💾 Instill Artifact

#About

💾 Instill Artifact orchestrates unstructured data to transform documents (e.g., HTML, PDF, CSV, PPTX, DOC), images (e.g., JPG, PNG, TIFF), audio (e.g., WAV, MP3 ) and video (e.g., MP4, MOV) into Instill Catalog - a unified AI-ready format. Instill Catalog is more than just a Knowledge Base; it is an Augmented Data Catalog for unstructured data and AI that ensures your data is clean, curated, and prepared for all of your future AI and Retrieval-Augmented Generation (RAG) needs.

💾 Instill Artifact can help with:

• Getting AI and RAG ready: Upload and process files into high-quality AI-ready data Catalogs.
• Simplicity: Operate via low-latency API calls, or at the click of a button with Instill Console.
• Integration: Seamlessly integrate with 💧 Instill VDP and ⚗️ Instill Model to provide a complete a full-stack AI solution.
• Transparency: Manage and view your data at the Catalog, file, or chunk levels.
• Data Integrity: Ensure AI application reliability with markdown-based source-of-truth.
• Scalability: Automate unstructured data transformation & growing data volumes efficiently.
• Versatility: Support for a plethora of unstructured, semi-structured, and structured file types and data sources.

#How it Works

When you upload files, 💾 Instill Artifact allows you to process their contents by extracting text data, which then undergoes chunking and embedding using preset 💧 Instill VDP pipelines.

Instill Catalog stores the chunk embeddings in a vector database for efficient search and retrieval. The processed chunks and original files are also stored within Instill Catalog, which defines a standardised AI-ready JSON object. This means that all data, encompassing unstructured, semi-structured, and structured data types, can be effortlessly ingested by 💧 Instill VDP to solve a wide array of downstream AI and data tasks.

Importantly, it also allows you to view and inspect the data in your Catalogs at different levels of granularity. Please see the View Files and View Chunks pages for more information.

#Limitations

During the Alpha Release period, the current Instill Cloud Catalog has the following limitations:

• Supported file types: .md, .txt, .pdf, .html , .ppt, .pptx, .doc, .docx, .xls, .xlsx and .csv
• Max file size:
  • Free tier: 50MB
  • Pro, Team & Enterprise tier: 150MB
• Max file storage (per namespace):
  • Free tier: 50MB
  • Pro tier: 500MB
  • Team tier: 2GB
  • Enterprise tier: Unlimited
• Max number of Catalogs (per namespace):
  • Free tier: 10
  • Pro tier: 50
  • Team & Enterprise tier: Unlimited