Ben
Results
1
comments of
Ben
我的代码这样,帮看看有没有问题,获取不了中文的相似的文本 def qdrant(docs_path): texts = [] for doc in tqdm(os.listdir(docs_path)): if doc.endswith('.txt'): with open(f'{docs_path}/{doc}','r',encoding='utf-8') as f: doc_data = f.read() text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0) texts = text_splitter.split_text(doc_data) Qdrant.from_texts(texts, embeddings, metadatas=[{"source": f"{i}-doc"}...