I want to use a created dataset
I was following this video: https://www.youtube.com/watch?v=8uvHH-ocSes
to create a dataset. I created it.
The problem is that I am using python, and I want to import the dataset created to train it with llamaindex.
The documentation is here: https://llamahub.ai/l/apify-actor
In this documentation, is only included the way to create a new dataset scrapping with a url, without giving the option to train with the dataset of an id.
Apify
YouTube
Web Scraping Data for Generative AI - Learn how to feed your LLMs w...
In this video, we show you how to feed your large language models with web data using your favorite LLM integrations like š¦š LangChain, LlamaIndex š¦ or Pinecone, and Apify Actors, like Website Content Crawler. Find out how to get data for generative AI.
š¬ Join our AI and web scraping channel on Discord to continue the conversation:
https://dis...
2 Replies
absent-sapphireā¢2y ago
This notebook shows how to load Apify datasets to LangChain.
https://github.com/langchain-ai/langchain/blob/master/docs/extras/integrations/document_loaders/apify_dataset.ipynb
GitHub
langchain/docs/extras/integrations/document_loaders/apify_dataset.i...
ā” Building applications with LLMs through composability ā” - langchain-ai/langchain
fascinating-indigoOPā¢2y ago
I found in llamahub https://llamahub.ai/l/apify-dataset
This solves my problem, I have just to watch a little more of the video hehe
ā