Tool

Load Patent Abstracts from PatentsView API

LlamaIndex data loader that retrieves patent abstracts from Patentsview API using patent numbers, requiring an API key for authentication.

Works with patentsview

75
Spark score
out of 100
Updated 2 days ago
Version 0.14.23

Add to Favorites

Why it matters

Retrieve and load patent abstract data from the PatentsView database using patent numbers, enabling researchers and developers to integrate patent information into their AI applications and knowledge bases.

Outcomes

What it gets done

01

Authenticate with PatentsView API using environment variable credentials

02

Query patent abstracts by providing a list of patent numbers

03

Extract structured patent data from the PatentsView database

04

Format patent abstracts for ingestion into LlamaIndex data structures

Install

Add it to your toolbox

Run in your project directory:

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

Overview

Patentsview Loader

Patentsview Loader is a LlamaIndex data reader that retrieves patent abstracts from the Patentsview API using patent numbers. It requires an API key for authentication and returns structured abstract data ready for indexing in LlamaIndex workflows. Use this loader when you need to programmatically fetch patent abstracts by patent number for building search indexes, performing patent analysis, or augmenting LLM applications with patent data. It's designed for integration into LlamaIndex-based workflows.

What it does

Patentsview Loader is a LlamaIndex data reader that fetches patent abstracts from the Patentsview API using a list of patent numbers. It authenticates via an API key and returns structured patent abstract data ready for indexing and retrieval workflows in LlamaIndex applications.

When to use - and when NOT to

Use Patentsview Loader when you need to programmatically retrieve patent abstracts for specific patent numbers to build search indexes, perform patent analysis, or augment LLM applications with patent data.

Do NOT use this loader if you need full patent documents beyond abstracts, or if you require real-time patent filing data - the Patentsview API focuses on granted patents and their abstracts.

Inputs and outputs

You provide a list of patent numbers (as strings) and a valid Patentsview API key. The loader accepts the API key either as a constructor parameter or through the PATENTSVIEW_API_KEY environment variable.

You receive patent abstract data structured for LlamaIndex ingestion, ready to be indexed and queried within your LlamaIndex application.

Integrations

Patentsview Loader integrates with LlamaIndex as a data reader component. It connects to the Patentsview API, which requires an API key obtainable through the Patentsview support portal. The loader is designed for loading data into LlamaIndex.

Who it's for

This loader serves users who need to incorporate patent abstract data into their LlamaIndex applications.

Installation and usage

Install the package:

pip install llama-index-readers-patentsview

Basic usage example:

from llama_index.readers.patentsview import PatentsviewReader

loader = PatentsviewReader(api_key=os.getenv("PATENTSVIEW_API_KEY"))
patents = ["8848839", "10452978"]
abstracts = loader.load_data(patents)

The API key must be requested from the Patentsview support portal before use.

Source README

Patentsview Loader

pip install llama-index-readers-patentsview

This loader loads patent abstract from a list of patent numbers with API provided by Patentsview.

Note: The API now requires an API key which can be requested on this page.
PatentsviewReader looks for its value in the environmental variable PATENTSVIEW_API_KEY

Usage

Here'a an example usage of PatentsviewReader.

from llama_index.readers.patentsview import PatentsviewReader

loader = PatentsviewReader(api_key=os.getenv("PATENTSVIEW_API_KEY"))
patents = ["8848839", "10452978"]
abstracts = loader.load_data(patents)

This loader is designed for loading data into LlamaIndex.

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.