feat: Add support for custom LLM describers #1449
Open
+261
−64
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Outdated suggestions cannot be applied.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.
This PR addresses issue #1129 by introducing a flexible and extensible way to use any multimodal Large Language Model for image descriptions, not just OpenAI models.
Instead of hardcoding support for specific LLM providers like Gemini or Claude, this PR introduces a new
llm_describbercallback function. This allows users to define their own logic for generating image descriptions, making the library compatible with any LLM provider.Key Changes:
MarkItDownclass now accepts anllm_describberfunction in its constructor.llm_describberis propagated to all converters that handle image descriptions (ImageConverter,PptxConverter).llm_describberis not provided, the library falls back to the existingllm_client/llm_modellogic for OpenAI models.llm_describberis called correctly.README.mdto document the new functionality.Example Usage:
This approach provides maximum flexibility and avoids the need to add specific support for each new LLM provider in the future.