* Addition of Non-OpenAI LLM section and main doc page
* Continued writing...
* Continued writing - cloud-based proxy servers
* Folder renamed
* Further writing
* together.ai example added
* Local proxy server added, diagram added, tidy up
* Added vLLM to local proxy servers documentation
* As per @ekzhu's feedback, individual pages and tidy up
* Added reference to LM Studio and renamed file
* Fixed incorrect huggingface.co link
* Run pre-commit checks, added LM Studio redirect
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* Add mypy check in pre-commit
* Add mypy check in pre-commit
* bug fix
* CI fix
* add python version matrix for checking types in CI
* update github actions
* revert some accidental changes
* revert some accidental changes
* revert some accidental changes
* revert some accidental changes
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* Add mypy check in pre-commit
* Add mypy check in pre-commit
* bug fix
* CI fix
* add python version matrix for checking types in CI
* added 3.12 to CI
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* refactor: [conversable_agent] remove list of func pointers
Ideally register_reply creates less state in multiple places and avoid having two copies of the same 'func pointer'.
* Update conversable_agent.py
---------
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* add assistant config
* add test
* change notebook to use assistant config
* use assistant config in testing
* code refinement
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* update default agent system message
* session friendly name functionality
* minor formatting
* fix issues with groupchat and version bump
* fix issues with groupchat and version bump. address #1580
* update groupchat system message
* add support for copying message in chatbox
* rewrite how agent history is maintained in workflow manager. Directly extend GroupChat and Conversable agent and override process_message method. Allow passing a message processor.
Fixes bug where the last message from a groupchat manager does not get called via register_reply.
* general qol updates
* add support for downloading + copying skills, models and agents from UI
* add regex check to agent name, address #1507
* add support for uploading workflow files
* refactor, add support for streaming intermediate agent response to ui
* improve streaming ux
* add support for uploading skills, models, agents, workflows
* add datamodel for socket message
* version update
* fix chatbox height bug
* fix csv pagination issue
* improve hidden menu for uploading entities
* fix minor issue with animation timing on chat interface
* version bump, css fixes
* use description field in autogen conversable class for description
* add implementation for llm summarization of agent chat
* support for llm summary of agent history
* formatting fixes
* formatting updates
* add dockerfile to run autogenstudio in a docker contailer
* autogenstudio docker container
* updates to websockets
* update socket connection logic,
* support using socket for passing message requests where a socket is available
* improve command for building frontend
* formatting updates
* remove duplicated code
# overwrite skills.py in work_dir is duplicated
* update description location
as Where the code calls is like config.description
* version bump
* refactor to ensure each session and call within a session has an independent working directory
* support use of socket for sending messages where available
* use rsync to copy built files to ui direction instead of cp -rT
* spelling correctino
* readme update
* fix numpy version
* version bump
* add support for dot env variables and updating default app dir to /home/<user>/.autogenstudio
* formatting update
* update gitignore
* formatting updates
---------
Co-authored-by: James Woffinden-Luey <jluey@microsoft.com>
Co-authored-by: cillyfly <cillyfly@gmail.com>
* refactor: [conversable_agent] remove raise from property access
raising exception seems drastic, can we return None and let the called fail in case it receives a None?
* Update conversable_agent.py
---------
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* fix type and default value of the code_execution_config of UserProxAgent
* fix type and default value of the code_execution_config of UserProxAgent
* set default value of llm_config in UserProxyAgent to None
* fixed tests
* revert llm_config to False
---------
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
