unsloth/studio/backend/requirements
Roland Tannous 8666ec9bd6 Studio: swap multimodal RAG embedder to Qwen3-VL-Embedding-2B
Built on Qwen3 (not CLIP), so the 77-token text cap that bit
BGE-VL-base is gone — long chunks embed losslessly. Loads via
vanilla SentenceTransformer with trust_remote_code, no custom
adapter needed. 2048-d shared text+image space.

Adds qwen-vl-utils>=0.0.14 to rag.txt for image preprocessing,
required by the Qwen3-VL embedder family.
2026-05-24 21:48:02 +04:00
..
single-env Studio: add github_repo seed reader and GitHub Support Bot recipe (#5169) 2026-04-24 12:02:03 -07:00
__init__.py Final cleanup 2026-03-12 18:28:04 +00:00
base.txt move requirements/ to studio/backend/ and update paths in setup.sh 2026-02-17 19:02:25 +00:00
extras-no-deps.txt Studio: load BGE-VL via transformers AutoModel, bypassing ST shim 2026-05-24 21:35:09 +04:00
extras.txt Fixing Qwen3.5 bug and adding Outetts dependencies (#4459) 2026-03-19 01:52:07 -07:00
no-torch-runtime.txt Studio: move RAG deps to dedicated rag.txt and install in normal path 2026-05-24 16:23:26 +04:00
overrides.txt fix: Windows installer fails on _yaml.pyd Access Denied (os error 5) (#4617) 2026-03-26 05:15:19 -07:00
rag.txt Studio: swap multimodal RAG embedder to Qwen3-VL-Embedding-2B 2026-05-24 21:48:02 +04:00
studio.txt studio: API external provider support for chat (OpenAI, Mistral, Gemini, Cohere, Anthropic, OpenRouter, DeepSeek, custom providers) (#4706) 2026-05-14 16:13:59 +04:00
triton-kernels.txt move requirements/ to studio/backend/ and update paths in setup.sh 2026-02-17 19:02:25 +00:00