Find answers from the community

Home
Members
Azathoth
A
Azathoth
Offline, last seen 3 months ago
Joined September 25, 2024
When I use vector store in default mode, what similarity algo am I using? Is it cosine similarity?
Plain Text

2 comments
A
L
Plain Text
class VectorStoreQueryMode(str, Enum):
    """Vector store query mode."""

    DEFAULT = "default"
    SPARSE = "sparse"
    HYBRID = "hybrid"
    TEXT_SEARCH = "text_search"
    SEMANTIC_HYBRID = "semantic_hybrid"

    # fit learners
    SVM = "svm"
    LOGISTIC_REGRESSION = "logistic_regression"
    LINEAR_REGRESSION = "linear_regression"

    # maximum marginal relevance
    MMR = "mmr"
1 comment
W
Can I get node text by node ID in VectorStoreIndex?
I create a index like this, I know text and ID of a node. How may I get embedded vector of this node?
Plain Text
index = VectorStoreIndex(
        nodes, embed_model=embed_model, show_progress=True
    )
1 comment
W
Hello, I use VectorStoreIndex to evaluate embedding model. I think default similarity function is cos similarity. But as I check node score, they are all between (0, 1) rather than (-1, 1). It seems like maybe normalized L2 function is being used.
Why all similarity score is between 0-1? Can I change default similarity function of VectorStoreIndex to some specific function instead of default cos function?
6 comments
A
L
W