Find answers from the community

Updated 3 months ago

when using posgres pg vector does llama

when using posgres pg vector does llama index use hnsw by default or something else? - > when running an ingestion pipeline with pgvector as vector store. Thanks
Example:

Plain Text

CREATE INDEX ON embeddings USING hnsw (embedding vector_cosine_ops) WITH (m = 10, ef_construction = 64);

3 comments

LLogan M

tbh I have no idea what its doing -- PRs very welcome to improve this

LLogan M

The code is here https://github.com/run-llama/llama_index/blob/main/llama_index/vector_stores/postgres.py

LLogan M

Its just running CREATE EXTENSION IF NOT EXISTS vector from what I can tell

Add a reply