Fix: Add back MarkdownElementNodeParser and give it access to a Local LLM #33

Open

Milestone

Ingest: Broader Content and Dataset type support (Images, PDF, text, Projects)

opened

run-llama/llama_index#16707
Workaround: MarkdownElementNodeParser(llm=MockLLM()), in obsidian/reader.py
Uses an LLM to parse tables, and defaults to OpenAI

Metadata

Assignees

No one assigned

Labels

No labels

No labels

Projects

No projects

Milestone

Ingest: Broader Content and Dataset type support (Images, PDF, text, Projects)No due date

Relationships

None yet

Development

No branches or pull requests