evlli/hass-core
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
83409 commits 291 branches 1355 tags 1.4 GiB
Commit graph

52 commits

Author SHA1 Message Date
Joost Lekkerkerker
a1906b434f
Change trigger platform key to trigger (#124357) 
* fix

* Fix

* Fix

* Update homeassistant/helpers/config_validation.py

Co-authored-by: Erik Montnemery <erik@montnemery.com>

* Fix

* Fix

* Fix

* Fix

* Add more tests

* Fix

* Fix tests

* Add tests

* Let's see what the CI does

* It fails on the code that tested the thing ofc

* It fails on the code that tested the thing ofc

* Revert test thingy

* Now the test works again, lovely

* Another one

* Fix websocket thingy

* Only copy when needed

* Improve comment

* Remove test

* Fix docstring

* I think this now also work since this transforms trigger to platform

* Add comment

* Update homeassistant/helpers/config_validation.py

Co-authored-by: Erik Montnemery <erik@montnemery.com>

* Update homeassistant/helpers/config_validation.py

Co-authored-by: Erik Montnemery <erik@montnemery.com>

* Update homeassistant/helpers/config_validation.py

Co-authored-by: Erik Montnemery <erik@montnemery.com>

* Check for mapping

* Add test

* Update homeassistant/helpers/config_validation.py

Co-authored-by: Erik Montnemery <erik@montnemery.com>

* Update test to also test for trigger keys

---------

Co-authored-by: Erik Montnemery <erik@montnemery.com>
 2024-09-25 14:19:58 +02:00
epenet
88cacbc898
Expose component constants for llm helper (#125891) 
* Expose climate INTENT_GET_TEMPERATURE

* Expose conversation trace items

* More fixes for llm helper
 2024-09-13 12:43:37 +02:00
Denis Shulyaka
a85ccb94e3
LLM Tool parameters check (#123621) 
* LLM Tool parameters check

* fix tests
 2024-09-08 18:42:51 -07:00
Denis Shulyaka
ed6d6575d7
Add aliases to script llm tool description (#122380) 
* Add aliases to script llm tool description

* Also add name
 2024-08-02 08:05:06 +02:00
Allen Porter
8d0e998e54
Improve conversation agent tracing to help with eval and data collection (#122542) 2024-07-31 14:38:44 +02:00
Denis Shulyaka
be24475cee
Update selector converters for llm script tools (#122830) 2024-07-30 08:24:03 -07:00
Allen Porter
e5bb1b2cc6
Update LLM prompt to improve quality for local LLMs (#122746) 2024-07-29 12:04:23 +02:00
Denis Shulyaka
064d7261b4
Ensure script llm tool name does not start with a digit (#122349) 
* Ensure script tool name does not start with a digit

* Fix test name
 2024-07-22 11:11:09 +02:00
Michael Hansen
417abda649
Add HassGetCurrentDate and HassGetCurrentTime intents (#121707) 2024-07-11 00:17:04 +02:00
Alan
8ff4991f07
LLM to handle int attributes (#121037) 2024-07-06 11:41:18 +02:00
Michael Hansen
d3ceaef098
Allow timer management from any device (#120440) 2024-06-26 09:06:56 +02:00
Marc Mueller
49df0c4366
Improve schema typing (2) (#120475) 2024-06-26 02:25:30 +02:00
Denis Shulyaka
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
Paulus Schoutsen
5c2db162c4
Remove "no API" prompt (#120280) 2024-06-24 08:57:59 +02:00
Paulus Schoutsen
19f97a3e53
LLM to handle decimal attributes (#120257) 2024-06-23 17:09:57 -04:00
tronikos
ad1f0db5a4
Pass prompt as system_instruction for Gemini 1.5 models (#120147) 2024-06-22 12:35:48 +02:00
Paulus Schoutsen
c49ca5ed56
Ensure intent tools have safe names (#119144) 2024-06-08 17:53:47 +02:00
Paulus Schoutsen
52ad90a68d
Include script description in LLM exposed entities (#118749) 
* Include script description in LLM exposed entities

* Fix race in test

* Fix type

* Expose script

* Remove fields
 2024-06-04 11:18:07 -04:00
tronikos
f9dff1632e
Use ISO format when passing date to LLMs (#118705) 2024-06-03 19:48:50 +02:00
Paulus Schoutsen
bdcfd93129
Automatically fill in slots based on LLM context (#118619) 
* Automatically fill in slots from LLM context

* Add tests

* Apply suggestions from code review

Co-authored-by: Allen Porter <allen@thebends.org>

---------

Co-authored-by: Allen Porter <allen@thebends.org>
 2024-06-03 10:36:41 -04:00
Paulus Schoutsen
f3b20d30ae
Add base prompt for LLMs (#118592) 2024-06-01 00:21:37 -04:00
tronikos
dfb407728f
Stop instructing LLM to not pass the domain as a list (#118590) 2024-05-31 20:21:18 -04:00
Paulus Schoutsen
6dd01dbff7
Rename llm.ToolContext to llm.LLMContext (#118566) 2024-05-31 11:11:24 -04:00
tronikos
2bd142d3a6
Improve LLM prompt (#118520) 2024-05-30 22:03:57 -04:00
tronikos
272c51fb38
Fix unnecessary single quotes escaping in Google AI (#118522) 2024-05-30 19:56:06 -04:00
tronikos
0d6c7d0973
Fix LLMs asking which area when there is only one device (#118518) 
* Ignore deprecated open and close cover intents for LLMs

* Fix LLMs asking which area when there is only one device

* remove unrelated changed

* remove unrelated changes
 2024-05-30 17:14:11 -04:00
tronikos
6d82cfa91a
Ignore deprecated open and close cover intents for LLMs (#118515) 2024-05-30 16:29:13 -04:00
Paulus Schoutsen
80588d9c67
Ignore the toggle intent (#118491) 2024-05-30 12:53:50 -04:00
tronikos
4893faa671
Instruct LLM to not pass a list to the domain (#118451) 2024-05-30 08:37:45 +02:00
tronikos
639f6c640c
Improve LLM prompt (#118443) 
* Improve LLM prompt

* test

* improvements

* improvements
 2024-05-29 21:44:33 -04:00
tronikos
4056c4c2cc
Ask LLM to pass area name and domain (#118357) 2024-05-29 08:03:43 -04:00
tronikos
c75cb08aae
Fix LLM tracing for Google Generative AI (#118359) 
Fix LLM tracing for Gemini
 2024-05-29 08:02:59 -04:00
tronikos
b7ee90a53c
Expose useful media player attributes to LLMs (#118363) 2024-05-29 08:01:40 -04:00
Paulus Schoutsen
d22871f1fd
Reduce the intent response data sent to LLMs (#118346) 
* Reduce the intent response data sent to LLMs

* No longer delete speech
 2024-05-28 23:07:00 -04:00
Paulus Schoutsen
c097a05ed4
Tweak Assist LLM API prompt (#118343) 2024-05-28 22:43:22 -04:00
Paulus Schoutsen
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
Paulus Schoutsen
f0d7f48930
Handle generic commands as area commands in the LLM Assist API (#118276) 
* Handle generic commands as area commands in the LLM Assist API

* Add word area
 2024-05-28 11:21:17 -04:00
Paulus Schoutsen
6f248acfd5
LLM Assist API: Inline all exposed entities (#118273) 
Inline all exposed entities
 2024-05-27 21:12:10 -04:00
Paulus Schoutsen
ecb05989ca
Add exposed entities to the Assist LLM API prompt (#118203) 
* Add exposed entities to the Assist LLM API prompt

* Check expose entities in Google test

* Copy Google default prompt test cases to LLM tests
 2024-05-27 00:27:08 -04:00
Paulus Schoutsen
1602c8063c
Standardize LLM instructions prompt (#118195) 
* Standardize instructions prompt

* Add time/date to default instructions
 2024-05-26 20:24:26 -04:00
Paulus Schoutsen
233c3bb2be
Add render prompt method when no API selected (#118136) 2024-05-26 13:35:15 +02:00
Denis Shulyaka
cee3be5f7a
Break long strings in LLM tools (#118114) 
* Break long code strings

* Address comments

---------

Co-authored-by: Paulus Schoutsen <balloob@gmail.com>
 2024-05-25 14:24:51 -04:00
Allen Porter
89e2c57da6
Add conversation agent debug tracing (#118124) 
* Add debug tracing for conversation agents

* Minor cleanup
 2024-05-25 14:16:51 -04:00
Denis Shulyaka
da74ac06d7
Add user name and location to the LLM assist prompt (#118071) 
Add user name and location to the llm assist prompt
 2024-05-24 22:23:05 -04:00
Paulus Schoutsen
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
Paulus Schoutsen
1f7245ecf2
Update LLM no tools message (#117935) 2024-05-22 21:17:03 -04:00
Denis Shulyaka
009c9e79ae
LLM Tools: Add device_id (#117884) 2024-05-21 21:24:46 -04:00
Paulus Schoutsen
f21226dd0e
Address late feedback Google LLM (#117873) 2024-05-21 20:11:18 +02:00
Michael Hansen
8079cc0464
Add description to intent handlers and use in LLM helper (#117864) 2024-05-21 12:54:34 -04:00
Denis Shulyaka
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