You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
# -- Set the source directory
PATH_TO_SEARCH_FOR_PDFS=$HOME
PATH_TO_MV_PDFS=$HOME/maf_data/maf_pdfs/
# -- Find all PDFs recursively from root directory
pdfs=$(find "$PATH_TO_SEARCH_FOR_PDFS" -name "*.pdf")
echo $pdfs
# -- Make output dir if it doesn't exist
mkdir -p $PATH_TO_MV_PDFS
gorilla "filter my pdfs zsh list based on which names are likely to be textbooks about mathematics or science, reassign it to pdfs2 and echo the list"
but the output command worries me
Welcome to Gorilla-CLI! Enhance your Command Line with the power of LLMs!
Simply use `gorilla <your desired operation>` and Gorilla will do the rest. For instance:
gorilla generate 100 random characters into a file called test.txt
gorilla get the image ids of all pods running in all namespaces in kubernetes
gorilla list all my GCP instances
A research prototype from UC Berkeley, Gorilla-CLI ensures user control and privacy:
- Commands are executed only with explicit user approval.
- While queries and error (stderr) logs are used to refine our model, we NEVER gather output (stdout) data.
Visit github.com/gorilla-llm/gorilla-cli for examples and to learn more!
🦍 Welcome to Gorilla. Use arrows to select
» pdfs2=$(ls *.pdf | grep -Ei 'math|science|physics|calculus|chemistry|biology|algebra|geometry'); echo $pdfs2
git filter-branch --renormalize-all --copy-to pdfs2 --echo pdfs | git rev-parse --git-dirty
find . -name '*.pdf' | grep -i -E '(math|science)' | xargs -I {} mv {} pdfs2 2> /dev/null; echo pdfs2/*
: #Do nothing
I would have wanted that gorilla passes the file names in the pdfs to an LLM to infer if it's a maths textbook, not use hardcoded works that are unlikely to work.
How to modify it so to filter it using the LLMs themselves?
let's try
gorilla "filter my pdfs zsh list based on which names are likely to be textbooks about mathematics or science using an LLM, reassign it to pdfs2 and echo the list"
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I'm trying this:
but the output command worries me
I would have wanted that gorilla passes the file names in the pdfs to an LLM to infer if it's a maths textbook, not use hardcoded works that are unlikely to work.
How to modify it so to filter it using the LLMs themselves?
let's try
Beta Was this translation helpful? Give feedback.
All reactions