Tool

Load Hubspot data into LlamaIndex for RAG applications

HubspotReader loads documents from HubSpot into LlamaIndex using private app access tokens.

Works with hubspotllamaindex

72
Spark score
out of 100
Updated 2 days ago
Version 0.14.23

Add to Favorites

Why it matters

Extract and load data from Hubspot CRM into LlamaIndex to enable retrieval-augmented generation and semantic search over customer relationship data.

Outcomes

What it gets done

01

Authenticate with Hubspot using private app access tokens

02

Extract documents and records from Hubspot CRM

03

Transform Hubspot data into LlamaIndex document format

04

Load processed data into LlamaIndex for indexing and retrieval

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/li-reader-readers-hubspot | bash

Overview

Hubspot Loader

HubspotReader is a Python loader that loads documents from HubSpot and formats them for LlamaIndex ingestion. It authenticates using access tokens from HubSpot private apps. Use HubspotReader when you need to load data from HubSpot into LlamaIndex. It requires a HubSpot private app access token for authentication.

What it does

HubspotReader is a data loader that loads documents from HubSpot into LlamaIndex. It authenticates via access tokens from HubSpot private apps.

When to use - and when NOT to

Use HubspotReader when you need to load data from HubSpot into LlamaIndex.

Do NOT use this loader if you need OAuth-based authentication for multi-user applications, as it currently only supports access token authentication via private apps.

Inputs and outputs

You provide a HubSpot access token obtained by creating a private app through the HubSpot developer portal. The loader returns documents formatted for LlamaIndex ingestion.

Installation:

pip install llama-index-readers-hubspot

Usage example:

import os

from llama_index.readers.hubspot import HubspotReader

reader = HubspotReader("<HUBSPOT_ACCESS_TOKEN>")
documents = reader.load_data()

Integrations

LlamaIndex: This loader is designed specifically as a data ingestion component for LlamaIndex, the data framework for building LLM applications. It outputs documents in LlamaIndex's native format for indexing and retrieval.

HubSpot Private Apps: Authenticates through HubSpot's private app access tokens, which you create following HubSpot's developer documentation for API access.

Who it's for

This tool is designed to be used as a way to load data into LlamaIndex.

Source README

Hubspot Loader

pip install llama-index-readers-hubspot

This loader loads documents from Hubspot. The user specifies an access token to initialize the HubspotReader.

At the moment, this loader only supports access token authentication. To obtain an access token, you will need to create a private app by following instructions here.

Usage

Here's an example usage of the HubspotReader.

import os

from llama_index.readers.hubspot import HubspotReader

reader = HubspotReader("<HUBSPOT_ACCESS_TOKEN>")
documents = reader.load_data()

This loader is designed to be used as a way to load data into LlamaIndex.

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.