load_local(db_directory, embedding_function, distance_strategy="MAX_INNER_PRODUCT") print(load_db .index, load_db .distance_strategy) # <faiss.swigfaiss_avx2.IndexFlat; proxy of <Swig Object of type 'faiss::IndexFlat *' at 0x7f4dd0accdb0> > MAX_INNER_PRODUCT I have looked through ...
mainly some folder name with just a number, then try to load that file path using faiss.load_local(). The path created after passing string path to Path(path) class is causing some issue. Expected behavior Issue: The actual file path is : D:\Question Answer Generative AI\Langchain\index...
This setup is crucial for the FAISS.load_local method to function properly, as it's designed to load the vector store with specific parameters like normalize_L2 and distance_strategy. For resolving this issue, verify the version of the FAISS library installed in your environment and ensure it ...
Running on local URL:http://0.0.0.0:7897 1、No module named 'triton'解决方法! 首先确定你的xformers是0.0.19版本,然后用我提供的triton.py文件替换掉此路径D:\RVC-WebUI\runtime\Lib\site-packages\xformers\ops\fmha\triton.py下的文件即可! 2、No module named 'faiss.swigfaiss_avx2’ 使用我提...
vector_store.save_local(self.vs_path) refresh_vs_cache(self.kb_name) defdo_delete_doc(self, kb_file:KnowledgeFile): kb_file:KnowledgeFile, **kwargs): embeddings=self._load_embeddings() vector_store=load_vector_store(self.kb_name, ...
vector_store.save_local(self.vs_path) refresh_vs_cache(self.kb_name) defdo_delete_doc(self, kb_file:KnowledgeFile): kb_file:KnowledgeFile, **kwargs): embeddings=self._load_embeddings() vector_store=load_vector_store(self.kb_name, ...