News for hackers. Stuff that matters.
Re:DeepRAG: Thinking to Retrieval Step by Step for Large Lan... by cpursley on Tuesday February 04, 2025 @05:09PM (#42939660)
I've had great luck just base64'ing images and asking Qwen 2.5 VL to both parse it to markdown and generate a title, description and list of keywords (seems to work well on tables and charts). My plan is to split PDFs into pngs first then run those against Qwen async, then put them into a vector database (haven't gotten around to that quite yet).
Re:DeepRAG: Thinking to Retrieval Step by Step for Large Lan... by metadat on Tuesday February 04, 2025 @09:46PM (#42943014)
How does the base64 output become useful / usable information to an LLM?
Re:DeepRAG: Thinking to Retrieval Step by Step for Large Lan... by cpursley on Thursday February 06, 2025 @05:47AM (#42961088)
No idea but Qwen 2.5 VL seems to understand it all quite well.