242a3c6616
Bump google-generativeai to 0.8.2 ( #126696 )
...
changelog: https://github.com/google-gemini/generative-ai-python/compare/v0.7.2...v0.8.2
2024-09-24 15:13:12 -07:00
8cafa1bcdf
Bump google-generativeai to 0.7.2 ( #124940 )
...
changelog: https://github.com/google-gemini/generative-ai-python/compare/v0.6.0...v0.7.2
2024-08-30 22:33:26 +02:00
cffa8b4feb
Update icons.json to new service schema part 2 ( #124769 )
2024-08-28 13:47:41 +02:00
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
f6ad018f8f
Change enum type to string for Google Generative AI Conversation ( #123069 )
2024-08-02 23:14:24 -07:00
8d0e998e54
Improve conversation agent tracing to help with eval and data collection ( #122542 )
2024-07-31 14:38:44 +02:00
975cfa6457
Fix gemini api format conversion ( #122403 )
...
* Fix gemini api format conversion
* add tests
* fix tests
* fix tests
* fix coverage
2024-07-22 17:56:13 -07:00
ac1ad9680b
Goofle Generative AI: Fix string format ( #122348 )
...
* Ignore format for string tool args
* Add tests
2024-07-21 21:54:31 -07:00
5ce54c2174
Replace GoogleAPICallError with GoogleAPIError ( #120902 )
2024-07-01 17:48:12 +02:00
d2a457c24f
Fix Google Generative AI: 400 Request contains an invalid argument ( #120741 )
2024-06-28 13:25:55 +02:00
2386ed3830
Add script llm tool ( #118936 )
...
* Add script llm tool
* Add tests
* More tests
* more test
* more test
* Add area and floor resolving
* coverage
* coverage
* fix ColorTempSelector
* fix mypy
* fix mypy
* add script reload test
* Cache script tool parameters
* Make custom_serializer a part of api
---------
Co-authored-by: Michael Hansen <mike@rhasspy.org>
2024-06-25 10:43:26 -05:00
5c2db162c4
Remove "no API" prompt ( #120280 )
2024-06-24 08:57:59 +02:00
ad1f0db5a4
Pass prompt as system_instruction for Gemini 1.5 models ( #120147 )
2024-06-22 12:35:48 +02:00
f605c10f42
Properly handle escaped unicode characters passed to tools in Google Generative AI ( #119117 )
2024-06-08 09:02:00 +02:00
5fdfafd57f
Catch GoogleAPICallError in Google Generative AI ( #119118 )
2024-06-08 08:51:42 +02:00
ae59d0eadf
Bump google-generativeai to 0.6.0 ( #119062 )
2024-06-07 20:50:55 +02:00
035e19be01
Google Gen AI: Copy messages to avoid changing the trace data ( #118745 )
2024-06-03 22:29:50 +02:00
a4612143e6
Use gemini-1.5-flash-latest in google_generative_ai_conversation.generate_content ( #118594 )
2024-05-31 21:57:14 -07:00
7af469f81e
Strip Google AI text responses ( #118593 )
...
* Strip Google AI test responses
* strip each part
2024-05-31 21:55:52 -07:00
f3b20d30ae
Add base prompt for LLMs ( #118592 )
2024-06-01 00:21:37 -04:00
bae96e7d36
Add Google Generative AI Conversation system prompt `user_name` and `llm_context` variables ( #118510 )
...
* Google Generative AI Conversation: Add variables to the system prompt
* User name and llm_context
* test for template variables
* test for template variables
---------
Co-authored-by: Paulus Schoutsen <balloob@gmail.com>
2024-05-31 15:28:44 -04:00
6dd01dbff7
Rename llm.ToolContext to llm.LLMContext ( #118566 )
2024-05-31 11:11:24 -04:00
272c51fb38
Fix unnecessary single quotes escaping in Google AI ( #118522 )
2024-05-30 19:56:06 -04:00
aeee222df4
Default to gemini-1.5-flash-latest in Google Generative AI ( #118367 )
...
Default to flash
2024-05-29 08:04:47 -04:00
d83ab7bb04
Fix issue when you have multiple Google Generative AI config entries and you remove one of them ( #118365 )
2024-05-29 11:59:06 +02:00
615a1eda51
LLM Assist API to ignore intents if not needed for exposed entities or calling device ( #118283 )
...
* LLM Assist API to ignore timer intents if device doesn't support it
* Refactor to use API instances
* Extract ToolContext class
* Limit exposed intents based on exposed entities
2024-05-28 21:29:18 -04:00
0cf574dc42
Update the recommended model for Google Gen AI ( #118323 )
2024-05-28 21:21:28 -04:00
63227f14ed
Add diagnostics to Google Generative AI ( #118262 )
...
* Add diagnostics for Google Generative AI
* Remove quality scale from manifest
* include options in diagnostics
2024-05-28 00:02:32 -04:00
0c245f1976
Fix freezing on HA startup when there are multiple Google Generative AI config entries ( #118282 )
...
* Fix freezing on HA startup when there are multiple Google Generative AI config entries
* Add timeout to list_models
2024-05-27 23:49:16 -04:00
722feb285b
Handle multiple function_call and text parts in Google Generative AI ( #118270 )
2024-05-27 19:57:03 -04:00
1602c8063c
Standardize LLM instructions prompt ( #118195 )
...
* Standardize instructions prompt
* Add time/date to default instructions
2024-05-26 20:24:26 -04:00
0588806922
Promote Google Generative AI to platinum quality ( #118158 )
...
* Promote Google Generative AI to platinum quality
* make exception for diagnostics
2024-05-26 17:07:31 -04:00
0972b29510
Add Google Generative AI reauth flow ( #118096 )
...
* Add reauth flow
* address comments
2024-05-26 11:44:48 -04:00
233c3bb2be
Add render prompt method when no API selected ( #118136 )
2024-05-26 13:35:15 +02:00
89e2c57da6
Add conversation agent debug tracing ( #118124 )
...
* Add debug tracing for conversation agents
* Minor cleanup
2024-05-25 14:16:51 -04:00
0182bfcc81
Google Generative AI: 100% test coverage for conversation ( #118112 )
...
100% coverage for conversation
2024-05-25 07:52:20 -04:00
81f3387d06
Flip prompts to put user prompt on top ( #118085 )
2024-05-25 00:33:24 -04:00
69f237fa9e
Update Google safety defaults to match Google ( #118084 )
2024-05-25 00:02:53 -04:00
c59d4f9bba
Add no-API LLM prompt back to Google ( #118082 )
...
* Add no-API LLM prompt back
* Use string join
2024-05-25 00:00:04 -04:00
86a24cc3b9
Fix default Google AI prompt on initial setup ( #118078 )
2024-05-24 23:55:11 -04:00
4b0f58ec63
Add device info to Google ( #118074 )
2024-05-24 22:23:25 -04:00
620487fe75
Add Google Generative AI safety settings ( #117679 )
...
* Add safety settings
* snapshot-update
* DROPDOWN
* fix test
* rename const
* Update const.py
* Update strings.json
2024-05-24 21:48:39 -04:00
5ca27f5d0c
Google Generative AI: add timeout to ensure we don't block HA startup ( #118066 )
...
* timeout
* fix
* tests
2024-05-24 21:31:02 -04:00
7554ca9460
Allow llm API to render dynamic template prompt ( #118055 )
...
* Allow llm API to render dynamic template prompt
* Make rendering api prompt async so it can become a RAG
* Fix test
2024-05-24 16:04:48 -04:00
d1af40f1eb
Google gen updates ( #117893 )
...
* Add a recommended model for Google Gen AI
* Add recommended settings to Google Gen AI
* Revert no API msg
* Use correct default settings
* Make sure options are cleared when using recommended
* Update snapshots
* address comments
2024-05-23 17:16:48 -04:00
e4130480c3
Google Generative AI: Handle response with empty parts in generate_content ( #117908 )
...
Handle response with empty parts in generate_content
2024-05-22 07:47:16 -07:00
2f0215b034
LLM Tools support for OpenAI integration ( #117645 )
...
* initial commit
* Add tests
* Move tests to the correct file
* Fix exception type
* Undo change to default prompt
* Add intent dependency
* Move format_tool out of the class
* Fix tests
* coverage
* Adjust to new API
* Update strings
* Update tests
* Remove unrelated change
* Test referencing non-existing API
* Add test to verify no exception on tool conversion for Assist tools
* Bump voluptuous-openapi==0.0.4
* Add device_id to tool input
* Fix tests
---------
Co-authored-by: Paulus Schoutsen <balloob@gmail.com>
2024-05-21 22:45:04 -04:00
009c9e79ae
LLM Tools: Add device_id ( #117884 )
2024-05-21 21:24:46 -04:00
ff2b851683
Make Google AI model picker a dropdown ( #117878 )
2024-05-21 22:13:07 +02:00
c3196a5667
LLM Tools support for Google Generative AI integration ( #117644 )
...
* initial commit
* Undo prompt chenges
* Move format_tool out of the class
* Only catch HomeAssistantError and vol.Invalid
* Add config flow option
* Fix type
* Add translation
* Allow changing API access from options flow
* Allow model picking
* Remove allowing HASS Access in main flow
* Move model to the top in options flow
* Make prompt conditional based on API access
* convert only once to dict
* Reduce debug logging
* Update title
* re-order models
* Address comments
* Move things
* Update labels
* Add tool call tests
* coverage
* Use LLM APIs
* Fixes
* Address comments
* Reinstate the title to not break entity name
---------
Co-authored-by: Paulus Schoutsen <balloob@gmail.com>
2024-05-19 22:11:25 -04:00
J. Nick Koston
Erik Montnemery
Paulus Schoutsen
Denis Shulyaka
Allen Porter
tronikos