Find answers from the community

Updated 3 months ago

https://docs.llamaindex.ai/en/stable/

https://docs.llamaindex.ai/en/stable/examples/vector_stores/postgres.html
I am using the above URL to create a VectorStore using pgvector. So I have two questions.
What should be the contents of vector_store_query_mode= in PgVector Query Options?
Also, do I need to pre-create an index for HNSW EF Search?
Thanks in advance.
W
f
4 comments
I think one of the following can be used here: https://github.com/run-llama/llama_index/blob/b8e565f24d2312d3c6ca8120c1b557e14c77e259/llama_index/vector_stores/types.py#L44

But if you do not have any idea or need I guess leaving it should also be fine as it must have a default mode by itself.

For second, I guess yes as it is creating a retriever based on the index so yea
Thank you very much. Am I correct in understanding that if you create an index, it will be used automatically?
Yes, as you are passing that index in the retrieval building process, So it will be used for this
As an additional question, do you have an example of code to create an index for the vector store created in this example? Thanks in advance.
Add a reply
Sign up and join the conversation on Discord