Merge pull request #173 from acon96/release/v0.3.3

Release v0.3.3
acon96 · Jun 15, 2024 · 75813de · 75813de
2 parents 9f7aa19 + 7393eae
commit 75813de
Show file tree

Hide file tree

Showing 12 changed files with 224 additions and 118 deletions.
diff --git a/README.md b/README.md
@@ -132,6 +132,7 @@ In order to facilitate running the project entirely on the system where Home Ass
 ## Version History
 | Version | Description                                                                                                                                                                                                          |
 |---------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| v0.3.3  | Improvements to the Generic OpenAI Backend, improved area handling, fix issue using RGB colors, remove EOS token from responses, replace requests dependency with aiohttp included with Home Assistant               |
 | v0.3.2  | Fix for exposed script entities causing errors, fix missing GBNF error, trim whitespace from model output                                                                                                            |
 | v0.3.1  | Adds basic area support in prompting, Fix for broken requirements, fix for issue with formatted tools, fix custom API not registering on startup properly                                                            |
 | v0.3    | Adds support for Home Assistant LLM APIs, improved model prompting and tool formatting options, and automatic detection of GGUF quantization levels on HuggingFace                                                   |

diff --git a/TODO.md b/TODO.md
@@ -1,14 +1,14 @@
 # TODO
-- [ ] support new LLM APIs  
+- [x] support new LLM APIs  
     - rewrite how services are called  
     - handle no API selected  
     - rewrite prompts + service block formats  
     - implement new LLM API that has `HassCallService` so old models can still work  
-    - update dataset so new models will work with the API  
+- [ ] update dataset so new models will work with the API  
 - [ ] make ICL examples into conversation turns  
 - [ ] translate ICL examples + make better ones  
-- [ ] areas/room support  
-- [ ] convert requests to aiohttp  
+- [x] areas/room support  
+- [x] convert requests to aiohttp  
 - [x] detection/mitigation of too many entities being exposed & blowing out the context length  
 - [ ] figure out DPO to improve response quality  
 - [x] setup github actions to build wheels that  are optimized for RPIs

diff --git a/custom_components/llama_conversation/__init__.py b/custom_components/llama_conversation/__init__.py
@@ -75,10 +75,13 @@ def create_agent(backend_type):
 
         return agent_cls(hass, entry)
 
-    # load the model in an executor job because it takes a while and locks up the UI otherwise
+    # create the agent in an executor job because the constructor calls `open()`
     backend_type = entry.data.get(CONF_BACKEND_TYPE, DEFAULT_BACKEND_TYPE)
     agent = await hass.async_add_executor_job(create_agent, backend_type)
 
+    # call load model
+    await agent._async_load_model(entry)
+
     # handle updates to the options
     entry.async_on_unload(entry.add_update_listener(update_listener))