* update docs, add link to v0.4
* update homepage text
* Update website/src/pages/index.js
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* [Fix] Precommit issues
* [Fix] checks
* [Fix] iterating through list_of_functions
* [Fix] pre-commit checks
* Update test/agentchat/contrib/test_agent_builder.py
Co-authored-by: Chi Wang <4250911+sonichi@users.noreply.github.com>
---------
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
Co-authored-by: Ryan Sweet <rysweet@microsoft.com>
Co-authored-by: Chi Wang <4250911+sonichi@users.noreply.github.com>
* remove unused import statement
* fix#2643: register custom model clients within GroupChat
* add docs for fix#2643
* Update website/docs/topics/groupchat/using_custom_models.md
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* Update website/docs/topics/groupchat/using_custom_models.md
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* fix: removed unnecessary llm_config from checking agent
* fix: handle missing config or "config_list" key in config
* fix: code formatting
* Isolate method for internal agents creation
* Add unit test to verify that internal agents' client actually registers ModelClient class
* fix: function arguments formatting
* chore: prepend "select_speaker_auto_" to llm_config and model_client_cls attributes in GroupChat
* feat: use selector's llm_config for speaker selection agent if none is passed to GroupChat
* Update test/agentchat/test_groupchat.py
* Update groupchat.py - moved class parameters around, added to docstring
* Update groupchat.py - added selector to async select speaker functions
* Update test_groupchat.py - Corrected test cases for custom model client class
* Update test_groupchat.py pre-commit tidy
---------
Co-authored-by: Matteo Frattaroli <m.frattroli97@gmail.com>
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Co-authored-by: Mark Sze <66362098+marklysze@users.noreply.github.com>
* Added function calling support to GeminiClient
* Appending a continue message from model to alternate between user and model
* Fixed cost calculation to include <128K costing and new 1.5-flash model. Added test case for function_call.
* Add notebook with samples for Gemini
* Updated test case
* Fix to handle not dict response in function call
* Handle non dict function results and append dummy model message between function response and user message
* Fixing message order in gemini
* Append text as multiple parts instead of test concatenation
* Raising error for Union data types in function parameter
* Delete default key
* Update gemini.py for multiple tool calls + pre-commit formatting
* no function role
* start adding function calling config
* do not serialize tool_config
* improve tool config parsing
* add hint
* improve function calling config
* removunnecessary comments
* try removing allowed function names in tool config conversion
* fix tool config parsing with empty tools list
* improve logging and case handling with vertexai tool config parsing
* reset file
* check if text is in part
* fix empty part checking case
* fix bug with attribute handling
* skip test if gemini deps are not installed
---------
Co-authored-by: Arjun G <arjun@arjun-g.com>
Co-authored-by: Beibin Li <BeibinLi@users.noreply.github.com>
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
Co-authored-by: Mark Sze <66362098+marklysze@users.noreply.github.com>
* Ollama client! With function calling. Initial commit, client, no docs or tests yet.
* Tidy comments
* Cater for missing prompt token count
* Removed use of eval, added json parsing support library
* Fix to the use of the JSON fix library, handling of Mixtral escape sequence
* Fixed 'name' in JSON bug, catered for single function call JSON without []
* removing role='tool' from inner tool result to reduce token usage.
* Added Ollama documentation and updated library versions
* Added Native Ollama tool calling (v0.3.0 req.) as well as hide/show tools support
* Added native tool calling and hide_tools parameter to documentation
* Update to Ollama 0.3.1, added tests
* Tweak to manual function calling prompt to improve number handling.
* Fix formatting
Co-authored-by: gagb <gagb@users.noreply.github.com>
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
* Fix formatting
* Better error message
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Co-authored-by: gagb <gagb@users.noreply.github.com>
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
When running the AutoGen Studio from source, one needs to separately launch the frontend server. Updated the docs to include these instructions.
Co-authored-by: Victor Dibia <victordibia@microsoft.com>
Eric Zhu