mirror of
https://github.com/run-llama/llama-hub.git
synced 2025-08-13 11:11:48 +00:00
Readwise Reader
Use Readwise's export API to fetch your highlights from web articles, epubs, pdfs, Kindle, YouTube, and load the resulting text into LLMs.
Setup
- Get your Readwise API key from readwise.io/access_token.
Usage
Here is an example usage of the Readwise Reader:
import os
from llama_index import GPTVectorStoreIndex, download_loader
ReadwiseReader = download_loader("ReadwiseReader")
token = os.getenv("READWISE_API_KEY")
loader = ReadwiseReader(api_key=token)
documents = loader.load_data()
index = GPTVectorStoreIndex.from_documents(documents)
index.query("What was the paper 'Attention is all you need' about?")
You can also query for highlights that have been created after a certain time:
import os
import datetime
from llama_index import GPTVectorStoreIndex, download_loader
ReadwiseReader = download_loader("ReadwiseReader")
token = os.getenv("READWISE_API_KEY")
loader = ReadwiseReader(api_key=token)
seven_days_ago = datetime.datetime.now() - datetime.timedelta(days=7)
documents = loader.load_data(updated_after=seven_days_ago)
index = GPTVectorStoreIndex.from_documents(documents)
index.query("What has Elon Musk done this time?")
This loader is designed to be used as a way to load data into LlamaIndex and/or subsequently used as a Tool in a LangChain Agent. See here for examples.