PGVector

Categories: Artificial Intelligence

Type: pgVector/v1

Connections

Version: 1

custom

Properties

Name	Label	Type	Description	Required
url	URL	STRING	The JDBC URL of the PostgreSQL instance (e.g. jdbc:postgresql://localhost:5432/postgres).	true
username	Username	STRING	The username for this connection.	true
password	Password	STRING	The password for this connection.	true
schemaName	Schema Name	STRING	The name of the PostgreSQL schema that contains the vector store table.	true
tableName	Table Name	STRING	The name of the table to use for storing vectors.	true
dimensions	Dimensions	INTEGER	The number of dimensions in the embedding vector.	true
distanceType	Distance Type	STRING Options COSINE_DISTANCE, EUCLIDEAN_DISTANCE, NEGATIVE_INNER_PRODUCT	The distance function to use for similarity search.	true
indexType	Index Type	STRING Options HNSW, IVFFLAT, NONE	The index algorithm to use for approximate nearest neighbor search.	true
initializeSchema	Initialize Schema	BOOLEAN Options true, false	Whether to initialize the schema on startup.	true
maxDocumentBatchSize	Max Document Batch Size	INTEGER	The maximum number of documents to process in a single batch.	true

Actions

Delete Documents

Name: delete

Delete documents from the vector store by metadata

Properties

Name	Label	Type	Description	Required
metadataFilter	Metadata Filter	ARRAY Items [{}]	List of metadata key-value pairs to filter by. Entries within a group are ANDed; groups are ORed.	false

Example JSON Structure

{
  "label" : "Delete Documents",
  "name" : "delete",
  "parameters" : {
    "metadataFilter" : [ { } ]
  },
  "type" : "pgVector/v1/delete"
}

Output

This action does not produce any output.

Load Documents

Name: load

Loads documents into the vector store using LLM embeddings.

Properties

Name	Label	Type	Description	Required
metadataFilter	Metadata Filter	ARRAY Items [{}]	List of metadata key-value pairs to filter by. Entries within a group are ANDed; groups are ORed.	false

Example JSON Structure

{
  "label" : "Load Documents",
  "name" : "load",
  "parameters" : {
    "metadataFilter" : [ { } ]
  },
  "type" : "pgVector/v1/load"
}

Output

This action does not produce any output.

Search Documents

Name: search

Query documents from the vector store using LLM embeddings.

Properties

Name	Label	Type	Description	Required
query	Query	STRING	The query to be executed.	true
metadataFilter	Metadata Filter	ARRAY Items [{}]	List of metadata key-value pairs to filter by. Entries within a group are ANDed; groups are ORed.	false
topK	Top K	INTEGER	The top 'k' similar results to return.	false
similarityThreshold	Similarity Threshold	NUMBER	Similarity threshold score to filter the search response by. Only documents with similarity score equal or greater than the threshold will be returned. A threshold value of 0 means any similarity is accepted. A threshold value of 1 means an exact match is required.	false

Example JSON Structure

{
  "label" : "Search Documents",
  "name" : "search",
  "parameters" : {
    "query" : "",
    "metadataFilter" : [ { } ],
    "topK" : 1,
    "similarityThreshold" : 0.0
  },
  "type" : "pgVector/v1/search"
}

Output

The output for this action is dynamic and may vary depending on the input parameters. To determine the exact structure of the output, you need to execute the action.

Update Documents

Name: update

Updates documents in the vector store by deleting existing ones matching the metadata filter and loading new ones using LLM embeddings.

Properties

Name	Label	Type	Description	Required
metadataFilter	Metadata Filter	ARRAY Items [{}]	List of metadata key-value pairs to filter by. Entries within a group are ANDed; groups are ORed.	false

Example JSON Structure

{
  "label" : "Update Documents",
  "name" : "update",
  "parameters" : {
    "metadataFilter" : [ { } ]
  },
  "type" : "pgVector/v1/update"
}

Output

This action does not produce any output.

On this page