Add model wrapper modules (embedding, reranker, llm, preference_extractor)

Add Python wrappers for:
- Qwen3/Nemotron embedding models
- BGE/Qwen3 rerankers
- vLLM/Llama/Qwen LLM backends
- GPT-4o/LLM-based preference extractors

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

1 files changed, 4 insertions, 0 deletions

diff --git a/src/personalization/models/llm/__init__.py b/src/personalization/models/llm/__init__.py
new file mode 100644
index 0000000..3f1af81
--- /dev/null
+++ b/src/personalization/models/llm/__init__.py
@@ -0,0 +1,4 @@
+from .qwen_instruct import QwenInstruct
+
+__all__ = ["QwenInstruct"]
+