Pinecone

Pinecone is a vector database designed for efficient similarity search and storage of high-dimensional data, commonly used in machine learning and AI applications.

Categories: artificial-intelligence

Type: pinecone/v1

---

Connections

Version: 1

null

Properties

Name	Label	Type	Control Type	Description	Required
embeddingApiKey	Open AI API Key	STRING	TEXT	The API key for the OpenAI API which is used to generate embeddings.	true
apiKey	Pinecone API Key	STRING	TEXT	The API key for the Pinecone API.	true
host	Host	STRING	TEXT	Url of the host.	true

---

Actions

Data Query

Name: dataQuery

Query data from a Pinecone vector store using OpenAI embeddings.

Properties

Name	Label	Type	Control Type	Description	Required
query	Query	STRING	TEXT	The query to be executed.	true

JSON Example

{
  "label" : "Data Query",
  "name" : "dataQuery",
  "parameters" : {
    "query" : ""
  },
  "type" : "pinecone/v1/dataQuery"
}

Load Data

Name: loadData

Loads data into a Pinecone vector store using OpenAI embeddings.

Properties

Name	Label	Type	Control Type	Description	Required
documentType	Document Type	STRING Options JSON, MD, PDF, TXT, TIKA	SELECT	The type of the document.	true
jsonKeysToUse	JSON Keys to Use	ARRAY Items [STRING]	ARRAY_BUILDER	Json keys on which extraction of content is based. If no keys are specified, it uses the entire JSON object as content.	false
document		FILE_ENTRY	FILE_ENTRY		true
useTokenTextSplitter	Use Token Text Splitter	BOOLEAN Options true, false	SELECT	Whether to use the token text splitter.	true
tokenTextSplitter	Token Text Splitter	OBJECT Properties {INTEGER(defaultChunkSize), INTEGER(minChunkSizeChars), INTEGER(minChunkLengthToEmbed), INTEGER(maxNumChunks), BOOLEAN(keepSeparator)}	OBJECT_BUILDER	Splits text into chunks based on token count, using the CL100K_BASE encoding.	true
useKeywordEnricher	Use Keyword Metadata Enricher	BOOLEAN Options true, false	SELECT	Whether to use the keyword metadata enricher.	true
keywordMetadataEnricher	Keyword Metadata Enricher	OBJECT Properties {INTEGER(keywordCount)}	OBJECT_BUILDER	Extract keywords from document content and add them as metadata.	true
useSummaryEnricher	Use Summary Metadata Enricher	BOOLEAN Options true, false	SELECT	Whether to use the summary enricher.	true
summaryMetadataEnricher	Summary Metadata Enricher	OBJECT Properties {[STRING](summaryTypes)}	OBJECT_BUILDER	Summarize the document content and add the summaries as metadata.	true

JSON Example

{
  "label" : "Load Data",
  "name" : "loadData",
  "parameters" : {
    "documentType" : "",
    "jsonKeysToUse" : [ "" ],
    "document" : {
      "extension" : "",
      "mimeType" : "",
      "name" : "",
      "url" : ""
    },
    "useTokenTextSplitter" : false,
    "tokenTextSplitter" : {
      "defaultChunkSize" : 1,
      "minChunkSizeChars" : 1,
      "minChunkLengthToEmbed" : 1,
      "maxNumChunks" : 1,
      "keepSeparator" : false
    },
    "useKeywordEnricher" : false,
    "keywordMetadataEnricher" : {
      "keywordCount" : 1
    },
    "useSummaryEnricher" : false,
    "summaryMetadataEnricher" : {
      "summaryTypes" : [ "" ]
    }
  },
  "type" : "pinecone/v1/loadData"
}