Fix embedding tokenizer mismatch with custom embedding server

Disable tiktoken pre-encoding for custom embedding servers. LangChain
was encoding text into OpenAI token IDs then sending them to llama-server
which has a different vocabulary, causing "invalid tokens" errors.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

blueprints/rag/logic.py

@@ -26,6 +26,7 @@ if _embedding_server_url:
         model=_embedding_model,
         base_url=_embedding_server_url,
         api_key="not-needed",
+        check_embedding_ctx_length=False,
     )
 else:
     embeddings = OpenAIEmbeddings(model=_embedding_model)