Find answers from the community

Home
Members
sunwoong
s
sunwoong
Offline, last seen 2 months ago
Joined September 25, 2024
Consider I have this kind of composite of indices, is it possible to give priority to certain docs or using only one docs?
31 comments
j
s
B
s
sunwoong
·

Local db

Can I use local DB while I'm querying?
9 comments
L
s
I'm working on a task to save and QA a PDF document, and it takes about 2523ms with VectorIndex, but much longer with ListIndex (I just stopped before the result came out).

I know that ListIndex takes longer because it reads the entire document, but does it always take longer whenever the process of reading the entire document is required, for example, for summarization?
12 comments
s
L
s
sunwoong
·

Prompts

When we write a prompts for example,
Plain Text
DEFAULT_REFINE_PROMPT_TMPL = (
    "The original question is as follows: {query_str}\n"
    "We have provided an existing answer: {existing_answer}\n"
    "We have the opportunity to refine the existing answer "
    "(only if needed) with some more context below.\n"
    "------------\n"
    "{context_msg}\n"
    "------------\n"
    "Given the new context, refine the original answer to better "
    "answer the question. "
    "If the context isn't useful, return the original answer."
)

How can I give my VectorStoreIndex information as a context_msg?
15 comments
s
L
s
sunwoong
·

Hello

Hello.
I'm working on a project about generating some sentences based on specific documents. Should I use llama_index here? I'm wondering about the difference between purpose of use of llama_index and lang_chain. Since I'm currently doing task about 'text generation', can llama_index only be used for 'Qusetion-Answering' Task?
11 comments
L
s