- Rather than chunky generic cards, make the suggested actions more action oriented, around the problem a user might want to solve. Give them follow-up options. Design still in progress.
- De facto, was being assumed everywhere if authenticatedData is null, that it's not logged in. This isn't true because the data can still be loading. Update the hook to send additional states.
- Bonus: Delete model picker code and a slew of unused imports.
New conversation have a slug, but older conversation may not. This
change allows those older conversations to still be shareable by using
a random uuid for constructing their url instead
- Some of the instructions were duplicated (e.g illegal, harmful)
- Return format requested was inconsistent
- Safety prompt felt overtly prudish which lowered their utility.
Make it laxer for now, add checks later if required
- Print hash in CI to ease verifying ci built python package matches
khoj package published on pypi
- Newer pypi publish github action should speed up workflow by ~30s
Major
---
Previously we couldn't enable research mode or use other slash
commands in automated tasks.
This change separates determining if a chat query is triggered via
automated task from the (other) conversation commands to run the query
with.
This unlocks the ability to enable research mode in automations
apart from other variations like /image or /diagram etc.
Minor
---
- Clean the code to get data sources and output formats
- Have some examples shown on automations page run in research mode now
This allows online search to work out of the box again
for self-hosting users, as no auth/api key setup required.
Docker users do not need to change anything in their setup flow.
Direct installers can setup Searxng locally or use public instances if
they do not want to use any of the other providers (like Jina, Serper)
Resolves#749. Resolves#990
