Navigation

Mobile Docs

Pinecone

Use Pinecone vector database

Store, search, and retrieve vector embeddings using Pinecone's specialized vector database. Generate embeddings from text and perform semantic similarity searches with customizable filtering options.

Toolspinecone

Usage

01Add the block to your workflow and connect it to the upstream step.
02Configure any required credentials or tokens in the inputs.
03Fill in required inputs and optional parameters for the run.
04Run a test execution, inspect outputs, and iterate before deploying.
05Deploy the pinecone block with monitoring enabled in production.

Inputs (UI)

Operation

dropdown

Layout: full

Options: Generate Embeddings, Upsert Text, Search With Text, Search With Vector

Model

dropdown

Layout: full

Condition: operation = "generate"

Options: multilingual-e5-large, llama-text-embed-v2, pinecone-sparse-english-v0

Text Inputs

long-input

Placeholder: [{"text": "Your text here"}]

Layout: full

Condition: operation = "generate"

Index Host

short-input

Placeholder: https://index-name-abc123.svc.project-id.pinecone.io

Layout: full

Condition: operation = "upsert_text"

Namespace

short-input

Placeholder: default

Layout: full

Condition: operation = "upsert_text"

Records

long-input

Placeholder: {"_id": "rec1", "text": "Apple's first product, the Apple I, was released in 1976.", "category": "product"} {"_id": "rec2", "chunk_text": "Apples are a great source of dietary fiber.", "category": "nutrition"}

Layout: full

Condition: operation = "upsert_text"

Index Host

short-input

Placeholder: https://index-name-abc123.svc.project-id.pinecone.io

Layout: full

Condition: operation = "search_text"

Namespace

short-input

Placeholder: default

Layout: full

Condition: operation = "search_text"

Search Query

long-input

Placeholder: Enter text to search for

Layout: full

Condition: operation = "search_text"

Top K Results

short-input

Placeholder: 10

Layout: full

Condition: operation = "search_text"

Fields to Return

long-input

Placeholder: ["category", "text"]

Layout: full

Condition: operation = "search_text"

Filter

long-input

Placeholder: {"category": "product"}

Layout: full

Condition: operation = "search_text"

Rerank Options

long-input

Placeholder: {"model": "bge-reranker-v2-m3", "rank_fields": ["text"], "top_n": 2}

Layout: full

Condition: operation = "search_text"

Index Host

short-input

Placeholder: https://index-name-abc123.svc.project-id.pinecone.io

Layout: full

Condition: operation = "fetch"

Namespace

short-input

Placeholder: Namespace

Layout: full

Condition: operation = "fetch"

Vector IDs

long-input

Placeholder: ["vec1", "vec2"]

Layout: full

Condition: operation = "fetch"

Index Host

short-input

Placeholder: https://index-name-abc123.svc.project-id.pinecone.io

Layout: full

Condition: operation = "search_vector"

Namespace

short-input

Placeholder: default

Layout: full

Condition: operation = "search_vector"

Query Vector

long-input

Placeholder: [0.1, 0.2, 0.3, ...]

Layout: full

Condition: operation = "search_vector"

Top K Results

short-input

Placeholder: 10

Layout: full

Condition: operation = "search_vector"

Options

checkbox-list

Layout: full

Condition: operation = "search_vector"

Options: Include Values, Include Metadata

API Key

short-input

Placeholder: Your Pinecone API key

Layout: full

Inputs (API)

operation

string

Required

apiKey

string

Required

indexHost

string

Optional

namespace

string

Optional

model

string

Optional

inputs

json

Optional

parameters

json

Optional

records

json

Optional

searchQuery

string

Optional

topK

string

Optional

fields

json

Optional

filter

json

Optional

rerank

json

Optional

ids

json

Optional

vector

json

Optional

includeValues

boolean

Optional

includeMetadata

boolean

Optional

Outputs

Primary response type:

{
  "matches": "json",
  "upsertedCount": "number",
  "data": "json",
  "model": "string",
  "vector_type": "string",
  "usage": "json"
}

Tool Access

pinecone_generate_embeddingspinecone_upsert_textpinecone_search_textpinecone_search_vectorpinecone_fetch