Vectors from two different embedding models are not comparable — Titan v2 has
1024 dimensions where nomic-embed-text has 768 — and _cosine_similarity zips
them, so a mismatch produced quietly meaningless scores rather than an error.
Nothing forced a re-embed either: sync_local_kb only looked at the content
hash, so switching models left every cached vector in place.
local_knowledge_docs now records the model each vector came from, and a row is
re-embedded when its content hash OR its model differs. Saving a new
LOCAL_KB_EMBEDDING_MODEL from the settings panel starts a background pass over
every file; the knowledge base panel also has a button for it. While that pass
runs, the per-request sync steps aside so no file is embedded twice.
The panel now shows what the embedding model is doing: model name, vector
size, how many files are embedded with the current model, how many are still
on an older one, a progress bar while a pass runs, and the last error. A
"接続テスト" button embeds one short string so a broken or unreachable model
can be told apart from one that is merely slow to warm up.
Also read TAVILY_API_KEY from os.environ at call time. It was imported as a
config constant, which is evaluated before load_into_env() runs, so a key
saved from the settings panel was stored but never used — not even after a
restart.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Summarizing web search results falls back to DEFAULT_MODEL, so a local Ollama
model ends up doing it and the call can fail — which surfaces only as
"保存できる要約なし" in the chat. Make SEARCH_SUMMARY_MODEL settable at runtime:
add it to the settings allowlist and read it from os.environ on each call
(knowledge._summary_model), the way LOCAL_KB_EMBEDDING_MODEL already works.
Importing it as a config constant would keep the old value until a restart.
Show the current value of the settings that are not secrets. A model name
rendered as ••••qwen3 gives no way to tell what is in effect, so the store now
marks those keys (NON_SECRET_KEYS) and returns them unmasked; the API field is
renamed masked -> display_value and carries a secret flag that the panel uses
to pick the input type, replacing the list it kept on its own side.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
- Add a password-protected /api/settings endpoint (HTTP Basic auth,
backend/app/core/auth.py) backed by a DB-stored allowlist of
connection settings (OPENAI_API_KEY, ANTHROPIC_API_KEY, AWS creds,
OLLAMA_API_BASE, TAVILY_API_KEY, LOCAL_KB_EMBEDDING_MODEL). Saved
values override .env and apply immediately via os.environ, so
Lightsail deployments no longer need SSH + `.env` edits to rotate
keys. Values are always returned masked to the frontend.
- Replace ModelSelector.vue's hardcoded model list with a DB-backed
/api/models CRUD API (read is public, writes reuse the settings
password) so the chat model dropdown can be edited from the GUI;
seed it once with the previous hardcoded presets on first boot.
- Fix local_knowledge.py reading LOCAL_KB_EMBEDDING_MODEL once at
import time instead of per-call, which would have silently ignored
GUI/DB overrides for the embedding model.
- Add SettingsPanel.vue (API keys + model management UI) and document
the new SETTINGS_PASSWORD env var in .env.example and the Lightsail
deploy guide.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
colcaroliandClaude Opus 5