Handle Ollama models that return content in thinking field#998
Open
Br1an67 wants to merge 1 commit into
Open
Conversation
|
I have introduced your fix into ollama.py. Unfortunately, The call The Output : |
|
This worked for me, to fix the LLMSectionHeaderProcessor step as well it seems the cause is a missing $defs in the schema that is referenced and ollama can't find (because it's not there). Adding this if statement at line 45 fixed it: I also needed a 128k context window for my pdfs and the pagerange i was testing (10 pages). |
|
Introduced the fix. Same call as before. I change the LLM from qwen3-vl to gemma4:e4b, and it seemed to work without errors. But still, with qwen3-vl, the following results occurred. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Fix Ollama inference failure (
Expecting value: line 1 column 1 (char 0)) when models likeqwen3-vlreturn the generated content in thethinkingfield instead of theresponsefield.Some Ollama models with thinking mode enabled (e.g.,
qwen3-vl) place the actual output in thethinkingfield while leavingresponseempty. The current code only reads fromresponse, causingjson.loads("")to fail.Closes #992
Changes
OllamaService.__call__()to read from thethinkingfield whenresponseis empty