hkunlp

/

instructor-xl

like 545

Follow

NLP Group of The University of Hong Kong 67

hi , when i use this command - instructor_embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
and then here i have created a function to create vector db from any given youtube url

def create_db_from_youtube_video_url(video_url: str) -> FAISS:
    #loads youtube transcripts from the given url
    loader = YoutubeLoader.from_youtube_url(video_url)
    transcript = loader.load()  
    #splits the text into chunks
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=20)
    docs = text_splitter.split_documents(transcript)
    db = FAISS.from_documents(docs, instructor_embeddings)
    return db

so here will the doc be uploaded on the server or the processinghappens locally, how can i confirm this behaviour?