v0.2.3

What's Changed

• Fix chat return of GPTAPI by @braisedpork1964 in #166
• Fix bug of ppt and googlescholar by @liujiangning30 in #167
• fix typo "ablility " in overview.md by @tackhwa in #175
• Fix errmsg: cast dict to str by @liujiangning30 in #172
• feat: support vllm by @RangiLyu in #177
• support demo with hf by @liujiangning30 in #179
• fix bug of Internlm2Protocol.parse by @liujiangning30 in #180
• Fix generation parameters in API models by @braisedpork1964 in #181
• support batch by @Harold-lkk in #182
• fix deprecated top_k for GPTAPI by @Iiji in #185
• support json mode and proxy by @Harold-lkk in #189
• Allow access to code from interpreter results by @braisedpork1964 in #191
• Fix: typo for lmdeploy_wrapper by @fanqiNO1 in #171
• Feat: stream chat for GPTAPI by @liujiangning30 in #194
• align streaming return format for GPTAPI by @liujiangning30 in #196
• stream chat for GPTAPI by @liujiangning30 in #197
• Mind search by @Harold-lkk in #208
• Fix: update requirements by @Liqu1d-G in #214
• role with name by @liujiangning30 in #215
• Bump to v0.3.0 by @liujiangning30 in #213
• Bump to v0.2.3 by @liujiangning30 in #216

New Contributors

• @tackhwa made their first contribution in #175
• @Iiji made their first contribution in #185
• @fanqiNO1 made their first contribution in #171
• @Liqu1d-G made their first contribution in #214

Full Changelog: v0.2.2...v0.2.3

v0.2.2

What's Changed

• Fix bug of LMDeployClient by @liujiangning30 in #140
• fix bug of TritonClient by @liujiangning30 in #141
• update readme demo by @Harold-lkk in #143
• Fix type annotation by @braisedpork1964 in #144
• [Enchance] lazy import for actions by @Harold-lkk in #146
• Fix: skip start_token by @liujiangning30 in #145
• Fix: filter_suffix in TritonClient by @liujiangning30 in #150
• Fix: gen_config in lmdeploypipeline updated by input gen_params by @liujiangning30 in #151
• max_tokens to max_new_tokens by @liujiangning30 in #149
• support inference for pad_token & chatglm chat by @zehuichen123 in #157
• Feat: no_skip_speicial_token by @liujiangning30 in #148
• fix batch generate by @Harold-lkk in #158
• fix bug caused by static model_name by @liujiangning30 in #156
• update version by @liujiangning30 in #161

Full Changelog: v0.2.1...v0.2.2

v0.2.1

What's Changed

• Fix docstring format of GoogleScholar by @braisedpork1964 in #138
• [Version] Bump v0.2.1 by @braisedpork1964 in #139

Full Changelog: v0.2.0...v0.2.1

v0.2.0

What's Changed

• Stream Output: Provides the stream_chat interface for streaming output, allowing cool streaming demos right at your local setup.

• Interfacing is unified, with a comprehensive design upgrade for enhanced extensibility, including:

  • Model: Whether it's the OpenAI API, Transformers, or LMDeploy inference acceleration framework, you can seamlessly switch between models.
  • Action: Simple inheritance and decoration allow you to create your own personal toolkit, adaptable to both InternLM and GPT.
  • Agent: Consistent with the Model's input interface, the transformation from model to intelligent agent only takes one step, facilitating the exploration and implementation of various agents.

• Documentation has been thoroughly upgraded with full API documentation coverage.

Welcome to watch our demo at https://www.youtube.com/watch?v=YAelRLi0Zak

Lagent Release v0.1.3

The last release for version 0.1

What's Changed

• update: add citation by @liujiangning30 in #56
• added korean readme since most of the koreans dont at all speakkorean by @bhargavshirin in #57
• Update README.md by @Killer2OP in #59
• [ADDED]: Back-to-Top Button in README by @Killer2OP in #65
• changed "Twitter" to "𝕏 (Twitter)" in README.md by @BandhiyaHardik in #67
• Update README.md by @apu52 in #62
• Update README.md by @Aryan4884 in #58
• Update README.md by @VinayKokate22 in #68
• update README.md and header-logo by @liujiangning30 in #70
• update header-logo by @liujiangning30 in #72
• Fixed: Added contributors section to readme.md . by @Kalyanimhala in #63
• [Fix] lmdeploy bc by @Harold-lkk in #74
• 【Bug】Fix templateparser by @Harold-lkk in #77
• [Fix]: fix turbomind by @RangiLyu in #81
• update ReAct example for internlm2 by @liujiangning30 in #85
• [Version] v0.1.3 by @Harold-lkk in #110

New Contributors

• @bhargavshirin made their first contribution in #57
• @Killer2OP made their first contribution in #59
• @BandhiyaHardik made their first contribution in #67
• @apu52 made their first contribution in #62
• @Aryan4884 made their first contribution in #58
• @VinayKokate22 made their first contribution in #68
• @Kalyanimhala made their first contribution in #63
• @RangiLyu made their first contribution in #81

v0.1.2

Bump version v0.1.2 (#55)

Lagent Release v0.1.1

Main Features

• Support multiple kinds of agents out of the box. Lagent now supports ReAct, AutoGPT, and ReWOO, which can drive the large language models(LLMs) for multiple trials of reasoning and function calling.
• Extremely simple and easy to extend. The framework is quite simple with a clear structure. With only 20 lines of code, you are able to construct your own agent. It also supports three typical tools: Python interpreter, API call, and Google search.
• Support various large language models. We support different LLMs, including API-based (GPT-3.5/4) and open-source (LLaMA 2, InternLM) models.