Starstruk Logo MarkStarstruk

v2.1

weaviate/Verbav2.1Dec 10, 2024by thomashacker

AI Summary

This release introduces new AI providers like Upstage and Groq, along with enhanced deployment options and Docker support. It features significant improvements in document processing capabilities, including audio support via AssemblyAI and better Markdown chunking. Additionally, the update resolves various bugs, including collection name conflicts and race conditions, while upgrading dependencies.

Key Highlights

  • Added new AI providers: Upstage (Reader, Embedder, Generator) and Groq.
  • Introduced a Custom deployment type and added Verba to Docker Hub.
  • Added AssemblyAI Reader for audio files and improved Markdown chunking.
  • Fixed collection name conflicts and race conditions in client creation.
  • System message is now a textarea and default deployment skips login screen.

Breaking Changes

  • Changed Collection names to prevent conflicts with older versions.
  • Changed Python version range to support versions below 3.13.

New Features

  • Upstage Reader, Embedder, and Generator support.
  • Custom deployment type and new port configuration.
  • Groq integration.
  • AssemblyAI Reader for audio file processing.
  • Language Detection for Chinese, English, French, German, and Dutch.
  • Improved Markdown Chunking logic.
  • Upgrade to latest Weaviate Client.
  • Ollama added to Docker Compose.
  • Verba added to Docker Hub.
  • Default deployment configuration skips the login screen.

Full Release Notes

## [2.1.0] Fixing Bugs and Adding Friends <3

## Added

- Added Upstage: Reader, Embedder, Generator (https://www.upstage.ai/)
- Added new deployment type: Custom
- Added new port configuration (https://github.com/weaviate/Verba/issues/308)
- Added Groq (https://github.com/weaviate/Verba/pull/278)
- AssemblyAI Reader for audio files (https://github.com/weaviate/Verba/pull/283)
- Language Detection for languages like chinese, english, french, german and dutch (https://github.com/weaviate/Verba/pull/302)
- Improve Markdown Chunking (https://github.com/weaviate/Verba/pull/323)
- Upgrade to latest Weaviate Client
- Added Ollama to Docker Compose
- Added Verba to Docker Hub
- Added default deployment to skip login screen (https://github.com/weaviate/Verba/issues/305)

## Fixed

- Catch Exception when trying to access the OpenAI API Embedding endpoint to retrieve model names
- Fixed reading empty string as environment variables (https://github.com/weaviate/Verba/pull/300)
- Fixed default Unstructed URL (https://github.com/weaviate/Verba/pull/295)
- Changed Collection names to prevent conflicts with other older Verba version generated collections
- Ensure Ollama URL is parsed correctly (https://github.com/weaviate/Verba/pull/327)
- Fixing typos (https://github.com/weaviate/Verba/pull/329)
- System Message is now a textarea in the frontend (https://github.com/weaviate/Verba/issues/334)
- Race Condition when multiple requests try to create same client (https://github.com/weaviate/Verba/issues/335)
- Fix wrong data types when querying additional chunks
- Remove legacy code (https://github.com/weaviate/Verba/issues/284)
- Change Python version range below 3.13
- Firecrawl Reader missing metadata (https://github.com/weaviate/Verba/issues/280)