* Add mkdocs-llmstxt and related config
* Remove existing llms.txt and llms-full.txt from repo
* Add docs page for llms.txt
* Minor edit
* Minor edit
* Add *.md to glob syntax in mkdocs-llmstxt config
* Add explicit URLs in API reference section to avoid build warnings
* Fix all build warnings related to bad cross-links and incorrect anchor links
* Suppress INFO logs about absolute links - the CI link checker will catch any issues
* Fix remaining build warnings
* Add Gemini CLI instructions
* Fix link to bidi tutorial
* Add async session initialization example when running in .py script
Added example code for initializing a session asynchronously when running in .py script
* Update docs/tutorials/agent-team.md
---------
Co-authored-by: Kristopher Overholt <koverholt@google.com>
* Add AG-UI adk-middleware tutorial
* Significantly trim down docs
* Change some headers
* Add AG-UI page to nav
* Shorten description on tutorials page
* Edits throughout tutorial
---------
Co-authored-by: Kristopher Overholt <koverholt@google.com>
* Phase 1: ADK Onboarding journey revision
- Quickstart: split by language and reduce time
- Build your agent: new section for agent building
- Home page: Simplify onboarding choices
- Surface "About ADK" in navigation
* Updates from first review round and Java research
- completely revised Java quickstart
* further updates from review
* more review updates
---------
Co-authored-by: Kristopher Overholt <koverholt@gmail.com>
Wrong method is used for getting weather. Instead of `get_weather` it should be `get_weather_stateful`
Co-authored-by: Joe Fernandez <joefernandez@users.noreply.github.com>
* fix: remove as_dict() usage from final session state logging
The code incorrectly called `.as_dict()` on a plain `dict` object, causing an AttributeError.
This commit removes the invalid `.as_dict()` call.
* fix: remove .as_dict() usage from final session state logging
The code incorrectly called `.as_dict()` on a plain `dict` object, causing an AttributeError.
This commit like the previous one removes another occurence of the `.as_dict()` call.
---------
Co-authored-by: Lavi Nigam <98014943+lavinigam-gcp@users.noreply.github.com>
The code incorrectly called `.as_dict()` on a plain `dict` object, causing an AttributeError.
This commit replaces it with direct usage of the dictionary and adds a comment.
Co-authored-by: Lavi Nigam <98014943+lavinigam-gcp@users.noreply.github.com>
* fix(tutorial): Correct say_hello tool logic, update LLM models, and ensure async session creation
This commit addresses several issues and updates within the ADK agent team tutorial (adk_tutorial.ipynb) and its corresponding documentation (agent-team.md).
Notebook Updates (adk-tutorial.ipynb):
- Ensured all `SessionService.create_session` calls are `await`ed for proper asynchronous operation throughout the notebook.
- Updated Anthropic model to `claude-sonnet-4-20250514` and OpenAI model to `gpt-4.1`, with commented alternatives for flexibility.
- Added LiteLLM documentation links for model references.
- Resolved the 'Hello None' issue in Step 3 by modifying the `say_hello` tool to correctly handle optional name arguments and prevent the `Default value is not supported` warning with Gemini models.
- Tested and confirmed notebook compatibility with `google-adk==1.0.0`.
Page Update (agent-team.md):
- Synchronized `agent-team.md` with all notebook changes to ensure documentation accuracy and reflect the latest updates.
* fix(tutorial): Refine CLI/Web UI agent team tutorial and update content
This commit introduces several fixes and improvements to the Python file-based version of the ADK agent team tutorial, aligning it for use with `adk web`, `adk run`, and `adk api_server`.
Key changes to the `adk-tutorial` Python files:
- Validated and ensured all tutorial steps are compatible with `google-adk==1.0.0`.
- Synchronized Python file content with the latest changes from the main Colab notebook version.
- Corrected `step2_anthropic.py`: agent name, description, and instruction strings now accurately reflect Anthropic context (previously used GPT-related strings).
- Updated model identifiers: `anthropic/claude-sonnet-4-20250514` in `step2_anthropic.py` and `openai/gpt-4.1` in `step2_gpt4.py`.
- Performed general cleanup and refactoring in `step3_agent_team.py`.
- Added example queries directly within the agent Python files for Steps 1, 2, 3, 5, and 6 to facilitate easier testing by users.
- Removed `step4_state_personalization.py` as its demonstration of session state manipulation (especially direct InMemorySessionService updates) is better suited for an interactive notebook environment.
README.md Updates:
- Added a note explaining the removal of Step 4 and directing users to the interactive notebook version for that specific content.
- Included references to the newly added sample queries in the agent Python files, guiding users on how to test the agent's functionalities.
* fix: tutorial section overhaul and bug fixes
- Tutorial section is moved out of getting started and is a seperate section
- Fixed a sentence in getting-started page that still showed “google search”
- Given we will have more tutorials as part of docs, now we have sub-sections with the tutorial name
- For weather agent team - fixed issues pointed out in #118#135
- It now includes code for asynio in the notebook
- It also now has .py file to run it through adk web
- Step 2 is now optional and not connected to other steps. So user can follow other steps if they choose to
- There is disclaimer at the top - for different method to run the code
- The text on the page is now synced with notebook
- Collab and social link are updated with new changes in folder.
* added a redirect in the redirect_maps
* adding license headers in the code for tutorial for .py files
Dinesh Thumma