v0.5.2 release

feature

• add new multi role chat by @lcl6679292 in #445

fix

• fix: install default nltk data by @suluyana in #446
• hotfix transformers version 4.41 by @zzhangpurdue in #447
• allow_fork_pass_ci by @zzhangpurdue in #449

Full Changelog: v0.5.1...v0.5.2

v0.5.1 release

Features

• support GPT-4o and openai multi-modal compatible by @Zhikaiiii in #437

Bug Fixing

• fix tool import bugs by @zzhangpurdue in #438
• fix modelsope local deployment by @zhangsibo1129 in #433

New Contributors

• @zhangsibo1129 made their first contribution in #433

Full Changelog: v0.5.0...v0.5.1

v0.5.0 release

What's Changed

Features

• Add Assistant API server with v1/chat/completion for tool calling, and v1/assistant/lite for agent running.
• Add Tool Manager API server, allow user executes utilities in isolated, secure containers.
• Add rag workflow based on llama-index
• Add automatic stop words finding for different LLM's special token.
• Support llama3.

Full Changelog: v0.4.1...v0.5.0

v0.4.1 release

What's Changed

Features

• 🔥 The Ray version of multi-agent solution is on modelscope-agent, please find the document
• update distributed instantiation method for multi-agent method to allow multi user run case in a same ray cluster
• fix bugs introduced by multi-agent

Demos & Apps

• multi-role chatroom use case support multi user & update prompt for multi-agent

Full Changelog: https://github.com/modelscope/modelscope-agent/commits/v0.4.1

v0.4.0 release

What's Changed

Features

• 🔥 The Ray version of multi-agent solution is on modelscope-agent, please find the document
• add a simple server api in apps/agentfabric, which is also the api running on modelscope studio
• add tool lazy load, so that it will not load all tools at starting.
• add token count in memory module.
• update agent loop logic make the result much more solid.

Demos & Apps

• multi-role chatroom and videogen by multi agent in apps based multi-agent framework
• using local model as llm by vllm in demos
• multi-round example with memory in demos

Full Changelog: https://github.com/modelscope/modelscope-agent/commits/v0.4.0