We added OpenAI's latest gpt-4o-2024-08-06 model to OpenAI Component on 💧 Instill VDP so you can build more reliable AI pipelines with Structured Outputs. This update enables you to define JSON schemas for model outputs, ensuring consistent, easily processable, and accurate responses that streamline workflows and enhance error handling. It is ideal for data analysts, developers, business intelligence teams, and customer service automation, particularly when working with large volumes of text data or building robust AI-powered applications that require reliable, structured information.

What's New

• OpenAI's latest model: gpt-4o-2024-08-06
• New response format option: json_schema

☁️ Instill Cloud demo

• structured-resume-screening

Improvements

• Removed the bottom credits balance
• Prevented deletion of catalogs under organizations
• Enhanced web operator scrape quality for markdown

Bug Fixes

• Resolved issue preventing users from scrolling in nodes within the pipeline-builder
• Corrected dual indicator display on Console
• Addressed organization credit consumption problem
• Fixed frontend not rendering backend error messages correctly
• Repaired broken Explore functionality in the Navigation Bar
• Resolved issue with iterator over pinecone-kb.output.matches Array

We added WhatsApp Component on 💧 Instill VDP to help you automate workflows and send template messages on WhatsApp. Construct useful workflows that can automate your work and unstructured data with any AI Component and then send the result as a message to anyone on WhatsApp.

Support tasks:

• Send Text Based Template Message
• Send Media Based Template Message
• Send Location Based Template Message
• Send Authentication Template Message
• Send Text Message
• Send Media Message
• Send Location Message
• Send Contact Message
• Send Interactive Call To Action Url Button Message

To request a new component, please gohere and click "Request A Component".

Elasticsearch is a distributed, RESTful engine with powerful search, analytics, and a scalable vector database, ideal for full-text and semantic search, as well as personalized recommendations.

We added Elasticsearch Component on 💧 Instill VDP to enable powerful and flexible solution for indexing, searching, updating, and deleting data within your Elasticsearch databases.

Support tasks:

• Search
• Vector Search
• Index
• Multi Index
• Update
• Delete
• Create Index
• Delete Index

To request a new component, please gohere and click "Request A Component".

Qdrant is a vector database and similarity search engine designed to handle high-dimensional vectors for performance and massive-scale AI applications.

We added Qdrant Component on💧 Instill VDP to integrate with the Qdrant vector search and storage solution and provide you with more flexibility and choice when it comes to vector database solutions.

Support tasks:

• Vector Search
• Batch Upsert
• Upsert
• Delete
• Create Collection
• Delete Collection

MongoDB is a NoSQL database that stores data in flexible, JSON-like documents, allowing for easy scalability and dynamic schema design, making it well-suited for handling large volumes of unstructured or semi-structured data in modern applications.

We added MongoDB Component on 💧 Instill VDP to enhance your data pipelines and connecting to your MongoDB databases.

Support tasks:

• Insert
• Insert Many
• Find
• Update
• Delete
• Drop Collection
• Drop Database
• Create Search Index
• Drop Search Index
• Vector Search

Weaviate is a vector database combining versatile vector and hybrid search capabilities with scalable, real-time operations on multi-modal data.

We added Weaviate Component on 💧 Instill VDP to expand your vector database options and enhance capabilities for managing and querying vector data efficiently.

Support tasks:

• Vector search
• Batch insert
• Insert
• Update
• Delete
• Delete Collection

To request a new component, please go here and click "Request A Component".

Fireworks AI is a generative AI inference platform to run and customize models with industry-leading speed and production readiness.

We added Fireworks AI Component on 💧 Instill VDP to unlock a wide range of natural language processing capabilities for your applications.

Support tasks:

• Text Generation Chat
• Text Embeddings

Models:

• llama3.1 (405B, 70B, 9B), llama3 (70B, 8B), gemma2-9b, phi-3-vision-128K, deepseek-coder, qwen2 (72B), nomic-ai/nomic-embed, thenlper/gte, WhereIsAI/UAE

☁️ Instill Cloud demo:

• fireworks-chinese-content-writer

Groq solutions are based on the Language Processing Unit (LPU), a new category of processor and LPUs run Large Language Models (LLMs) at substantially faster speeds and, on an architectural level, up to 10x better energy efficiency compared to GPUs.

We added Groq Component on 💧 Instill VDP to help you achieve fast AI inference at scale for your AI applications.

Supported tasks:

• Text generation chat with models: llama3.1, llama3, gemma2, gemma, and more

☁️ Instill Cloud demo

• groq-interview-helper

To request a new component, please gohere and click "Request A Component".

We recently launched 💾 Instill Artifact, the final piece that completes Instill Core as a full-stack AI infrastructure tool. Instill Artifact allows you to unify unstructured data from various sources on one platform and prepare it for AI and RAG tasks. Check out our blog for more details.

We've introduced the Artifact Component to 💧 Instill VDP, giving you the power to effortlessly build data pipelines that turn your files and documents into RAG-ready data. With this, you can easily retrieve relevant data from your catalog for AI chatbots, search, and recommendation systems. Plus, you can directly query your catalog and get instant, LLM-powered answers from your data.

Support tasks:

• Upload Files
• Get Files Metadata
• Get Chunks Metadata
• Get File In Markdown
• Match File Status
• Search Chunks
• Query

☁️ Instill Cloud demo

• talk-to-catalog

We're excited to introduce 💾 Instill Artifact, a new feature for orchestrating unstructured data like documents, images, audio, and video into Instill Catalog - a unified AI-ready Augmented Data Catalog format for unstructured data and AI applications.

💾 Instill Artifact can help with:

• Data Preparation: Create high-quality AI-ready data catalogs from uploaded files.
• Simplicity: Use low-latency API calls or Instill Console's one-click interface.
• Transparency: Access and control data at 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.
• Versatility: Process various unstructured, semi-structured, and structured data types and sources.
• Full-Stack AI Integration: Seamlessly connect with 💧 Instill VDP and ⚗️ Instill Model.

This release allows you to:

• Create your own Knowledge Base
• Upload files in formats like PDF, Markdown, and TXT
• View metadata for each Knowledge Base
• Examine "Catalog" details for uploaded files

This feature completes 🔮 Instill Core and lays the groundwork for developing full-stack AI solutions by ensuring your data is unified, clean, and ready for insight extraction.