Skip to content

fix(ocr_client): default to 'Text Recognition:' prompt in ollama_generate mode #208

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
JaredforReal merged 2 commits into from
Apr 21, 2026
Merged

fix(ocr_client): default to 'Text Recognition:' prompt in ollama_generate mode #208

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5e948ad
fix(ocr_client): default to 'Text Recognition:' prompt in ollama_gene…
mufradhossain Apr 21, 2026
7ddd841
test(ocr_client): update empty prompt tests to expect 'Text Recogniti…
mufradhossain Apr 21, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion glmocr/ocr_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -468,9 +468,12 @@ def _convert_to_ollama_generate(self, request_data: Dict) -> Dict:
images.append(image_url)

# Build Ollama generate request
# Default to "Text Recognition:" when prompt is empty because Ollama
# requires a non-empty prompt to trigger the model. This matches the
# official documented usage for GLM-OCR on Ollama.
ollama_request = {
"model": self.model or "glm-ocr:latest",
"prompt": prompt,
"prompt": prompt if prompt else "Text Recognition:",
"stream": False,
}

Expand Down
4 changes: 2 additions & 2 deletions glmocr/tests/test_unit.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1682,14 +1682,14 @@ def test_empty_messages(self):
"""Handles empty messages list."""
client = self._make_client()
result = client._convert_to_ollama_generate({"messages": []})
assert result["prompt"] == ""
assert result["prompt"] == "Text Recognition:"
assert "images" not in result

def test_no_messages_key(self):
"""Handles missing messages key."""
client = self._make_client()
result = client._convert_to_ollama_generate({})
assert result["prompt"] == ""
assert result["prompt"] == "Text Recognition:"

def test_non_user_messages_ignored(self):
"""System and assistant messages are ignored (last user message used)."""
Expand Down
Loading