Add configurable reranker batch size (env var RAG_RERANKING_BATCH_SIZE,
default 32) following the same pattern as RAG_EMBEDDING_BATCH_SIZE.
- config.py: PersistentConfig for RAG_RERANKING_BATCH_SIZE
- main.py: import, state init, pass to get_reranking_function
- colbert.py: accept batch_size param in predict() (was hardcoded 32)
- utils.py: get_reranking_function passes batch_size at call time
- retrieval.py: expose in config GET/POST endpoints and ConfigForm
- Documents.svelte: add Reranking Batch Size input in admin settings
Closes#23730
* fix: prevent ExternalReranker from blocking event loop during RAG queries (#120)
Co-authored-by: Tim Baek <tim@openwebui.com>
Co-authored-by: Claude <noreply@anthropic.com>
Fixes#19900
* Merge pull request open-webui#19030 from open-webui/dev (#122)
Co-authored-by: Tim Baek <tim@openwebui.com>
Co-authored-by: Claude <noreply@anthropic.com>
Fixes#19900
---------
Co-authored-by: Tim Baek <tim@openwebui.com>
Co-authored-by: Claude <noreply@anthropic.com>