Starstruk Logo MarkStarstruk

v2

multica-ai/multicav2Sep 6, 2024by thomashacker

AI Summary

A major version update introducing async ingestion with realtime logging, migration to Weaviate v4 Client, and a completely reworked Admin Interface and Suggestion logic. It features advanced chunking strategies (Semantic, Recursive, HTML), a new Document Explorer, and support for VoyageAI and custom metadata.

Key Highlights

  • Async Ingestion with realtime logging
  • Migrated to Weaviate v4 Client
  • New File Selection Interface and Directory Upload
  • Advanced Chunking: Semantic, Recursive, and HTML
  • Document Explorer with Vector View and PCA

New Features

  • Async ingestion
  • Weaviate v4 Client migration
  • New file selection interface
  • Directory upload support
  • Control settings per file/url
  • Multiple labels for documents
  • Config validation
  • HTML, Recursive, and Semantic Chunkers
  • Label and Document filtering
  • Multiple themes
  • Admin Interface rework
  • Suggestion logic rework
  • VoyageAI support
  • Custom metadata support
  • Document Explorer (Content, Chunk, Vector views)

Full Release Notes

# Importastic Verba Update (v2.0.0)  🚀 

## What's New?

## Added

- Async Ingestion with realtime logging
- Migrated to Weaviate v4 Client
- Added new File Selection Interface
- Add Directory Upload
- Control Settings per file/url individually
- Import individual files or all
- Overwrite existing files
- Add multiple labels to documents
- More configuration for readers, chunkers, and embedders
- Improved Document Search UI
- Add Config Validation
- Add HTML Reader
- Add Recursive Chunker
- Add HTML Chunker
- Add Markdown Chunker
- Add Code Import
- Add Code Chunking
- Add Semantic Chunking
- Label Filter
- Document Filter (Add document to chat)
- Add more themes
- Reworked Admin Interface
- Added Suggestion View
- Reworked Suggestion logic
- Added VoyageAI
- Added custom metadata
- Added DocumentExplorer with
  - Content View
  - Chunk View
  - Vector View
    - Visualize vectors of chunks of one or multiple documents
    - PCA

## To get started with Verba, simply run:

`pip install goldenverba`

or download the wheels.

Happy RAG! ❤️