073589ae19
Deprecate DeviceEntry.suggested_area ( #149730 )
2025-08-04 10:34:38 +02:00
1734b316d5
Return intent response from LLM chat log if available ( #148522 )
2025-07-16 16:16:01 +02:00
02a11638b3
Add Google AI STT ( #147563 )
2025-07-16 14:11:29 +02:00
334d5f09fb
Create Google Generative AI sub entries for an enabled entry ( #148161 )
...
Co-authored-by: Erik Montnemery <erik@montnemery.com>
2025-07-14 11:24:00 +02:00
23a8442abe
Make attachments native to chat log ( #148693 )
...
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-07-13 19:35:11 +02:00
1920edd712
Update Google Generative AI Conversation max tokens to 3000 ( #148625 )
...
Co-authored-by: Claude <noreply@anthropic.com>
2025-07-11 13:10:12 -07:00
19b3b6cb28
Add attachment support to Google Gemini ( #148208 )
2025-07-10 23:45:11 +02:00
8cb9cadce9
Extract files_to_prompt from Gemini action ( #148203 )
...
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Allen Porter <allen.porter@gmail.com>
2025-07-06 15:15:38 +02:00
4f4ec6f41a
Add Google Gen AI structured data support ( #148143 )
2025-07-05 08:22:17 -07:00
04cc451c76
Add AI Task platform to Google Gen AI ( #146766 )
2025-07-03 23:36:34 -07:00
2e7113d881
Swap the Models label for the model name not it's display name, ( #147918 )
...
Swap display name for name.
2025-07-01 21:12:58 -07:00
99f7a031d6
Correct Google generative AI config entry migration ( #147856 )
2025-07-01 10:46:13 +02:00
1b2be083c2
Make sure Google Generative AI integration migration is clean ( #147625 )
2025-06-26 23:03:36 +02:00
35478e3162
Set Google AI model as device model ( #147582 )
...
* Set Google AI model as device model
* fix
2025-06-26 19:44:15 +02:00
fb133664e4
Include subentries in Google Generative AI diagnostics ( #147558 )
2025-06-26 10:50:47 +02:00
0f95fe566c
Use default title for migrated Google Generative AI entries ( #147551 )
2025-06-25 22:30:41 -04:00
f0a78aadbe
Fixes in Google AI TTS ( #147501 )
...
* Fix Google AI not using correct config options after subentries migration
* Fixes in Google AI TTS
* Fix tests by @IvanLH
* Change type name.
---------
Co-authored-by: Paulus Schoutsen <balloob@gmail.com>
Co-authored-by: Paulus Schoutsen <paulus@home-assistant.io>
2025-06-25 18:12:23 -04:00
0cf7952964
Remove duplicated subentry device update in Google Gen AI + add merge test ( #147396 )
...
* late comments on Google subentries
* Add test that merges 2 config entries
2025-06-23 22:34:06 -04:00
56f4039ac2
Migrate Google Gen AI to use subentries ( #147281 )
...
* Migrate Google Gen AI to use subentries
* Add reconfig successful msg
* Address comments
* Do not allow addin subentry when not loaded
* Let HA do the migration
* Use config_entries.async_setup
* Remove fallback name on base entity
* Fix
* Fix
* Fix device name assignment in entity and tts modules
* Fix tests
---------
Co-authored-by: Joostlek <joostlek@outlook.com>
2025-06-23 20:59:32 -04:00
2833e97625
Default to gemini-2.5-flash ( #147334 )
2025-06-23 20:11:16 +02:00
8498928e47
Move Google Gen AI fixture to allow reuse ( #146921 )
2025-06-15 23:00:27 -04:00
c988d1ce36
Add support for Gemini's new TTS capabilities ( #145872 )
...
* Add support for Gemini TTS
* Add tests
* Use wave library and update a few comments
2025-06-14 22:21:04 -07:00
ec02f6d010
Extract Google LLM base entity class ( #146817 )
2025-06-14 22:17:52 -07:00
32eb4af6ef
Enable message Streaming in the Gemini integration. ( #144937 )
...
* Added streaming implementation
* Indicate the entity supports streaming
* Added tests
* Removed unused snapshots
---------
Co-authored-by: Paulus Schoutsen <balloob@gmail.com>
2025-05-25 21:50:55 -04:00
0edfbded23
Fixes #140182 by checking file status before sending the prompt. ( #144131 )
...
* Added unit tests
* Addressed review comments
* Fixed tests
* PR comments
2025-05-05 23:45:39 -07:00
2326c23133
Increase Gemini max tokens to avoid failures observed in evaluations ( #143728 )
...
* Increase Gemini max tokens to avoid failures observed in evaluations
* Update snapshots
2025-04-26 15:30:47 -07:00
4483025856
Update Google Generative AI to allow multiple LLM APIs ( #143191 )
2025-04-19 11:44:12 +02:00
c14380247b
Handle None on the response candidates in Google Generative AI ( #142497 )
...
* Added type checking on the candidates list
* Made error message a constant
2025-04-07 21:20:54 -07:00
30e50d261d
Made Google Search enable dependent on Assist availability ( #141712 )
...
* Made Google Search enable dependent on Assist availability
* Show error instead of rendering again
* Cleanup test code
2025-04-03 16:23:59 -04:00
e88b321741
Ensure user always has first turn for Google Gen AI ( #141893 )
2025-03-30 23:31:45 -04:00
85d2e3d006
Fix LLM to speed up prefill ( #141156 )
...
* fix: two minor LLM changes to speed up prefill
- moved the current date/time to the end of the prompt
- started sorting all entities by last_changed
* addressed PR comments
* fixed tests
* reduced scope of try/catch in LLM prompt
* addressed more PR comments
* fixed Anthropic test
* addressed another PR comment
* fixed remainder of tests
2025-03-30 13:30:40 -07:00
56cc4044e4
Fix a type error when using google-genai==1.7.0 ( #141431 )
...
* Fix parts
* Fix the type being sent to the SDK
* Revert changes to __init__
* Test fixes
* Bump version back to 1.7
2025-03-25 19:59:21 -07:00
c8f839068c
Bump google-genai to 1.7.0 ( #140770 )
...
Gemini: Upgrade google-genai to support generating images
2025-03-24 10:52:16 -07:00
d3b8dbb76c
Google gen ai fix for empty chat log messages ( #136019 ) ( #140315 )
...
* Google gen ai fix for empty chat log messages (#136019 )
* Google gen ai test for empty chat history fields (#136019 )
2025-03-23 22:27:35 -07:00
6a7fa3769d
Add Google Search tool in Google Generative AI ( #140772 )
...
* Added Google Search grounding
* Added testing
2025-03-23 22:23:52 -07:00
f14b76c54b
Add Gemini/OpenAI token stats to the conversation trace ( #141118 )
...
* Add gemini token status to the conversation trace
* Add OpenAI Token Stats
* Revert input_tokens_details since its not in the openai version yet
* Fix ruff lint errors
2025-03-23 12:03:06 -04:00
d9cf2750d5
Ensure file is correctly uploaded by the GenAI SDK ( #140969 )
...
Opened the file outside of the SDK
2025-03-19 22:58:19 -07:00
2aa584ce39
Correctly retrieve only loaded Google Generative AI config_entries ( #139999 )
...
* Correctly retrieve only loaded config_entries
* Ruff
2025-03-06 13:17:33 -08:00
8e35783164
Trim the Schema allowed keys to match the Public Gemini API docs. ( #139876 )
...
* Trim the Schema allowed types to match the Public API docs, not the SDK types as those do not match
* Testing
2025-03-05 18:34:11 -08:00
4e8186491c
Fix Gemini Schema validation for #139416 ( #139478 )
...
Fixed Schema validation for issue #139477
2025-02-27 19:10:42 -08:00
580c6f2684
Allow arbitrary Gemini attachments ( #138751 )
...
* Gemini: Allow arbitrary attachments
This lets me use Gemini to extract information from PDFs, HTML, or other files.
* Gemini: Only add deprecation warning when deprecated parameter has a value
* Gemini: Use Files.upload() for both images and other files
This simplifies the code.
Within the Google client, this takes a different codepath (it uploads images as a file instead of re-saving them into inline bytes). I think that's a feature (it's probably more efficient?).
* Gemini: Deduplicate filenames
2025-02-23 16:11:38 -08:00
3160b7baa0
Swap the Gemini SDK to the newly released Unified SDK ( #138246 )
...
* Swapped the old GenAI client with the newly realeased one
* Fixed the Generate Content Action, Config Flow loading and code cleanup
* Add a function to mask the issues with Tools which start with Hass
* Fix most tests
* google-genai==1.1.0
* fixes
* Fixed the remaining tests
* Adressed comments
---------
Co-authored-by: Paulus Schoutsen <balloob@gmail.com>
Co-authored-by: tronikos <tronikos@users.noreply.github.com>
2025-02-21 22:41:05 -08:00
35416189f2
Remove some unused tests from Google Generative AI ( #138249 )
...
* Remove some unused tests from Google Generative AI
* Remove unused snapshots
2025-02-10 18:25:34 -08:00
3b871afcc4
Update default Google model to Gemini Flash 2.0 ( #137505 )
2025-02-05 23:27:13 -05:00
9679fc7878
Chat session rev2 ( #137209 )
...
* Chat Session rev 2
* Rename session to chat_log
* Simplify typing
* Typing
* Address comments
* Fix anthropic and ollama
2025-02-03 00:05:20 -05:00
8ab6bec746
Migrate Google Gen AI to ChatSession ( #136779 )
...
* Migrate Google Gen AI to ChatSession
* Remove unused method
2025-01-29 10:42:39 -05:00
8db63adc11
Bump ruff to 0.9.1 ( #135197 )
2025-01-14 11:46:12 +01:00
a85ccb94e3
LLM Tool parameters check ( #123621 )
...
* LLM Tool parameters check
* fix tests
2024-09-08 18:42:51 -07:00
25d33e96cc
Add missing hass type hint in component tests (g) ( #124203 )
2024-08-19 00:29:26 -07:00
aa6f0cd55a
Add CONTROL supported feature to Google conversation when API access ( #123046 )
...
* Add CONTROL supported feature to Google conversation when API access
* Better function name
* Handle entry update inline
* Reload instead of update
2024-08-02 23:16:30 -07:00
Erik Montnemery
Paulus Schoutsen
tronikos
Joost Lekkerkerker
Ivan Lopez Hernandez
Markus Lanthaler
Allen Porter
John Karabudak
SLaks
Mirko Liebender
Denis Shulyaka
epenet