Jump to content

philocalyst

Member
  • Posts

    5
  • Joined

  • Last visited

Recent Profile Visitors

The recent visitors block is disabled and is not being shown to other users.

philocalyst's Achievements

Helping Hand

Helping Hand (3/5)

0

Reputation

  1. Got it. So my history was growing exponentially and that was what was reflected in the tokens. For some reason I thought if I wasn't in the chat window it was a new conversation each time. The context option is still misleading to me, I wish it was clearer those are messages included, it was my first assumption but I feel it's fair to say how "context" is dealt with in AI engineering is by tokens not chat messages. Thank you for being so kindly dealing with these issues, it's generous of you.
  2. Just a general concern, which caused another problem as I tried to fix it, for some reason when I send in a query through the workflow it will somehow use 40,000+ tokens?! Then I tried to shorten my context window (even though I'm not within the actual chat view so it shouldn't matter) and now it's saying messages: first message must use the "user" role Is this expected behavior? Don't know what to do, I find it very convenient just not worth the 20 cents per query.
  3. Would you consider adding a fallback search option? Mainly for when the API is being slow, the ability to open it in the traditional Moby search would be comforting to me.
  4. Love the utility! Thank you for putting this together. I use a dark theme, and I like larger text in general, and I don't see options to edit the font size or colors of the interface... Is this something that could be implemented?
  5. Hey! As someone who was just using moby as a web search option, this was super cool to see! It was only working for single-word inputs for me, so I went ahead and added it so it works for multi-word inputs as well if you want to add that to the main functionality: #!/usr/bin/env zsh api_key="${moby_games_api_key}" if [[ $api_key ]] then title="$*" url="https://api.mobygames.com/v1/games" json=`curl --get --data-urlencode "format=normal" --data-urlencode "limit=25" --data-urlencode "title=$title" --data-urlencode "api_key=$api_key" $url` json=${json:gs/\"games\"\:/\"items\"\:} json=${json:gs/"game_id"/"uid"} json=${json:gs/"moby_url"/"url"} # remove description to speed things up json=`echo -E $json | jq '.items |= map(del(.description))'` # add arg which is the URL we will pass to Open URL json=`echo -E $json | jq '.items[] |= (. + {arg: .url})'` # add platforms and release years as subtitle json=`echo -E $json | jq '.items |= map(. + {subtitle: (.platforms | map("\(.platform_name) (\(.first_release_date[0:4]))") | join(", "))})'` # cmd for Moby Games URL, cmd+shift for Official URL json=`echo -E $json | jq '.items |= map(if .official_url then . + {mods: { cmd: {valid: true, arg: .url, subtitle: .url}, "shift+cmd": {valid: true, arg: .official_url, subtitle: .official_url} }} else . + {mods: { cmd: {valid: true, arg: .url, subtitle: .url} }} end)'` echo -n $json fi Thank you for making this workflow a reality! Just a suggestion.
×
×
  • Create New...