Features
GPU-accelerated KNN and ANN vector search
In-database embedding generation (multiple models)
LLM text generation (Llama, Mistral, Mixtral)
Summarization and translation tasks
Supervised learning: regression, classification, clustering
Fine-tune LLMs on custom data
HNSW and IVFFlat indexing
Data preprocessing: splitting and chunking
SQL API for all ML operations
Python and JavaScript SDKs
Colocate data and compute for low latency
Open-source deployment (self-hosted)
Cloud service with managed GPUs
Privacy and security (on-premises option)
Integrates with PyTorch, TensorFlow, Hugging Face
Two-click AI web scraping from any website
Pre-built templates for Amazon, LinkedIn, Google Maps, Zillow, TikTok, and 20+ other sites
AI summarization, categorization, and translation of scraped data
Scrape articles, transcripts, and long-form text
Extract contact info from websites, PDFs, and images
Export scraped data to Google Sheets, Airtable, or Notion
Lead generation with data enrichment from Apollo, RocketReach, ThatsThem, Tracxn
Property listing aggregation from Zillow, Realtor.com, Redfin
Competitor monitoring for listings, pricing, reviews, and stock
Customer sentiment analysis from reviews and feedback
SEO monitoring: scrape meta tags, keywords, headings
Social media scraping for Twitter, TikTok, Instagram, Pinterest
E-commerce scraping for Amazon, eBay, Etsy, Shopify, Coles, Tradera
API endpoints: Distill, Extract, Batch, Search (POST /search for Google results)
13 SDKs (Java, Ruby, Rust, PHP, C#, Kotlin, Swift, Elixir, Dart, Bash) and 14 integrations