Fallacy Finder

Swap providers, update models, and tune analysis behavior.

Application settings

Everything here is stored in the application instance settings file settings.json

Changes take effect on the next request.

Ollama
This list is pulled from the Ollama instance configured above.
OpenAI-compatible API
Not configured in server environment ENV
This key is never shown in the UI and is read only from the OPENAI_API_KEY environment variable.
Fallacy scanning analyzes one paragraph at a time, with optional neighboring context. You can fine tune this behavior in the Advanced Options.
Maximum seconds to allow for one paragraph analysis call before it is skipped and the scan continues.
Skip very short paragraphs to avoid wasting LLM calls on fragments, captions, or headings.
How many neighboring paragraphs to include on each side of the focus paragraph for context.
Maximum characters sent for each neighboring context paragraph.
Cancel
Test the active provider connection before saving settings.