Find answers from the community

Updated 2 months ago

Hello, how do I convert a list of

Hello, how do I convert a list of TextNode objects into Document objects? The reason I'm asking is because I'm try to run the Zephyr 7B Beta Collab provided, but it doesn't work when I start with a list of TextNode objects instead of a Document object. The error I get is 'TextNode' object has no attribute 'get_doc_id' My code is:
Plain Text
    document: Document = Document(text=txt_str, metadata=metadata or {})  # same approach as SimpleDirectoryReader
    documents: list[Document] = [document]

    node_parser = SentenceWindowNodeParser.from_defaults(
        window_size=3,
        window_metadata_key="window",
        original_text_metadata_key="original_text",
    )
    nodes: list[TextNode] = node_parser.get_nodes_from_documents(documents)  # this returns TextNodes rather than a Document

    llm = HuggingFaceLLM(
        model_name="HuggingFaceH4/zephyr-7b-beta",
        tokenizer_name="HuggingFaceH4/zephyr-7b-beta",
        query_wrapper_prompt=PromptTemplate("<|system|>\n</s>\n<|user|>\n{query_str}</s>\n<|assistant|>\n"),
        context_window=3900,
        max_new_tokens=256,
        # model_kwargs={"quantization_config": quantization_config},
        # tokenizer_kwargs={},
        generate_kwargs={"temperature": 0.7, "top_k": 50, "top_p": 0.95},
        messages_to_prompt=messages_to_prompt,
        device_map="cpu",
    )

    service_context = ServiceContext.from_defaults(llm=llm, embed_model=embed_model)
    vector_index = VectorStoreIndex.from_documents(nodes, service_context=service_context)  # Error happens here
k
1 comment
Actually, I think I solved my own problem: the solution is to just do vector_index = VectorStoreIndex(nodes, service_context=service_context)
Add a reply
Sign up and join the conversation on Discord