No credit card required

Website Content Crawler

apify/website-content-crawler

No credit card required

Crawl websites and extract text content to feed AI models, LLM applications, vector databases, or RAG pipelines. The Actor supports rich formatting using Markdown, cleans the HTML, downloads files, and integrates well with 🦜🔗LangChain, LlamaIndex, and the wider LLM ecosystem.

Back to issues Create new issue

KV Store isn't downloading file attachments correctly

Closed

embrace_ai opened this issue

We recently initiated a crawl and noticed that some of the file attachments aren't being saved to the KV Store correctly.

For example, the file encountered at the URL below is 50 MB but the corresponding KV store entry is reporting 1.5 MB. Do we need to increase our download timeout in order to download the entire file in time?

https://barbercosmo.ca.gov/schools/healthsafety_textbook_ko.pdf
dc9f565-healthsafety_textbook_ko.pdf

Jindřich Bär (jindrich.bar)

Hello and thank you for your interest in this Actor!

I don't think there is anything you can do with this right now - this is most likely caused by the way we handle file downloads in this Actor. I started looking into this and already have a promising proof-of-concept for the patch, but before releasing it, I need to test this thoroughly.

I'll keep you posted with updates!

Thank you again for the report and sorry for the momentary inconvenience. Cheers!

Jindřich Bär (jindrich.bar)

This is fixed in the latest build of this Actor (0.3.33). Give it a try and let us know how it went.

Thank you again for your patience!

Add comment

Developer

Apify

Actor metrics

2.8k monthly users
317 stars
100.0% runs succeeded
4 days response time
Created in Mar 2023
Modified 1 day ago

Categories

Developer tools

Business

AI Content Markdown Scraper

quaking_pail/ai-content-markdown-scraper

This Apify Actor, "Website Content Crawler with Markdown Extraction," is designed to perform a comprehensive crawl of specified websites, extract their text content, convert it into Markdown format, and store it in a structured dataset. The extracted content is suitable for feeding LLMs.

AI_Builder

Website Screenshot Generator

apify/screenshot-url

Create a screenshot of a website based on a specified URL. The screenshot is stored as the output in a key-value store. It can be used to monitor web changes regularly after setting up the scheduler.

Apify

2.5k

Pinecone Integration

apify/pinecone-integration

This integration transfers data from Apify Actors to a Pinecone and is a good starting point for a question-answering, search, or RAG use case.

Apify

OpenAI Vector Store Integration

jiri.spilka/openai-vector-store-integration

The Apify OpenAI Vector Store integration uploads data from Apify Actors to the OpenAI Vector Store linked to OpenAI Assistant.

Jiří Spilka

Qdrant Integration

apify/qdrant-integration

Transfer data from Apify Actors to a Qdrant vector database.

Apify

Pinecone GPT Chatbot

tri_angle/pinecone-gpt-chatbot

Pinecone GPT Chatbot combines OpenAI's GPT models with Pinecone's database to generate insightful responses. Its interactive chatbot interface presents precise and comprehensive answers to user queries. Benefit from semantic understanding, efficient workflows, and enriched knowledge integration!

Tri⟁angle

WCC Pinecone Integration

tri_angle/wcc-pinecone-integration

Crawl any website and store its content in your Pinecone vector database. Enhance the accuracy and reliability of your own AI Assistant with facts fetched from external sources or connect this integration to our Pinecone GPT Chatbot assistant available in Apify Store.

Tri⟁angle

Website Content Vector Retriever

hamza.alwan/website-content-vector-retriever

Hamza Alwan

Neo4j Graph Creator

orange_knife-owner/neo4j

Create a Knowledge Graph of any Website! Knowledge graphs give you a good understanding of how a website is structured and can be used for RAG applications with the new hot field of GraphRAG!