0.4.0

modelscope/FunASR0.4.0Jan 3, 2025by Mini256

AI Summary

This release introduces a beta evaluation tool for the Chat Engine, adds support for new LLM and embedding providers like Gitee AI and Amazon Bedrock, and includes improvements for file handling and user interface.

Key Highlights

Support for Evaluation (beta) tool with Factual Correctness and Semantic Similarity metrics
New LLM providers: Gitee AI, vLLM, and Xinference
New Embedding providers: Gitee AI and Amazon Bedrock
Configuration for upload file size limits via site settings
Support to download reference files in the chat page

New Features

Evaluation tool (beta)
Gitee AI LLM support
vLLM support
Xinference support
Amazon Bedrock embedding support
Gitee AI embedding support
Upload size limit configuration
Download reference file feature

Full Release Notes

## Highlights

- Support [Evaluation (beta)](https://tidb.ai/docs/evaluation) tool to evaluate the performance and reliability of the Chat Engine’s outputs  (by @Icemap @634750802 ).
  - Current support key metrics:
    - Factual Correctness
    - Semantic Similarity
- Support new LLM providers
  - [Gitee AI](https://tidb.ai/docs/llm#gitee-ai) (by @lc-soft)
  - Test new OpenAI-like providers (by @jrj5423)
    - [vLLM](https://tidb.ai/docs/llm#vllm)
    - [Xinference](https://tidb.ai/docs/llm#xinference)
- Support new embedding model providers
  - [Gitee AI](https://tidb.ai/docs/embedding-model#gitee-ai) (by @lc-soft)
  - [Amazon Bedrock](https://tidb.ai/docs/embedding-model#amazon-bedrock) (by  @jrj5423 @Mini256)

## Improvements

- Limit the upload file size via `max_upload_file_size` (10MB by default) parameter on site setting (by @sszgwdk @634750802 )
- Support download the reference file in the chat page (by @Rutheniumlmw @634750802 )

## New Contributors

* @sszgwdk made their first contribution in https://github.com/pingcap/autoflow/pull/497
* @jrj5423 made their first contribution in https://github.com/pingcap/autoflow/pull/522
* @Rutheniumlmw made their first contribution in https://github.com/pingcap/autoflow/pull/538
* @lc-soft made their first contribution in https://github.com/pingcap/autoflow/pull/470
* @nicognaW made their first contribution in https://github.com/pingcap/autoflow/pull/496

If you are deploying Autoflow using docker, please follow the [Upgrade](https://tidb.ai/docs/deploy-with-docker#upgrade) guide to upgrade your Autoflow.

**Full Changelog**: https://github.com/pingcap/autoflow/compare/v0.3.0...0.4.0