liujiangning30
581d9fb898
support demo with hf ( #179 )
2024-03-26 17:59:01 +08:00
RangiLyu
26672731e9
feat: support vllm ( #177 )
...
* feat: support vllm
* update requirements
2024-03-21 17:20:38 +08:00
liujiangning30
466d7aa24d
Fix errmsg: cast dict to str ( #172 )
2024-03-20 14:27:04 +08:00
tackhwa
5f55e12736
fix typo "ablility " in overview.md ( #175 )
...
fix type "ablility " in overview.md
2024-03-20 14:26:33 +08:00
liujiangning30
e16a6bfc3a
Fix bug of ppt and googlescholar ( #167 )
...
* fix bug of ppt and googlescholar
* Format required parameters
2024-03-04 13:52:06 +08:00
BraisedPork
605a921878
Fix chat return of GPTAPI ( #166 )
...
fix chat return data
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
2024-02-29 13:56:10 +08:00
liujiangning30
4fd014bebf
update version ( #161 )
2024-02-23 19:50:49 +08:00
liujiangning30
432ffaae8a
fix bug caused by static model_name ( #156 )
2024-02-21 14:47:40 +08:00
liukuikun
a64aa599ce
fix batch generate ( #158 )
2024-02-20 15:11:42 +08:00
liujiangning30
662011783e
Feat: no_skip_speicial_token ( #148 )
...
* Feat: no_skip_speicial_token
* fix: get_logger of lmdeploy
* update lmdeploy requirement
2024-02-19 16:33:13 +08:00
loveSnowBest
3cf20f5011
support inference for pad_token & chatglm chat ( #157 )
...
* update code for chatglm
* update code
* handle batch infer for chat
* update warning for cases
2024-02-19 15:54:48 +08:00
liujiangning30
7b71988d09
max_tokens to max_new_tokens ( #149 )
...
* Fix: max_new_tokens to max_tokens
* change `max_tokens` to `max_new_tokens` in API models
* max_tokens to max_new_tokens
* inject parameter 'max_new_tokens' for examples
---------
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
2024-02-06 12:08:53 +08:00
liujiangning30
90ef5215b6
Fix: gen_config in lmdeploypipeline updated by input gen_params ( #151 )
2024-02-05 15:53:08 +08:00
liujiangning30
6a5447663a
Fix: filter_suffix in TritonClient ( #150 )
2024-02-04 17:36:52 +08:00
liujiangning30
a2c23ef9dd
Fix: skip start_token ( #145 )
2024-02-02 16:09:46 +08:00
liukuikun
3be9ec042c
[Enchance] lazy import for actions ( #146 )
2024-02-02 15:44:27 +08:00
BraisedPork
aa5a357a34
Fix type annotation ( #144 )
...
fix type annotation
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
2024-02-02 11:19:45 +08:00
liukuikun
5650a75f3e
update readme demo ( #143 )
2024-02-01 23:09:47 +08:00
liujiangning30
eea6e1cb56
fix bug of TritonClient ( #141 )
2024-02-01 20:40:37 +08:00
liujiangning30
42c6d265e1
Fix bug of LMDeployClient ( #140 )
...
* Fix bug of LMDeployClient
* fix bug of web_demo
2024-02-01 17:58:10 +08:00
BraisedPork
e20a768066
[Version] Bump v0.2.1 ( #139 )
...
bump v0.2.1
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
2024-02-01 13:14:26 +08:00
BraisedPork
60244a253a
Fix docstring format of GoogleScholar ( #138 )
...
* fix docstrings
* update pre-commit-hooks
* chores
---------
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
2024-02-01 13:11:07 +08:00
liukuikun
990828ceb2
[Version] Bump 0.2.0 ( #136 )
2024-01-31 21:41:35 +08:00
liujiangning30
b2e6d0ee7a
Feat: support stream output in cli_demo ( #137 )
...
* Feat: support stream output in cli_demo
* support generation in cli_demo
2024-01-31 21:33:46 +08:00
liujiangning30
fda869162b
Fix bug of lmdeploy.LMDeployServer ( #132 )
2024-01-31 21:15:57 +08:00
liujiangning30
baeed6ed88
remove exception catch in hf ( #135 )
2024-01-31 21:15:25 +08:00
liujiangning30
94959c16da
update default prompt ( #133 )
2024-01-31 21:15:06 +08:00
liukuikun
d61dc03079
precommit run all ( #134 )
2024-01-31 21:09:19 +08:00
liujiangning30
190fb731be
Feat: support stream_chat in hf ( #131 )
...
* Feat: support stream_chat in hf
* update docstring
2024-01-31 20:37:16 +08:00
BraisedPork
f887b423fa
Update README files ( #117 )
...
* update README
* introduce features
* add demo
---------
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
2024-01-31 20:36:57 +08:00
liujiangning30
35331a5016
Feat: add cli_demo and del unnecessaries ( #124 )
...
* Feat: add cli_demo and del unnecessaries
* support agent_cli_demo
2024-01-31 19:24:07 +08:00
BraisedPork
5dc6fb5b3d
Encapsulate IPython InteractiveShell ( #128 )
...
* add IPython Shell
* add docstrings
* fix docstrings
* add docstrings
---------
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
2024-01-31 19:13:24 +08:00
BraisedPork
7489767651
Modify parameter descriptions in parsers ( #130 )
...
switch parameter descriptions to English
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
2024-01-31 19:12:40 +08:00
BraisedPork
83437b081f
Fix requirements ( #129 )
...
fix requirements
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
2024-01-31 17:51:07 +08:00
BraisedPork
3d9992182e
Fix action results ( #127 )
...
fix action results
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
2024-01-31 17:50:47 +08:00
BraisedPork
ca1ab4b5ec
Fix conf_py_path for zh_CN docs ( #126 )
...
fix conf_py_path
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
2024-01-31 16:20:49 +08:00
liujiangning30
f974a7bd39
Feat: support response from FinishAction ( #122 )
2024-01-31 16:09:14 +08:00
BraisedPork
d943becaec
Modify levels of readthedocs configuration ( #125 )
...
fix readthedocs config
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
2024-01-31 15:51:04 +08:00
BraisedPork
f90010c867
Add readthedocs configuration for zh_CN ( #123 )
...
* configure readthedocs
* remove unmaintained docs
---------
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
2024-01-31 14:58:00 +08:00
liujiangning30
ae3c7c37a6
Fix bug ( #121 )
...
* rename parameter 'max_out_len' of base_api to 'max_tokens'
* fix bug of hf
2024-01-31 13:36:01 +08:00
BraisedPork
559275daf4
Fix Annotated import error ( #120 )
...
fix typing
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
2024-01-31 13:35:15 +08:00
liujiangning30
c7c46785bb
Feat: strip ModelStatus from AgentState ( #115 )
...
* Feat: strip ModelStatus from AgentState
* update schema
* fix bug of modelStatus
2024-01-30 22:53:37 +08:00
liujiangning30
c9973b9558
fix bug of HFTransformer.generate ( #118 )
2024-01-30 22:52:43 +08:00
liujiangning30
94ba3a1a75
add docstring ( #116 )
...
* BaseLLm generate docstring
2024-01-30 19:30:40 +08:00
Sean
76a46c9a8c
Update internlm2_agent.py ( #114 )
...
fix typo
2024-01-30 16:36:29 +08:00
liujiangning30
d4a71f40b5
Fix: outputs with same format ( #112 )
...
model outputs with the same format
2024-01-30 16:36:08 +08:00
BraisedPork
5581fad8ce
Validate actions implement run XOR other tool APIs ( #111 )
...
Validate actions implement `run` XOR other tool APIs
2024-01-30 15:12:25 +08:00
liukuikun
95b68c821a
[Refactor] Refactor Lagent ( #97 )
...
* Feature: redesign BaseModel (#80 )
* redesign BaseModel
* update docstring
* update baseModel
* [Refactor] improve `Action` and `ActionExecutor` (#83 )
* [Fix]: fix turbomind (#81 )
fix turbomind
* add parsers
* skip ActionReturn in postprocessing
* check existence of API name
* add exception catch in action executing
* validate input arguments
* modify returned structure of `get_actions_info`
* adapt tools to the new protocol
* remove `LLMQA` action
---------
Co-authored-by: RangiLyu <lyuchqi@gmail.com >
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
* [Feature] add tools (#89 )
* add new tools
* update PPT
* chores
* update action module init
---------
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
* rename func 'completion' to 'generate' (#90 )
* [Feature] support batch inference in API models (#91 )
* implement `chat`
* update agent interfaces
* redundancy reduction
---------
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
* Feature: lmdeploy_wrapper implemented BaseMode (#86 )
* [Fix]: fix turbomind (#81 )
fix turbomind
* Feature: lmdeploy_wrapper implemented BaseMode
* remove comments of 'llms.__init__'
* update of 'llms.__init__'
* update lmdepoly_wrapper with 'gen_params'
* add property 'state_map' in __init_ and use APIClient to stream infer_
* func 'generate' in LMDeployClient with 'APIClient'
* fix bug of TritonClient
* add docstr for LMDeployPipeline & LMDeployServer
* class LMDeployClient inherits class LMDeployServer
* LMDeployClient with BaseModel.__init__ and use field 'max_tokens' control model output
* add TODO
* move 'import mmengine' to func '_update_gen_params'
---------
Co-authored-by: RangiLyu <lyuchqi@gmail.com >
* Fix APITemplateParser object is not callable (#95 )
fix APITemplateParser object is not callable
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
* [Feat] support StreamAgent (#82 )
* [Feat] support StreamAgent
* update `StreamAgent`
* truncate inner history
---------
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
* [Feat] hf llm implemented BaseMode (#92 )
* Feature: huggingface implemented BaseMode
* hf llm implemented BaseMode
* fix bug of hf llm
* inject attention_mask during inference
* remove unnecessary
* [Feature] support building tool descriptions automatically (#96 )
* redundancy reduction
* add `tool_api` to annotate a tool method
* improve json parsing
* enhance parsers
* update README.md
---------
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
* Enhance tool annotation (#98 )
improve `tool_api`
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
* [Docs] initialize the documentation (#99 )
init the docs
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
* Modify the structure of `ActionReturn`'s result (#102 )
* modify the struction of action results
* fix docstrings
---------
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
* Fix .readthedocs.yml (#104 )
fix rtd config
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
* [Feature] support IPython interpreter action (#103 )
* add ipython interpreter
* update requirements
* remove `return_list` argument
---------
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
* Fix BINGMap key (#105 )
fix the fallback value
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
* StreamAgent infer demo (#106 )
* update cfg & fix bug of StreamAgent
* fix bug of func 'stream_chat'
* streamlit demo with full response
* enchance stream chat
* fix bug of stream chat
* fix and file rename
* add exception catch for func 'chat'
---------
Co-authored-by: liujiangning <liujiangning@pjlab.org.cn >
* [Docs] Add action tutorials (#107 )
* add `get_started` chapter
* fix docstrings
* add action.md
* add zh docs
---------
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
* Fix returns of OpenAI interface (#108 )
fix `BaseAPIModel` chat returns
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
* Feat: add warn for func 'generate_from_template' (#109 )
* add warn for func 'generate_from_template'
* clearer alerts for deprecation
* clearer alerts for deprecation
---------
Co-authored-by: liujiangning30 <147385819+liujiangning30@users.noreply.github.com >
Co-authored-by: BraisedPork <46232992+braisedpork1964@users.noreply.github.com >
Co-authored-by: RangiLyu <lyuchqi@gmail.com >
Co-authored-by: wangzy <wangziyi@pjlab.org.cn >
Co-authored-by: liujiangning <liujiangning@pjlab.org.cn >
2024-01-30 12:48:21 +08:00
liukuikun
85b91cc652
[Version] v0.1.3 ( #110 )
...
update version
2024-01-30 11:32:56 +08:00
liujiangning30
c89729620f
update ReAct example for internlm2 ( #85 )
...
* update ReAct example for internlm2
* update ReAct example for internlm2
* update base_llm
* rename file
* update readme
* update meta_template
2024-01-23 10:57:58 +08:00
