github/home-llm
1
1
Fork 0
mirror of https://github.com/acon96/home-llm.git synced 2026-01-09 21:58:00 -05:00
Code Issues Packages Projects Releases Wiki Activity

fix openai responses backend

Browse Source
This commit is contained in:
Alex O'Connell
2025-09-15 22:10:25 -04:00
parent 1425413fc9
commit 1394dcb5d2
2 changed files with 67 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
TODO.md
View File

@@ -5,6 +5,7 @@
- [ ] new model based on qwen3 0.6b
- [ ] new model based on gemma3 270m
- [ ] support AI task API
- [ ] move llamacpp to a separate process because of all the crashing
- [x] support new LLM APIs
- rewrite how services are called
- handle no API selected
@@ -44,14 +45,13 @@
## v0.4 TODO for release:
[ ] re-order the settings on the options config flow page. the order is very confusing
[ ] split out entity functionality so we can support conversation + ai tasks
[x] fix icl examples to match new tool calling syntax config
[x] set up docker-compose for running all of the various backends
[ ] fix and re-upload all compatible old models (+ upload all original safetensors)
[ ] move llamacpp to a separate process because of all the crashing
[ ] dedicated localai backend (tailored openai variant /w model loading)
[ ] fix the openai responses backend
- [ ] re-order the settings on the options config flow page. the order is very confusing
- [ ] split out entity functionality so we can support conversation + ai tasks
- [x] fix icl examples to match new tool calling syntax config
- [x] set up docker-compose for running all of the various backends
- [ ] fix and re-upload all compatible old models (+ upload all original safetensors)
- [ ] dedicated localai backend (tailored openai variant /w model loading)
- [x] fix the openai responses backend
## more complicated ideas
- [ ] "context requests"