Merge pull request #128 from djlongy/fix/markdown-upload-content-type

fix: send Markdown uploads as text/markdown

src/oikb/client.py

@@ -3,11 +3,24 @@
 from __future__ import annotations
 
 import json
+import mimetypes
+import os
 from typing import Any
 
 import httpx
 
 
+# Python 3.11 has no .md entry and slim images ship no /etc/mime.types, so a
+# Markdown upload went out as application/octet-stream and Open WebUI handed it
+# to its document extraction engine (Docling, Tika) instead of reading it as text.
+_TEXT_TYPES = {".md": "text/markdown", ".markdown": "text/markdown"}
+
+
+def _content_type(filename: str) -> str:
+    ext = os.path.splitext(filename)[1].lower()
+    return mimetypes.guess_type(filename)[0] or _TEXT_TYPES.get(ext, "application/octet-stream")
+
+
 class OikbClient:
     """Stateless HTTP client for the Open WebUI KB API.
 
@@ -84,7 +97,7 @@ class OikbClient:
 
         resp = self._http.post(
             "/files/",
-            files={"file": (filename, file_content)},
+            files={"file": (filename, file_content, _content_type(filename))},
             data={"metadata": json.dumps(metadata)},
         )
         resp.raise_for_status()

tests/test_kb_sync.py

@@ -1,9 +1,12 @@
+import mimetypes
 from unittest.mock import AsyncMock, Mock
 
 import httpx
 import pytest
+import respx
 from click.testing import CliRunner
 
+from oikb.client import OikbClient
 from oikb.connectors import BaseConnector, ManifestEntry
 from oikb.kb_sync import group_entries_by_kb, run_entries_sync
 from oikb.sync import SyncCancelled, SyncResult
@@ -145,3 +148,11 @@ def test_upload_error_includes_server_detail():
     client.upload_file.side_effect = httpx.HTTPStatusError("Bad Request", request=response.request, response=response)
     result = run_entries_sync(client, [{"source": "one", "kb-id": "kb"}], resolve_connector=lambda *a, **kw: Source({"a.txt": b"a"}), quiet=True)
     assert "extraction failed" in result.errors[0]
+
+
+@respx.mock
+def test_upload_sends_markdown_as_text_without_system_mime_types(monkeypatch):
+    monkeypatch.setattr(mimetypes, "guess_type", lambda *a, **kw: (None, None))
+    route = respx.post("https://webui.example/api/v1/files/").mock(return_value=httpx.Response(200, json={"id": "f"}))
+    OikbClient("https://webui.example", "token").upload_file(b"| a |\n| - |\n", "doc.md", "kb", "hash")
+    assert b"Content-Type: text/markdown" in route.calls.last.request.content