mirror of
https://github.com/lrnselfreliance/wrolpi.git
synced 2026-11-21 15:36:18 -05:00
ai: live-chat fixes from first real-model run
Three findings from running Qwen3-1.7B against the docker stack: the llm image lost libgomp when the build tools were removed (llama-server needs the OpenMP runtime); the Help prompt let the small model answer from memory instead of the docs, so it now requires search_help before any answer; and help search results called the slug "doc" while get_help_doc's argument is "slug", so the model invented slugs — the names now match. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
parent
6d14467046
commit
f49ae3aee5
5 changed files with 13 additions and 10 deletions
|
|
@ -133,7 +133,7 @@ def search_help(search_str: str, limit: int = 5) -> (List[dict], int):
|
|||
results = []
|
||||
for score, doc in scored[:limit]:
|
||||
result = dict(
|
||||
doc=doc.slug,
|
||||
slug=doc.slug,
|
||||
title=doc.title,
|
||||
link=help_doc_link(doc.slug),
|
||||
snippet=_snippet(doc.body, tokens),
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue