6e8b3d9e8e
llm_client_backend: add object type to completion marker
...
The OpenAI chat completion API shows that streaming chat completion
chunks should have the object type "chat.completion.chunk" in the
completion marker chunk. Without this, some parsers of the OpenAI API
don't handle chat completion streaming responses from this server.
This commit fixes the lack of an object type, keeps compliance with the
described API in the OpenAI docs (see
https://platform.openai.com/docs/api-reference/chat/create ), and ensures
parsers like the Home Assistant HomeLLM addon work with it.
2026-01-18 14:09:58 -05:00
6dd2b784f7
[feat] The tts backend supports model switching.
2025-04-23 14:47:10 +08:00
d5a2dc4755
[perf] Optimize contextual conversations
2025-04-23 12:25:31 +08:00
bfbc3f5414
[fix] Fix language parameter passing
2025-04-17 18:28:17 +08:00
33477071ca
[feat] The asr backend supports model switching.
2025-04-16 19:24:31 +08:00
cb13b0acea
[fix] Fix wrong fields
2025-04-15 19:38:36 +08:00
c0bcfd4d4b
[perf] Add audio segmentation and transcoding
2025-04-15 16:36:40 +08:00
0bf4767ff0
[chore] Delete log printing
2025-04-15 14:10:09 +08:00
f860eb74be
[perf] Increase chunk_size and add sending interval
2025-04-15 10:35:09 +08:00
fe73b135c7
[perf] Audio base64 data is sent using streaming
2025-04-14 17:59:03 +08:00
d54df28357
[refactor] Refactor tts_client_backend
2025-04-14 14:16:27 +08:00
46e0ecf3b2
[refactor] Refactor asr_client_backend
2025-04-14 11:03:56 +08:00
b7fa5ad767
[fix] Fixed multiple exit issues
2025-04-11 18:01:40 +08:00
21ab7c7ac7
[fix] Optimize the llm model switching method and fix the instance exit problem
2025-04-11 17:25:56 +08:00
8651a0f39b
[fix] Fix client pool lock.Optimization task paused
2025-04-11 11:18:14 +08:00
538b219c48
[perf] Optimize different model loading methods
2025-04-09 19:46:43 +08:00
fec1b48996
[perf] Optimize model loading method
2025-04-09 19:45:45 +08:00
423fa93a70
[perf] Optimize token statistics method
2025-04-09 15:56:50 +08:00
82997ac42b
[clean] Clean up the code
2025-04-08 18:07:54 +08:00
dcc871d145
[fix] Fix model list retrieval
2025-03-25 11:36:12 +08:00
ccbf41e636
[perf] Optimize model loading flow
2025-03-18 18:09:19 +08:00
c9304f1635
[fix] Fixed client request timeout bug
2025-02-26 11:07:49 +00:00
c64f974a7d
[perf] Optimize llm_client parameter configuration method
2025-02-26 08:38:54 +00:00
131c628351
[feat] Add CMM size verification
2025-02-26 03:49:17 +00:00
5879061a54
[feat] Add sys_client
2025-02-25 20:59:11 +08:00
Kit Rhett Aultman
LittleMouse
LittleMouse