[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
Python aifaissgpt-osslangchainllama-indexllmlocalstorageoffline-firstollamaprivacypythonragretrieval-augmented-generationvector-databasevector-searchvectors
security: Enhance Hugging Face model loading security - resolves #136 (#138)
Aakash Suresh32967daf81f1
diff --git a/benchmarks/llm_utils.py b/benchmarks/llm_utils.pyindex 9a8217c..f64c55b 100644--- a/benchmarks/llm_utils.py+++ b/benchmarks/llm_utils.py@@ -54,29 +54,51 @@ def extract_thinking_answer(response):return response.strip()-def load_hf_model(model_name="Qwen/Qwen3-8B"):- """Load HuggingFace model"""+def load_hf_model(model_name="Qwen/Qwen3-8B", trust_remote_code=False):+ """Load HuggingFace model++ Args:+ model_name (str): Name of the model to load+ trust_remote_code (bool): Whether to allow execution of code from the model repository.+ Defaults to False for security. Only enable for trusted models.+ """if not HF_AVAILABLE:raise ImportError("transformers not available")+ if trust_remote_code:+ print(+ "⚠️ WARNING: Loading model with trust_remote_code=True. This can execute arbitrary code."+ )+print(f"Loading HF: {model_name}")- tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)+ tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=trust_remote_code)model = AutoModelForCausalLM.from_pretrained(model_name,torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,device_map="auto",- trust_remote_code=True,+ trust_remote_code=trust_remote_code,)return tokenizer, model-def load_vllm_model(model_name="Qwen/Qwen3-8B"):- """Load vLLM model"""+def load_vllm_model(model_name="Qwen/Qwen3-8B", trust_remote_code=False):+ """Load vLLM model++ Args:+ model_name (str): Name of the model to load+ trust_remote_code (bool): Whether to allow execution of code from the model repository.+ Defaults to False for security. Only enable for trusted models.+ """if not VLLM_AVAILABLE:raise ImportError("vllm not available")+ if trust_remote_code:+ print(+ "⚠️ WARNING: Loading model with trust_remote_code=True. This can execute arbitrary code."+ )+print(f"Loading vLLM: {model_name}")- llm = LLM(model=model_name, trust_remote_code=True)+ llm = LLM(model=model_name, trust_remote_code=trust_remote_code)# Qwen3 specific configif is_qwen3_model(model_name):@@ -178,19 +200,33 @@ def evaluate_rag(searcher, llm_func, queries, domain="default", top_k=3, complex}-def load_qwen_vl_model(model_name="Qwen/Qwen2.5-VL-7B-Instruct"):- """Load Qwen2.5-VL multimodal model"""+def load_qwen_vl_model(model_name="Qwen/Qwen2.5-VL-7B-Instruct", trust_remote_code=False):+ """Load Qwen2.5-VL multimodal model++ Args:+ model_name (str): Name of the model to load+ trust_remote_code (bool): Whether to allow execution of code from the model repository.+ Defaults to False for security. Only enable for trusted models.+ """if not HF_AVAILABLE:raise ImportError("transformers not available")+ if trust_remote_code:+ print(+ "⚠️ WARNING: Loading model with trust_remote_code=True. This can execute arbitrary code."+ )+print(f"Loading Qwen2.5-VL: {model_name}")try:from transformers import AutoModelForVision2Seq, AutoProcessor- processor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)+ processor = AutoProcessor.from_pretrained(model_name, trust_remote_code=trust_remote_code)model = AutoModelForVision2Seq.from_pretrained(- model_name, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True+ model_name,+ torch_dtype=torch.bfloat16,+ device_map="auto",+ trust_remote_code=trust_remote_code,)return processor, model@@ -202,9 +238,14 @@ def load_qwen_vl_model(model_name="Qwen/Qwen2.5-VL-7B-Instruct"):try:from transformers import AutoProcessor, Qwen2VLForConditionalGeneration- processor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)+ processor = AutoProcessor.from_pretrained(+ model_name, trust_remote_code=trust_remote_code+ )model = Qwen2VLForConditionalGeneration.from_pretrained(- model_name, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True+ model_name,+ torch_dtype=torch.bfloat16,+ device_map="auto",+ trust_remote_code=trust_remote_code,)return processor, modeldiff --git a/packages/leann-core/src/leann/chat.py b/packages/leann-core/src/leann/chat.pyindex 8135daf..1f870bf 100644--- a/packages/leann-core/src/leann/chat.py+++ b/packages/leann-core/src/leann/chat.py@@ -546,11 +546,30 @@ class OllamaChat(LLMInterface):class HFChat(LLMInterface):- """LLM interface for local Hugging Face Transformers models with proper chat templates."""+ """LLM interface for local Hugging Face Transformers models with proper chat templates.- def __init__(self, model_name: str = "deepseek-ai/deepseek-llm-7b-chat"):+ Args:+ model_name (str): Name of the Hugging Face model to load.+ trust_remote_code (bool): Whether to allow execution of code from the model repository.+ Defaults to False for security. Only enable for trusted models as this can pose+ a security risk if the model repository is compromised.+ """++ def __init__(+ self, model_name: str = "deepseek-ai/deepseek-llm-7b-chat", trust_remote_code: bool = False+ ):logger.info(f"Initializing HFChat with model='{model_name}'")+ # Security warning when trust_remote_code is enabled+ if trust_remote_code:+ logger.warning(+ "SECURITY WARNING: trust_remote_code=True allows execution of arbitrary code from the model repository. "+ "Only enable this for models from trusted sources. This creates a potential security risk if the model "+ "repository is compromised."+ )++ self.trust_remote_code = trust_remote_code+# Pre-check model availability with helpful suggestionsmodel_error = validate_model_and_suggest(model_name, "hf")if model_error:@@ -588,14 +607,16 @@ class HFChat(LLMInterface):try:logger.info(f"Loading tokenizer for {model_name}...")- self.tokenizer = AutoTokenizer.from_pretrained(model_name)+ self.tokenizer = AutoTokenizer.from_pretrained(+ model_name, trust_remote_code=self.trust_remote_code+ )logger.info(f"Loading model {model_name}...")self.model = AutoModelForCausalLM.from_pretrained(model_name,torch_dtype=torch.float16 if self.device != "cpu" else torch.float32,device_map="auto" if self.device != "cpu" else None,- trust_remote_code=True,+ trust_remote_code=self.trust_remote_code,)logger.info(f"Successfully loaded {model_name}")finally:@@ -859,7 +880,10 @@ def get_llm(llm_config: Optional[dict[str, Any]] = None) -> LLMInterface:host=llm_config.get("host"),)elif llm_type == "hf":- return HFChat(model_name=model or "deepseek-ai/deepseek-llm-7b-chat")+ return HFChat(+ model_name=model or "deepseek-ai/deepseek-llm-7b-chat",+ trust_remote_code=llm_config.get("trust_remote_code", False),+ )elif llm_type == "openai":return OpenAIChat(model=model or "gpt-4o",