-
Notifications
You must be signed in to change notification settings - Fork 28
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Implementation of nf-gpt into crisprseq pipeline. #193
base: dev
Are you sure you want to change the base?
Conversation
This PR is against the
|
|
…gpt functionality calling
…e is run in the first place, otherwise error is thrown.
… generated gpt tockens to 15k. Adjusted gpt questions.
pulling remote changes
This is a very early stage implementation of the nf-gpt plugin into the pipeline. It can currently handles a list of genes extracted from the drugZ, bagel2 or mle module output and parses it to the plugin.
You can run the changes using:
export OPENAI_API_KEY=your-api-key
nextflow run . -profile test_screening,docker --outdir test -dump-channels --gpt_interpretation drugz,mle,bagel2,rra -resume
DISCLAIMER! You will need a functioning Open AI api key. for this to work.
Since this is very early version and only comes with the bare minimum of functionality there are a lot of adjustment that have to me made:
Keep in mind this implementation does not aim to achieve 100% correct results from the gpt model, but instead is to build a foundational implementation for (future) LLMs into a nf-core pipeline.
If you have any suggestions or requested changes please let me know and i will try to adjust the code.