Commit graph

15 commits

Author SHA1 Message Date
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
676fe5a9a2
Add recommended model options to OpenAI (#118083)
* Add recommended options to OpenAI

* Use string join
2024-05-25 00:01:48 -04:00
Paulus Schoutsen
a257f63119
Add device info to OpenAI (#118077) 2024-05-24 23:55:01 -04:00
Paulus Schoutsen
3b2cdb63f1
Update OpenAI defaults (#118059)
* Update OpenAI defaults

* Update max temperature
2024-05-24 15:37:44 -04:00
Denis Shulyaka
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
Sid
2cc916db6d
Replace pylint broad-except with Ruff BLE001 (#116250) 2024-05-07 14:00:27 +02:00
Marc Mueller
988c71ecc5
Add empty line after module docstring [n-q] (#112702) 2024-03-08 15:04:07 +01:00
Erik Montnemery
e0c1feb22c
Migrate integrations n-r to generic flowhandler (#111864) 2024-02-29 20:09:01 +01:00
Denis Shulyaka
1242456ff1
Bump openai end switch from dall-e-2 to dall-e-3 (#104998)
* Bump openai

* Fix tests

* Apply suggestions from code review

* Undo conftest changes

* Raise repasir issue

* Explicitly use async mock for chat.completions.create

It is not always detected correctly as async because it uses a decorator

* removed duplicated message

* ruff

* Compatibility with old pydantic versions

* Compatibility with old pydantic versions

* More tests

* Apply suggestions from code review

Co-authored-by: Paulus Schoutsen <paulus@home-assistant.io>

* Apply suggestions from code review

---------

Co-authored-by: Paulus Schoutsen <paulus@home-assistant.io>
2023-12-11 09:47:26 -05:00
Joseph
df025b5993
Enumerate openai.Models to validate config (#99438) 2023-11-24 13:14:44 +01:00
Paulus Schoutsen
325733158d
Allow multiple instances for OpenAI (#90609)
* Allow multiple instances for OpenAI

* Add test
2023-04-12 08:29:13 -04:00
Paulus Schoutsen
885be98f8f
OpenAI to use GPT3.5 (#90423)
* OpenAI to use GPT3.5

* Add snapshot
2023-03-29 05:37:43 +02:00
Franck Nijhof
f9d7d65f3a
Use template selector for prompt template in OpenAI (#87205)
* Use template selector for prompt template in OpenAI

* Fix tests

* Do not parse template result
2023-02-02 15:20:10 -05:00
Ben Dews
21d1c647c5
Add configuration options to OpenAI integration (#86768)
* Added multiple features to OpenAI integration

* Fixed failed test

* Removed features and improved tests

* initiated component before starting options flow
2023-01-30 08:24:11 -05:00
Paulus Schoutsen
7d641e4d3e
Add OpenAI integration (#86621)
* Add OpenAI integration

* Remove empty manifest fields

* More prompt tweaks

* Update manifest

* Update homeassistant/components/openai_conversation/config_flow.py

Co-authored-by: Franck Nijhof <git@frenck.dev>

* Address comments

* Add full integration tests

* Cripple the integration

* Test single instance

Co-authored-by: Franck Nijhof <git@frenck.dev>
2023-01-25 11:30:13 -05:00