haiku.rag/docs/configuration
Yiorgis Gozadinos 543aba7547
Multimodal reranking: send picture chunks to vllm rerankers as images
reranking.multimodal (vllm provider only) attaches picture bytes to
synthetic picture chunks before rerank; VLLMReranker sends them as
content-parts documents (base64 data URI + description text) in the
same /v1/rerank request as plain text documents.
2026-07-24 12:29:20 +03:00
..
index.md Multimodal reranking: send picture chunks to vllm rerankers as images 2026-07-24 12:29:20 +03:00
processing.md Dedupe picture chunks and skip small pictures at chunking 2026-07-09 10:24:32 +03:00
prompts.md drop prose emdashes and semicolons; minor fixes 2026-05-20 14:27:16 +03:00
providers.md Multimodal reranking: send picture chunks to vllm rerankers as images 2026-07-24 12:29:20 +03:00
qa.md Lower search.max_context_chars default to 5000 2026-07-14 11:58:42 +03:00
storage.md docs 2026-06-12 10:17:18 +03:00