* 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>
* 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>
* Feat/headless browser (retargeted) (#1832)
* Add headless browser to the WebSurferAgent, closes#1481
* replace soup.get_text() with markdownify.MarkdownConverter().convert_soup(soup)
* import HeadlessChromeBrowser
* implicitly wait for 10s
* inicrease max. wait time to 99s
* fix: trim trailing whitespace
* test: fix headless tests
* better bing query search
* docs: add example 3 for headless option
---------
Co-authored-by: Vijay Ramesh <vijay@regrello.com>
* Handle missing Selenium package.
* Added browser_chat.py example to simplify testing.
* Based browser on mdconvert. (#1847)
* Based browser on mdconvert.
* Updated web_surfer.
* Renamed HeadlessChromeBrowser to SeleniumChromeBrowser
* Added an initial POC with Playwright.
* Separated Bing search into it's own utility module.
* Simple browser now uses Bing tools.
* Updated Playwright browser to inherit from SimpleTextBrowser
* Got Selenium working too.
* Renamed classes and files for consistency.
* Added more instructions.
* Initial work to support other search providers.
* Added some basic behavior when the BING_API_KEY is missing.
* Cleaned up some search results.
* Moved to using the request.Sessions object. Moved Bing SERP paring to mdconvert to be more broadly useful.
* Added backward compatibility to WebSurferAgent
* Selenium and Playwright now grab the whole DOM, not jus the body, allowing the converters access to metadata.
* Fixed printing of page titles in Playwright.
* Moved installation of WebSurfer dependencies to contrib-tests.yml
* Fixing pre-commit issues.
* Reverting conversable_agent, which should not have been changed in prior commit.
* Added RequestMarkdownBrowser tests.
* Fixed a bug with Bing search, and added search test cases.
* Added tests for Bing search.
* Added tests for md_convert
* Added test files.
* Added missing pptx.
* Added more tests for WebSurfer coverage.
* Fixed guard on requests_markdown_browser test.
* Updated test coverage for mdconvert.
* Fix brwser_utils tests.
* Removed image test from browser, since exiftool isn't installed on test machine.
* Removed image test from browser, since exiftool isn't installed on test machine.
* Disable Selenium GPU and sandbox to ensure it runs headless in Docker.
* Added option for Bing API results to be interleaved (as Bing specifies), or presented in a categorized list (Web, News, Videos), etc
* Print more details when requests exceptions are thrown.
* Added additional documentation to markdown_search
* Added documentation to the selenium_markdown_browser.
* Added documentation to playwright_markdown_browser.py
* Added documentation to requests_markdown_browser
* Added documentation to mdconvert.py
* Updated agentchat_surfer notebook.
* Update .github/workflows/contrib-tests.yml
Co-authored-by: Davor Runje <davor@airt.ai>
* Merge main. Resolve conflicts.
* Resolve pre-commit checks.
* Removed offending LFS file.
* Re-added offending LFS file.
* Fixed browser_utils tests.
* Fixed style errors.
---------
Co-authored-by: Asapanna Rakesh <45640029+INF800@users.noreply.github.com>
Co-authored-by: Vijay Ramesh <vijay@regrello.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Co-authored-by: Davor Runje <davor@airt.ai>
* add couchbase vector store
* add unit test
* cleanup
* add couchbase to website
* fix code formatting
---------
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
