Xiaoyun Zhang
5f7c34ac72
[.Net] Remove Workflow class && bump version to 0.0.14 ( #2675 )
...
* remove workflow class
* bump version to 0.0.14
2024-05-13 21:58:50 +00:00
Victor Dibia
d50f654748
Rewrite AutoGen Studio Database Layer to Use SQLModel ORM ( #2425 )
...
* update orm branch + accesibility tweaks
* general file location refactor
* add support for LocalCommandLineCodeExecutor and DockerCommandLineCodeExecutor
* update code execution config laoding
* version update
* bump version rc1
* add model type selection (openai , gemini, azure)
* add ability to test workflow
* psycopg3 support
* add close logic to build tab pop ups, enable testing of workflows in build view
* updates to dbmanager, version bump
* add max_tokens default value
* ensure sessions are used correctly in dbmanager
* initial support for migrations
* update sessions/workflow api routing for clarity.
* general refactor, + add support for initial sample workflows
* orm branch updates
* Removed incorrect Git LFS files
* update git lfs tracking
---------
Co-authored-by: Audel Rouhi <knucklessg1@gmail.com >
2024-05-11 14:31:21 +00:00
R. Singh
60c665871a
Feature: Add ability to use a separate python environment in local executor ( #2615 )
...
* Add ability to use virtual environments in local executor
* Copy environment variables from parent environment
* Fix mypy errors and formatting
* Account for venv on Windows
* Use a virtual environment context object instead of path
* Add utility method to create a virtual environment
* Remove assertion using `_venv_path`
* Add tests for `create_virtual_env`
* Modify test code and add output assertion
* Modify test code and assertion
* Execute activation script before actual command on windows
* Add docs for using a virtual env
2024-05-11 06:25:20 +00:00
Adam Hultman
8276ad3db6
fix agent optimizer nb typo ( #2642 )
2024-05-10 23:06:27 +00:00
Mark Sze
a86c474339
Resuming a GroupChat ( #2627 )
...
* Initial resume
* Cleaned up resume function
* Further updating resuming group chat
* Added async resume_chat and documentation
* Added test cases, refined group chat function parameters
* compiled documentation
* Added tests to main
* Removed mdx file.
* Revert "Merge remote-tracking branch 'origin/main' into groupchatresume"
This reverts commit 8f709308f08bfcb2bff1ekzhu@users.noreply.github.com >
2024-05-10 22:56:25 +00:00
Xiaoyun Zhang
e509549a01
update ( #2655 )
2024-05-10 22:41:56 +00:00
Simon Podhajsky
b5d856dd36
Add instructions for Docker issue with hash mismatch to FAQ ( #2639 )
...
* Add instructions for Docker issue with hash mismatch to FAQ
* Make pre-commit happy
2024-05-10 07:02:31 +00:00
Mohamed A. Fouad
6dd2b59da4
Update graph_utils.py ( #2601 )
...
* Update graph_utils.py
Adds save_speaker_transitions_dict
* Update graph_utils.py
Adds export_path:str which defaults to None into visualize_speaker_transitions_dict. In there, run plt.savefig(path) if export_path is not None
* Update graph_utils.py
* Update graph_utils.py
Adds export_path functionality to visualize_speaker_transitions_dict()
---------
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
2024-05-10 00:29:35 +00:00
Xiaoyun Zhang
ca8bf89673
update release note ( #2641 )
2024-05-09 23:03:07 +00:00
Xiaoyun Zhang
374270f9c7
[.Net] Add KernelPluginMiddleware in AutoGen.SemanticKernel ( #2595 )
...
* add kernel function middleware
* update
* fix format
* fix build error
2024-05-09 22:36:20 +00:00
Thong Q. Nguyen
648dad5c40
Fix chess example ( #2631 )
2024-05-09 17:35:00 +00:00
Jack Gerrits
30e06cee10
Update prototype.py
2024-05-08 23:52:18 -04:00
David Luong
b529fe21a3
[.Net]: Introduce ChatCompletionAgent to AutoGen.SemanticKernel package ( #2584 )
...
* WIP add SKAgent to proj
* Fix Unit test
* Remove accidental coommit
* Add version props
* Revert Kludge test changes
* PR comments : executionSettings and use / upgrade SemanticKernelExperimentalVersion
* Add back deleted api and constructor, mark as Obsolete
* PR feedback : Introduce SemanticKernelChatCompletionAgent. Add unit tests and refactor semanticKernelChatMessageContentConnector to be SkSequentialChatMessageContentConnector.cs
* Revert SkSequentialChatMessageContentConnector
* PR comments, remove systemMessage in SemanticKernelChatCompletionAgent
* Fix formatting
* Fix bad merge
* Revert "Fix bad merge"
This reverts commit a189ad9f42luongdavid@microsoft.com >
2024-05-09 03:50:36 +00:00
Xiaoyun Zhang
5be103ab6b
[.Net] Add an example to show how to connect to third party OpenAI API endpoint + upgrade Azure.AI.OpenAI package ( #2619 )
...
* update
* update
* add blog
2024-05-08 23:56:16 +00:00
Jack Gerrits
0c08ca30a1
Create prototype.py
2024-05-07 18:18:58 -04:00
Microsoft Open Source
982b1ba716
README.md committed
2024-05-07 15:12:56 -07:00
Microsoft Open Source
0bf1e7b57a
SECURITY.md committed
2024-05-07 15:12:56 -07:00
Microsoft Open Source
3a6683af4f
SUPPORT.md committed
2024-05-07 15:12:55 -07:00
Microsoft Open Source
43567233ca
LICENSE committed
2024-05-07 15:12:54 -07:00
Microsoft Open Source
02d4448bb1
CODE_OF_CONDUCT.md committed
2024-05-07 15:12:54 -07:00
microsoft-github-operations[bot]
edfb95257f
Initial commit
2024-05-07 22:12:52 +00:00
Xiaoyun Zhang
f75103f254
[.Net] fix #2609 ( #2618 )
...
* add lmstudio agent to assistant agent
* fix #2609
* update updatelog
* Update Directory.Build.props
2024-05-07 21:37:46 +00:00
Carlos Garcia Lalicata
949520bba6
[marketing sample] Several Improvements ( #55 )
...
* cleaning marketing sample
* Clean up ignored files
* Clean up ignored files
* adding missing gitignore in the backend
* tons of improvements towards azd
* azd up works
2024-05-06 23:06:50 +02:00
Rob
ecc4113a7e
fix: event logging with nested chats ( #2600 )
...
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
2024-05-06 18:51:45 +00:00
Ikko Eltociear Ashimine
da52c0246c
docs: update tutorial.ipynb ( #2606 )
...
Creat -> Create
2024-05-06 16:26:49 +00:00
r48Bit
9418b179c2
Update to correct pip install for litellm ( #2602 )
...
The doc mentions `pip install litellm[proxy]` which won't work. The correct command is `pip install 'litellm[proxy]'`.
2024-05-06 16:18:01 +00:00
zbram101
498aa7f367
notebook showing assistant agents connecting azure ai search and azur… ( #2594 )
...
* notebook showing assistant agents connecting azure ai search and azure identity
* formatting fix for notebook azr_ai_search
---------
Co-authored-by: Bharadwaj Ramachandran <bharadwajramachandran@Bharadwajs-MacBook-Pro.local >
2024-05-06 16:12:00 +00:00
Wael Karkoub
372ac1e794
Text Compression Transform ( #2225 )
...
* adds implementation
* handles optional import
* cleanup
* updates github workflows
* skip test if dependencies not installed
* skip test if dependencies not installed
* use cpu
* skip openai
* unskip openai
* adds protocol
* better docstr
* minor fixes
* updates optional dependencies docs
* wip
* update docstrings
* wip
* adds back llmlingua requirement
* finalized protocol
* improve docstr
* guide complete
* improve docstr
* fix FAQ
* added cache support
* improve cache key
* cache key fix + faq fix
* improve docs
* improve guide
* args -> params
* spelling
2024-05-06 14:16:49 +00:00
Kosta Petan
6199104a59
update packages ( #54 )
2024-05-06 13:40:53 +02:00
Carlos Garcia Lalicata
cbf42523cc
[Ongoing] Adding Marketing sample ( #52 )
...
* boilerplate init
* agents work
* agents
* adding frontend
* Now we can call the actor directly, and indireclty
* Orleans packages need to be there in order serialization works. no clue why
* horrible code, making the signlar hub static
* more horrible code, now the frontend can send messages to the backend and receibe the answer
* marketing works. a lot to fix still
* adding a legal assistant
* breaking agents
* adding a signalr client
* adding AlreadyExistentUser
* cleaning up
* renaming solution
* cleaning to prep for push to upstream
* cleaning in prep for upstream
* cleaning and forcing agents to always have a state
* removing legal-assistant for now
* sln should not bethere
* creating the class using new T
* replacing Activator by where T : new
* removing infra from marketing sample
* Add state initialization in AiAgent
* changing namespace name, and creating an agent to interact with signalr
* signalr agent works fine. It just loops forever when connecting. I need to diferentiate if it already happened
* init Readme.md
* Using Semantic Kernel to run Dall-E
* Graphic designer does not ened its own openai client anylonger
2024-05-06 10:27:36 +02:00
Erez A. Korn
5a3a8a5541
Correct link to Jupyter Code Executor in code-executors.ipynb ( #2589 )
...
* Correct link to Jupyter Code Executor in code-executors.ipynb
The link to the code executor was referencing the wrong folder.
* Update website/docs/tutorial/code-executors.ipynb
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com >
* Update website/docs/tutorial/code-executors.ipynb
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com >
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com >
2024-05-06 03:19:33 +00:00
Shaokun Zhang
e3a7e8a37e
Update AgentOptimizer BibTeX ( #2578 )
...
* update paper
* update
---------
Co-authored-by: “skzhang1” <“shaokunzhang529@gmail.com ”>
Co-authored-by: Jieyu Zhang <jieyuz2@cs.washington.edu >
2024-05-06 00:58:49 +00:00
Xiaoyun Zhang
e878be55a3
[.Net] refactor over streaming version api ( #2461 )
...
* update
* update
* fix comment
2024-05-05 14:51:00 +00:00
Abdur Rahman Nawaz
4711d7bb9c
Fix for http client ( #2579 )
...
* Fix for http client
* fixed constructor to only ignore the http_client while copying
* fixed comment formating
* removed check for http_client and added error message with docs
* fix formatting
* fix formatting
* added test for http-fix
* changed title and content of docs
* changed test func name
2024-05-04 14:12:36 +00:00
Ian
3a4bb088f7
add faq for autogen and openai assistant compatible version ( #2587 )
2024-05-04 06:56:50 +00:00
Eric Zhu
093c1a26e3
Add note in the lfs check action to help contributors fix Git LFS check failure. ( #2563 )
...
* Add note in the lfs check action.
* Update lfs-check.yml
2024-05-03 15:16:59 +00:00
Ian
bf0c49d96f
Add a guide doc for GPTAssistantAgent ( #2562 )
...
* add a oai assistant agent guide
* add a oai assistant agent guide
* polish
* address comments
* remove useless type ingnore comments
* fix ci
---------
Co-authored-by: Ian Zhai <ian@IandeMacBook-Pro.local >
2024-05-03 02:36:48 +00:00
Justin Trugman
10bb25ba7d
Function Calling with GPTAssistantAgent ( #2375 )
...
* Function Calling with GPTAssistantAgent
* Add Link to Notebook in Website
* Add metadata to the notebook
* formatting of H2 and H3 text
* updated to new method of function calling
* Run Pre-commit
* utilize get_function_schema
2024-05-02 16:56:15 +00:00
David Luong
3e693578bf
[.NET] Return ChatCompletions instead of ChatResponseMessage for token usage. ( #2545 )
...
* update
* update
* update
* update
* update
* add sample project
* revert notebook change back
* update
* update interactive version
* add nuget package
* refactor Message
* update example
* add azure nightly build pipeline
* Set up CI with Azure Pipelines
[skip ci]
* Update nightly-build.yml for Azure Pipelines
* add dotnet interactive package
* add dotnet interactive package
* update pipeline
* add nuget feed back
* remove dotnet-tool feed
* remove dotnet-tool feed comment
* update pipeline
* update build name
* Update nightly-build.yml
* Delete .github/workflows/dotnet-ci.yml
* update
* add working_dir to use step
* add initateChat api
* update oai package
* Update dotnet-build.yml
* Update dotnet-run-openai-test-and-notebooks.yml
* update build workflow
* update build workflow
* update nuget feed
* update nuget feed
* update aoai and sk version
* Update InteractiveService.cs
* add support for GPT 4V
* add DalleAndGPT4V example
* update example
* add user proxy agent
* add readme
* bump version
* update example
* add dotnet interactive hook
* update
* udpate tests
* add website
* update index.md
* add docs
* update doc
* move sk dependency out of core package
* udpate doc
* Update Use-function-call.md
* add type safe function call document
* update doc
* update doc
* add dock
* Update Use-function-call.md
* add GenerateReplyOptions
* remove IChatLLM
* update version
* update doc
* update website
* add sample
* fix link
* add middleware agent
* clean up doc
* bump version
* update doc
* update
* add Other Language
* remove warnings
* add sign.props
* add sign step
* fix pipelien
* auth
* real sign
* disable PR trigger
* update
* disable PR trigger
* use microbuild machine
* update build pipeline to add publish to internal feed
* add internal feed
* fix build pipeline
* add dotnet prefix
* update ci
* add build number
* update run number
* update source
* update token
* update
* remove adding source
* add publish to github package
* try again
* try again
* ask for write pacakge
* disable package when branch is not main
* update
* implement streaming agent
* add test for streaming function call
* update
* fix #1588
* enable PR check for dotnet branch
* add website readme
* only publish to dotnet feed when pushing to dotnet branch
* remove openai-test-and-notebooks workflow
* update readme
* update readme
* update workflow
* update getting-start
* upgrade test and sample proejct to use .net 8
* fix global.json format && make loadFromConfig API internal only before implementing
* update
* add support for LM studio
* add doc
* Update README.md
* add push and workflow_dispatch trigger
* disable PR for main
* add dotnet env
* Update Installation.md
* add nuget
* refer to newtonsoft 13
* update branch to dotnet in docfx
* Update Installation.md
* pull out HumanInputMiddleware and FunctionCallMiddleware
* fix tests
* add link to sample folder
* refactor message
* refactor over IMessage
* add more tests
* add more test
* fix build error
* rename header
* add semantic kernel project
* update sk example
* update dotnet version
* add LMStudio function call example
* rename LLaMAFunctin
* remove dotnet run openai test and notebook workflow
* add FunctionContract and test
* update doc
* add documents
* add workflow
* update
* update sample
* fix warning in test
* reult length can be less then maximumOutputToKeep (#1804 )
* merge with main
* add option to retrieve inner agent and middlewares from MiddlewareAgent
* update doc
* adjust namespace
* update readme
* fix test
* use IMessage
* more updates
* update
* fix test
* add comments
* use FunctionContract to replace FunctionDefinition
* move AutoGen contrac to AutoGen.Core
* update installation
* refactor streamingAgent by adding StreamingMessage type
* update sample
* update samples
* update
* update
* add test
* fix test
* bump version
* add openaichat test
* update
* Update Example03_Agent_FunctionCall.cs
* [.Net] improve docs (#1862 )
* add doc
* add doc
* add doc
* add doc
* add doc
* add doc
* update
* fix test error
* fix some error
* fix test
* fix test
* add more tests
* edits
---------
Co-authored-by: ekzhu <ekzhu@users.noreply.github.com >
* [.Net] Add fill form example (#1911 )
* add form filler example
* update
* fix ci error
* [.Net] Add using AutoGen.Core in source generator (#1983 )
* fix using namespace bug in source generator
* remove using in sourcegenerator test
* disable PR test
* Add .idea to .gitignore (#1988 )
* [.Net] publish to nuget.org feed (#1987 )
* publish to nuget
* update ci
* update dotnet-release
* update release pipeline
* add source
* remove empty symbol package
* update pipeline
* remove tag
* update installation guide
* [.Net] Rename some classes && APIs based on doc review (#1980 )
* rename sequential group chat to round robin group chat
* rename to sendInstruction
* rename workflow to graph
* rename some api
* bump version
* move Graph to GroupChat folder
* rename fill application example
* [.Net] Improve package description (#2161 )
* add discord link and update package description
* Update getting-start.md
* [.Net] Fix document comment from the most recent AutoGen.Net engineer sync (#2231 )
* update
* rename RegisterPrintMessageHook to RegisterPrintMessage
* update website
* update update.md
* fix link error
* [.Net] Enable JsonMode and deterministic output in AutoGen.OpenAI OpenAIChatAgent (#2347 )
* update openai version && add sample for json output
* add example in web
* update update.md
* update image url
* [.Net] Add AutoGen.Mistral package (#2330 )
* add mstral client
* enable streaming support
* add mistralClientAgent
* add test for function call
* add extension
* add support for toolcall and toolcall result message
* add support for aggregate message
* implement streaming function call
* track (#2471 )
* [.Net] add mistral example (#2482 )
* update existing examples to use messageCOnnector
* add overview
* add function call document
* add example 14
* add mistral token count usage example
* update version
* Update dotnet-release.yml (#2488 )
* update
* revert gitattributes
* Return ChatCompletions instead of ChatResponseMessage for token usage.
---------
Co-authored-by: XiaoYun Zhang <xiaoyuz@microsoft.com >
Co-authored-by: Xiaoyun Zhang <bigmiao.zhang@gmail.com >
Co-authored-by: mhensen <mh@webvize.nl >
Co-authored-by: ekzhu <ekzhu@users.noreply.github.com >
Co-authored-by: Krzysztof Kasprowicz <60486987+Krzysztof318@users.noreply.github.com >
Co-authored-by: luongdavid <luongdavid@microsoft.com >
2024-05-02 01:36:34 +00:00
David Luong
f4a07ff0ed
[.Net] Support raw-data in ImageMessage ( #2552 )
...
* update
* add sample project
* revert notebook change back
* update
* update interactive version
* add nuget package
* refactor Message
* update example
* add azure nightly build pipeline
* Set up CI with Azure Pipelines
[skip ci]
* Update nightly-build.yml for Azure Pipelines
* add dotnet interactive package
* add dotnet interactive package
* update pipeline
* add nuget feed back
* remove dotnet-tool feed
* remove dotnet-tool feed comment
* update pipeline
* update build name
* Update nightly-build.yml
* Delete .github/workflows/dotnet-ci.yml
* update
* add working_dir to use step
* add initateChat api
* update oai package
* Update dotnet-build.yml
* Update dotnet-run-openai-test-and-notebooks.yml
* update build workflow
* update build workflow
* update nuget feed
* update nuget feed
* update aoai and sk version
* Update InteractiveService.cs
* add support for GPT 4V
* add DalleAndGPT4V example
* update example
* add user proxy agent
* add readme
* bump version
* update example
* add dotnet interactive hook
* update
* udpate tests
* add website
* update index.md
* add docs
* update doc
* move sk dependency out of core package
* udpate doc
* Update Use-function-call.md
* add type safe function call document
* update doc
* update doc
* add dock
* Update Use-function-call.md
* add GenerateReplyOptions
* remove IChatLLM
* update version
* update doc
* update website
* add sample
* fix link
* add middleware agent
* clean up doc
* bump version
* update doc
* update
* add Other Language
* remove warnings
* add sign.props
* add sign step
* fix pipelien
* auth
* real sign
* disable PR trigger
* update
* disable PR trigger
* use microbuild machine
* update build pipeline to add publish to internal feed
* add internal feed
* fix build pipeline
* add dotnet prefix
* update ci
* add build number
* update run number
* update source
* update token
* update
* remove adding source
* add publish to github package
* try again
* try again
* ask for write pacakge
* disable package when branch is not main
* update
* implement streaming agent
* add test for streaming function call
* update
* fix #1588
* enable PR check for dotnet branch
* add website readme
* only publish to dotnet feed when pushing to dotnet branch
* remove openai-test-and-notebooks workflow
* update readme
* update readme
* update workflow
* update getting-start
* upgrade test and sample proejct to use .net 8
* fix global.json format && make loadFromConfig API internal only before implementing
* update
* add support for LM studio
* add doc
* Update README.md
* add push and workflow_dispatch trigger
* disable PR for main
* add dotnet env
* Update Installation.md
* add nuget
* refer to newtonsoft 13
* update branch to dotnet in docfx
* Update Installation.md
* pull out HumanInputMiddleware and FunctionCallMiddleware
* fix tests
* add link to sample folder
* refactor message
* refactor over IMessage
* add more tests
* add more test
* fix build error
* rename header
* add semantic kernel project
* update sk example
* update dotnet version
* add LMStudio function call example
* rename LLaMAFunctin
* remove dotnet run openai test and notebook workflow
* add FunctionContract and test
* update doc
* add documents
* add workflow
* update
* update sample
* fix warning in test
* reult length can be less then maximumOutputToKeep (#1804 )
* merge with main
* add option to retrieve inner agent and middlewares from MiddlewareAgent
* update doc
* adjust namespace
* update readme
* fix test
* use IMessage
* more updates
* update
* fix test
* add comments
* use FunctionContract to replace FunctionDefinition
* move AutoGen contrac to AutoGen.Core
* update installation
* refactor streamingAgent by adding StreamingMessage type
* update sample
* update samples
* update
* update
* add test
* fix test
* bump version
* add openaichat test
* update
* Update Example03_Agent_FunctionCall.cs
* [.Net] improve docs (#1862 )
* add doc
* add doc
* add doc
* add doc
* add doc
* add doc
* update
* fix test error
* fix some error
* fix test
* fix test
* add more tests
* edits
---------
Co-authored-by: ekzhu <ekzhu@users.noreply.github.com >
* [.Net] Add fill form example (#1911 )
* add form filler example
* update
* fix ci error
* [.Net] Add using AutoGen.Core in source generator (#1983 )
* fix using namespace bug in source generator
* remove using in sourcegenerator test
* disable PR test
* Add .idea to .gitignore (#1988 )
* [.Net] publish to nuget.org feed (#1987 )
* publish to nuget
* update ci
* update dotnet-release
* update release pipeline
* add source
* remove empty symbol package
* update pipeline
* remove tag
* update installation guide
* [.Net] Rename some classes && APIs based on doc review (#1980 )
* rename sequential group chat to round robin group chat
* rename to sendInstruction
* rename workflow to graph
* rename some api
* bump version
* move Graph to GroupChat folder
* rename fill application example
* [.Net] Improve package description (#2161 )
* add discord link and update package description
* Update getting-start.md
* [.Net] Fix document comment from the most recent AutoGen.Net engineer sync (#2231 )
* update
* rename RegisterPrintMessageHook to RegisterPrintMessage
* update website
* update update.md
* fix link error
* [.Net] Enable JsonMode and deterministic output in AutoGen.OpenAI OpenAIChatAgent (#2347 )
* update openai version && add sample for json output
* add example in web
* update update.md
* update image url
* [.Net] Add AutoGen.Mistral package (#2330 )
* add mstral client
* enable streaming support
* add mistralClientAgent
* add test for function call
* add extension
* add support for toolcall and toolcall result message
* add support for aggregate message
* implement streaming function call
* track (#2471 )
* [.Net] add mistral example (#2482 )
* update existing examples to use messageCOnnector
* add overview
* add function call document
* add example 14
* add mistral token count usage example
* update version
* Update dotnet-release.yml (#2488 )
* update
* revert gitattributes
* WIP : Binary ImageMessage
* WIP : Able to pass unit test
* Add example, cover more usages
* Rename File
---------
Co-authored-by: XiaoYun Zhang <xiaoyuz@microsoft.com >
Co-authored-by: Xiaoyun Zhang <bigmiao.zhang@gmail.com >
Co-authored-by: mhensen <mh@webvize.nl >
Co-authored-by: ekzhu <ekzhu@users.noreply.github.com >
Co-authored-by: Krzysztof Kasprowicz <60486987+Krzysztof318@users.noreply.github.com >
Co-authored-by: luongdavid <luongdavid@microsoft.com >
2024-05-02 01:30:42 +00:00
Xiaoyun Zhang
1f501b210c
Update dotnet-build.yml to add merge_group trigger ( #2567 )
...
* Update dotnet-build.yml
* Update dotnet-build.yml
2024-05-02 01:09:45 +00:00
Xiaoyun Zhang
e3ccf228e2
Adding an action to set workflow as success when no change is made in target paths ( #2553 )
...
* update
* Update build.yml
* Update build.yml
* test workflow
* add build_check
* update
2024-05-01 22:44:27 +00:00
asandez1
5fdaf1a8c0
Docker multilanguage executor saver with policy ( #2522 )
...
* feat: update executor saver policy
* feat: languages
* feat: add test _cmd
* fix: try catch
* fix: log
* fix: test docker mock
* fix: invalid path test
* fix: invalid path message
* fix: invalid path message
* fix: is_docker test
* fix: delete old test
* fix: cmd lang
2024-05-01 21:14:09 +00:00
Li Jiang
83f9f3e733
Fix chroma import error ( #2557 )
...
* Fix chroma import error
* fix format
2024-05-01 18:05:45 +00:00
Xiaoyun Zhang
d7dda9be09
use conditional check to replace path filter in build and dotnet-ci workflow ( #2546 )
...
* use conditional check
* update
2024-04-30 21:08:47 +00:00
Gabriel Bezerra Valério
a0fffc815b
feat: add bind_dir arg to DockerCommandLineExecutor + docs update ( #2309 )
...
* add bind_dir arg and update docs
* lint
2024-04-30 20:49:04 +00:00
Jinhua Wang
bcb6117c97
Update token_count_utils.py ( #2531 )
...
* Update token_count_utils.py
Update the token counts of new gpt models
ref: https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4
* format code with pre-commit
---------
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com >
2024-04-30 20:42:38 +00:00
Arun
ba9ff45adb
Remove unneeded duplicate check for pydantic v1 since we are already checking that in the else block. ( #2467 )
...
* Remove unneeded duplicate check for pydantic v1 since we are already in
the else block.
* fix formatting
2024-04-30 17:26:36 +00:00
Mark Sze
5b6ae324e2
Re-query speaker name when multiple speaker names returned during Group Chat speaker selection ( #2304 )
...
* Added requery_on_multiple_speaker_names to GroupChat and updated _finalize_speaker to requery on multiple speaker names (if enabled)
* Removed unnecessary comments
* Update to current main
* Tweak error message.
* Comment clarity
* Expanded description of Group Chat requery_on_multiple_speaker_names
* Reworked to two-way nested chat for speaker selection with default of 2 retries.
* Adding validation of new GroupChat attributes
* Updates as per @ekzhu's suggestions
* Update groupchat
- Added select_speaker_auto_multiple_template and select_speaker_auto_none_template
- Added max_attempts comment
- Re-instated support for role_for_select_speaker_messages
-
* Update conversable_agent.py
Added ability to force override role for a message to support select speaker prompt.
* Update test_groupchat.py
Updated existing select_speaker test functions as underlying approach has changed, added necessary tests for new functionality.
* Removed block for manual selection in select_speaker function.
* Catered for no-selection during manual selection mode
---------
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
2024-04-30 04:16:08 +00:00
Xiaoyun Zhang
5e29ac84dc
[.Net] fix code ql for dotnet build && update trigger for dotnet workflow ( #2529 )
...
* fix formatting
* update dotnet build pipieline
2024-04-29 20:27:57 +00:00
