v2.0.0

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! ❤️

v1.0.3

v1.0.3 🚀

What's New?

Added

• Cancel Generation Button
• Added .docx support
• Added Documentation for JSON Files
• Added GitLabReader (#151)
• Improved HuggingFace Embedding Models thanks to @tomaarsen
• MixedBreadEmbedder
• AllMPNetEmbedder

Fixed

• Check error logs coming from Ollama and send it to the frontend
• Check If Chunks Are NoneType
• #173
• #163
• #148

To get started with Verba, simply run:

pip install goldenverba==1.0.3

or download the wheels.

Happy RAG! ❤️

1.0.1 Beautiful Verba

Beautiful Verba Update (v1.0.0) 🚀

What's New?

Added

• Added DaisyUI
• Optimized frontend codebase
• Fully Reworked Verba Design
  • Fully Responsive, optimized for all screen sizes
• Customization Capabilities
  • Added Default, Darkmode, Weaviate themes
  • Full text, color, image customization
• Improve Chat Interface
  • Better formatting of markdown + code
  • Keep conversations saved in localBrowser storage
  • Better Debugging by providing more information about current states
• Improve Document Viewer Interface
  • Add Pagination
  • Add Sorting
  • Use Aggregation for Filtering
• Improve Status Overview
  • Reworked Frontend + Optimize Code
  • Sort status entries
  • Improve Loading Speed by using Aggregation
• Improve Component Selection for both Ingestion and RAG
  • Added new configuraiton that will be passed between frontend and backend
  • Cleaned codebase, merged interfaces and managers to single files
  • Added clean endpoints for better code readability
  • Reworked on interfaces
• Added better console and logging for ingestion
• More Configuration
  • Enable/Disable Caching and Autocomplete Suggestions
  • Improved verba_config.json
• Ability to enable/disable caching + autosuggestions
• Add Google Gemini as new Embedder and Generator
• Added .CSV support (all file types available in Unstructured IO)
• More test data
• Add Ollama as Generator and Embedding Component
• Add Support for Cohere R+
• Improved WindowRetriever Context Generation
• Show RAW Context in Frontend + Save in LocalStorage
• Save Settings and Configuration in Weaviate

Changed

• Changed to AppRouter framework
• Changed frontend project structure
• Changed backend project structure
• Removed Llama Generator Component

Fixed

• Using Accelerator Library

To get started with Verba, simply run:

pip install goldenverba

or download the wheels.

Happy RAG! ❤️

v0.4.0

Verba 0.4.0 Release 🚀

What's New?

Added

• Improved Docker Documentation
• Improved Docker Settings
• New Environment Variables for OpenAI proxies: OpenAI_BASE_URL (LiteLLM support)

Fixed

• Python not working on version 3.12, 3.11, and 3.9
• GitHub Links on README
• Fix Docker Default Vectorizer (#50)
• Fix requirements.txt spelling error
• Other minor Bug fixes

Changed

• Removed spaCy from project

To get started with Verba 0.4.0, simply run:

pip install goldenverba

Happy RAG! ❤️

v0.3.1

Verba 0.3.1 Release 🚀

What's New?

Added

• PDFReader powered by PyPDF2
• TokenChunker powered by tiktoken
• Ruff Linting (set as pre-commit)
• Markdown Formatting for chat messages (#48)

Fixed

• Added missing dependencies (chardet issue)
• Fixed restart bug
• Fixed MiniLM Cuda to_device bug (#41)
• Fixed Config Issues (#51)
• Fixed Weaviate Embedded Headers for Cohere

To get started with Verba 0.3.1, simply run:

pip install goldenverba

Happy RAG! ❤️

v0.3.0

Verba 0.3.0 Release - The Golden RAGtriever's Newest Update! 🚀

We're excited to announce the release of Verba 0.3.0 - a significant step forward for our Golden RAGtriever. This update brings a host of new features, improvements, and fixes to enhance your experience with our powerful Retrieval-Augmented Generation tool.

What's New in Verba 0.3.0?

Major Enhancements:

• Refactored Modular Architecture: We've restructured Verba for better performance and scalability.
• New Data Import Capabilities: Import data effortlessly through the frontend, CLI, and script.
• Advanced Readers and Chunkers: Introducing SimpleReader, PathReader, GithubReader, PDFReader, WordChunker, and SentenceChunker.
• Improved Embedders: ADAEmbedder, SentenceTransformer, and Cohere have been added for more robust data processing.
• Enhanced Generators: GPT3, GPT4, LLama, and Cohere are now available, offering versatile data generation options.
• Added Functionality: Enjoy a new Status Page, Reset functionality, Streaming Token Generation, Lazy Document Loading, Copy and Cached Tag, Improved Semantic Cache, and more.

Additional Features:

• Extended Model Support: LLama 2 and Cohere are now supported, alongside the latest OpenAI models.
• Enhanced Documentation: Dive into improved documentation and new technical docs and contribution guidelines.

Fixes and Tweaks:

• Improved Error Handling: We've addressed data ingestion errors and schema handling on startup.
• Refined Experience: Removed Simple- and AdvancedEngine logic for a streamlined user experience.

To get started with Verba 0.3.0, simply run:

pip install goldenverba

Join us in exploring this new frontier of data interaction and generation with Verba 0.3.0. Your feedback, as always, is invaluable to us, so please share your experiences and suggestions to help us continue improving Verba.

Happy RAG! ❤️

v0.2.3

First release of Verba The Golden RAGtriever! ✨

• Hybrid Search
• Chunk Window Retrieval
• Custom Data import
• Supports Weaviate Embedded, WCS, and Docker deployment
• Live Demo Release
• And many more!