Vector Store Retriever

This node specializes in retrieving embeddings from a vector store based on their relevance to user queries.

Note: Dissimilarity scores calculated using FAISS or Chroma with L2 distance are not bound to a specific range, therefore allowing only for ordinal comparison of scores. These scores also depend on the embeddings model used to generate the embeddings, as different models produce embeddings with varying scales and distributions. Therefore, understanding or comparing similarity across different models or spaces without contextual normalization is not meaningful.

Options

Queries column

Column containing the queries.

Number of results

Number of top results to get from vector store search. Ranking from best to worst.

Retrieved document column name

The name for the appended column containing the retrieved documents.

Retrieve metadata from documents

Whether or not to retrieve document metadata, if provided.

Retrieve dissimilarity scores

Whether or not to retrieve dissimilarity scores for the retrieved documents. FAISS and Chroma use L2 distance by default to calculate dissimilarity scores. Lower score represents more similarity.

Dissimilarity scores column name

The name for the appended column containing the dissimilarity scores.

Input Ports

Icon

Vector store containing document embeddings.

Icon

Table containing a string column with the queries for the vector store.

Output Ports

Icon

Table containing the queries and their closest match from the vector store.

Popular Predecessors

  • No recommendations found

Popular Successors

  • No recommendations found

Views

This node has no views

Workflows

  • No workflows found

Links

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.