, .rw2, .heic, .heif) are photos Lens can't
+open itself, so anytopdf reads them wherever it is here or a node is set, whatever `documents.converter` says but
+`lens`: RAW from the preview the camera embedded, HEIC where libheif or ImageMagick is beside anytopdf. Without
+anytopdf, uploading one says what it needs, and folder scans pass them by. A RAW photo gets the Camera RAW photo
+content type.
+
 It runs with no network, no runtime plugins and no config file of its own, and its PDF has no provenance page and
 holds only the document's text, so what Lens reads is what the document says. Faces, objects and speech stay Lens's
 own steps. The resource's rendition says `anytopdf` made it.

diff --git a/fastapi_backend/app/domain/content_types.py b/fastapi_backend/app/domain/content_types.py
@@ -44,6 +44,8 @@
     ("image", "image", "Image", "Any picture", {}),
     ("scan", "image", "Scanned page", "A page from a scanner or a phone", {"pattern": r"\bscan(s|ned|ning)?\b"}),
     ("photo", "image", "Photo", "A photograph", {"extensions": [".jpg", ".jpeg", ".heic"]}),
+    ("raw_photo", "image", "Camera RAW photo", "Straight from a camera's sensor: DNG, CR2, NEF, ARW and the like",
+     {"extensions": [".arw", ".cr2", ".cr3", ".dng", ".nef", ".orf", ".raf", ".rw2"]}),
     ("text", "text", "Text", "Any text", {}),
     ("chat_export", "text", "Chat export", "A WhatsApp, Telegram, Slack or iMessage chat, by who said it", {"forms": ["chat"]}),
     ("structured", "text", "Records", "JSON or JSON Lines data, one record at a time", {"forms": ["records"]}),

diff --git a/fastapi_backend/app/domain/convert.py b/fastapi_backend/app/domain/convert.py
@@ -102,7 +102,10 @@ def needs(name):
 
 def word(name):
     """What a document is, for people: "Word document", "email", "PDF"."""
-    return WORDS.get(ext_of(name), "document")
+    ext = ext_of(name)
+    if ext in store.CAMERA_EXT:
+        return "photo"
+    return WORDS.get(ext, "document")
 
 
 def content_type(name):
@@ -144,6 +147,11 @@ def capabilities(cfg):
 def unavailable(cfg, name):
     """Why this server can't read this document (None when it can): what it would need."""
     ext = ext_of(name)
+    if ext in store.CAMERA_EXT:
+        if anytopdf.mode(cfg) == "lens" or not anytopdf.available(cfg):
+            kind = "camera RAW" if ext in store.RAW_EXT else "HEIC"
+            return f"reading {kind} photos needs anytopdf (Settings › Documents › Make PDFs with anytopdf, or a conversion node)"
+        return None
     if ext not in store.DOCUMENT_EXT or ext == ".pdf":
         return None
     can = capabilities(cfg)
@@ -799,7 +807,7 @@ def keep_attachments(db, cfg, rid, attachments, say):
             continue
         ext = ext_of(f["name"])
         kind = documents.kind_of(f["name"]) or ("audio" if ext in {e.lower() for e in cfg["audio"]["extensions"]} else None)
-        if not kind or (kind == "document" and unavailable(cfg, f["name"])):
+        if not kind or unavailable(cfg, f["name"]):
             continue
         made += _resource_of(db, cfg, rid, rec, f, kind)
     if attachments[MAX_ATTACHMENTS:]:

diff --git a/fastapi_backend/app/domain/documents.py b/fastapi_backend/app/domain/documents.py
@@ -24,6 +24,9 @@
 R = store.R
 TYPES = {
     ".pdf": "application/pdf",
+    ".heic": "image/heic",
+    ".heif": "image/heif",
+    ".dng": "image/x-adobe-dng",
     ".jpg": "image/jpeg",
     ".jpeg": "image/jpeg",
     ".png": "image/png",
@@ -469,6 +472,14 @@ def transcribe(db, cfg, rid, say):
         except convert.Unavailable as e:
             raise ValueError(f"this {convert.word(path)} can't be read here: {e}") from None
         say(f"made into a PDF by {BY[learnt['by']]}")
+    elif source == "image" and convert.ext_of(path) in store.CAMERA_EXT:
+        # a camera RAW or HEIC photo: Lens can't open it, anytopdf can; its PDF is the photo's rendition
+        why = convert.unavailable(cfg, path)
+        if why:
+            raise ValueError(f"this photo can't be read here: {why}")
+        learnt = {"by": anytopdf.to_pdf(cfg, path, convert.rendition_path(cfg, rid))}
+        pdf = convert.rendition_path(cfg, rid)
+        say("made into a PDF by anytopdf")
     elif source == "image" and anytopdf.mode(cfg) == "anytopdf" and anytopdf.available(cfg):
         # anytopdf flattens a photographed page and reads it: its PDF is the image's rendition, read like a document's
         try:

diff --git a/fastapi_backend/app/domain/sources.py b/fastapi_backend/app/domain/sources.py
@@ -582,7 +582,7 @@ def file_kind(cfg, name, documents_as="document"):
             return "transcript"
         return None if convert.unavailable(cfg, name) else "document"
     if ext in store.IMAGE_EXT:
-        return "image"
+        return None if convert.unavailable(cfg, name) else "image"  # a RAW photo needs anytopdf
     return "transcript" if ext in TRANSCRIPT_EXT else None
 
 

diff --git a/fastapi_backend/app/domain/store.py b/fastapi_backend/app/domain/store.py
@@ -120,7 +120,10 @@ def labels():
 EMAIL_EXT = (".eml", ".msg")
 DOCUMENT_EXT = (".pdf", *OFFICE_EXT, *TEXT_EXT, *PAGE_EXT, *EMAIL_EXT)
 STRUCTURED_EXT = (".json", ".jsonl")  # read as records, a chat or a transcript (domain/records.py)
-IMAGE_EXT = (".jpg", ".jpeg", ".png", ".tif", ".tiff", ".webp", ".gif", ".bmp")
+RAW_EXT = (".arw", ".cr2", ".cr3", ".dng", ".nef", ".orf", ".raf", ".rw2")  # camera RAW
+# photos Pillow can't open: anytopdf reads them (RAW from its embedded preview; HEIC where libheif is beside it)
+CAMERA_EXT = (*RAW_EXT, ".heic", ".heif")
+IMAGE_EXT = (".jpg", ".jpeg", ".png", ".tif", ".tiff", ".webp", ".gif", ".bmp", *CAMERA_EXT)
 DEFAULTS = {
     "data_dir": "./archive-data",
     "database": {"url": None, "namespace": "archive", "database": "main", "user": "root", "password": "root"},

diff --git a/fastapi_backend/tests/api/test_anytopdf.py b/fastapi_backend/tests/api/test_anytopdf.py
@@ -259,6 +259,27 @@ def test_with_anytopdf_chosen_it_reads_images_too(here, client, env, db, cfg, fo
     assert any("read without anytopdf: anytopdf couldn't read it (error: it broke)" in x for x in log), log
 
 
+def test_camera_raw_photos_are_read_by_anytopdf(here, client, env, db, cfg):
+    """A RAW photo is one Lens can't open: anytopdf reads it, whatever documents.converter says but `lens`."""
+    from app.domain import content_types
+
+    he, ha = env["he"], env["ha"]
+    up = _upload(client, he, b"NEF raw bytes", "DSC_0042.nef")
+    drain(db, settings.effective(db, cfg))
+    rec = _rec(db, up["recording"])
+    assert (rec["source"], rec["status"], rec["rendition"]) == ("image", "analyzed", {"from": ".nef", "by": "anytopdf"}), rec.get("error")
+    assert "Photographed page document" in _text(db, up["recording"])
+    assert "--scan-mode" not in fake_anytopdf.runs(here)[-1]["args"]  # a photo, not a page to flatten
+    assert content_types.of_recording(db, up["recording"])[0]["key"] == "raw_photo"
+
+    # without anytopdf (or with Lens's converters chosen) a RAW photo isn't taken, and says what it needs
+    assert client.put("/api/v1/settings/documents", headers=ha, json={"converter": "lens"}).status_code == 200
+    r = _start(client, he, b"x" * 10, "DSC_0043.nef")
+    assert r.status_code == 400 and "camera RAW photos needs anytopdf" in r.json()["detail"], r.text
+    r = _start(client, he, b"x" * 10, "IMG_0001.heic")
+    assert r.status_code == 400 and "HEIC photos needs anytopdf" in r.json()["detail"], r.text
+
+
 def test_with_a_browser_and_poppler_here_it_draws_web_pages(here, client, env, db, cfg, monkeypatch):
     from app.domain import documents
 

diff --git a/fastapi_backend/tests/fake_anytopdf.py b/fastapi_backend/tests/fake_anytopdf.py
@@ -91,7 +91,7 @@ def face_of(path):
 def text_of(name, raw):
     """What the fake reads in a file: an image's name, a page of HTML's text, else its text."""
     name = str(name)
-    if pathlib.Path(name).suffix.lower() in (".png", ".jpg", ".jpeg"):
+    if pathlib.Path(name).suffix.lower() in (".png", ".jpg", ".jpeg", ".nef", ".dng", ".heic"):  # a camera RAW too
         return [f"Photographed page {pathlib.Path(name).stem}"]
     if pathlib.Path(name).suffix.lower() == ".docx":  # its paragraphs, as LibreOffice on the node would read them
         import io

diff --git a/nextjs-frontend/components/import/files.ts b/nextjs-frontend/components/import/files.ts
@@ -30,7 +30,9 @@ const TEXT_DOC_EXT = [".txt", ".text", ".md", ".markdown", ".mdx"];
 const PAGE_EXT = [".html", ".htm"];
 const EMAIL_EXT = [".eml", ".msg"];
 export const DOCUMENT_EXT = [".pdf", ...OFFICE_EXT, ...TEXT_DOC_EXT, ...PAGE_EXT, ...EMAIL_EXT];
-export const IMAGE_EXT = [".jpg", ".jpeg", ".png", ".tif", ".tiff", ".webp", ".gif", ".bmp"];
+/** Camera RAW and HEIC photos (the backend's CAMERA_EXT): read by anytopdf, so the server takes them only with it. */
+const CAMERA_EXT = [".arw", ".cr2", ".cr3", ".dng", ".nef", ".orf", ".raf", ".rw2", ".heic", ".heif"];
+export const IMAGE_EXT = [".jpg", ".jpeg", ".png", ".tif", ".tiff", ".webp", ".gif", ".bmp", ...CAMERA_EXT];
 /** What a document is, in words (the backend's convert.WORDS). */
 const DOCUMENT_NAME: Record<string, string> = {
   ".pdf": "PDF document",
@@ -85,6 +87,9 @@ export const DEFAULT_LIMITS: UploadLimits = {
     ".webm",
     ".webp",
     ...DOCUMENT_EXT,
+    ...CAMERA_EXT,
+    ".json",
+    ".jsonl",
   ].sort(),
   chunk_mb: 8,
   transcript_mb: 50,

diff --git a/nextjs-frontend/components/sources/source-model.ts b/nextjs-frontend/components/sources/source-model.ts
@@ -260,7 +260,26 @@ const DOCUMENT = [
   ".eml",
   ".msg",
 ];
-const IMAGE = [".jpg", ".jpeg", ".png", ".tif", ".tiff", ".webp", ".gif", ".bmp"];
+const IMAGE = [
+  ".jpg",
+  ".jpeg",
+  ".png",
+  ".tif",
+  ".tiff",
+  ".webp",
+  ".gif",
+  ".bmp",
+  ".arw",
+  ".cr2",
+  ".cr3",
+  ".dng",
+  ".nef",
+  ".orf",
+  ".raf",
+  ".rw2",
+  ".heic",
+  ".heif",
+];
 
 export type SourceFileKind = "audio" | "transcript" | "document" | "image" | "other";