Skip to content
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

Prompting LLM for all the prompt types #29

Open
sefeoglu opened this issue Feb 7, 2024 · 1 comment
Open

Prompting LLM for all the prompt types #29

sefeoglu opened this issue Feb 7, 2024 · 1 comment
Assignees

Comments

@sefeoglu
Copy link
Owner

sefeoglu commented Feb 7, 2024

Hi @JulianSampels,
Could you help @Tazio-Faha in adapting the codes for getting all the prompts from results_prompts and save them in a similar format here ?

alignments_path = 'alignments.json' # Make sure to update this path
input_file_path = 'treePromptVersion0.json' # Update this path accordingly
all_lines = load_all_lines(input_file_path)
alignments = load_alignments(alignments_path)
# Process all lines and get results
results = process_lines(all_lines, alignments)
# Save the results to a JSON file
output_file_path = 'all_ontology_results.json' # Update this path as needed
save_results_to_json(results, output_file_path)

Thanks in advance,
Best.

@JulianSampels
Copy link
Collaborator

JulianSampels commented Feb 7, 2024

@Tazio-Faha I implemented the import and export for all the prompts which need to be run on the llm.
Just call your llm function here:

prompt = promptDict.get(promptKey)
yesOrNo = 'yes'#ToDo: run prompt here

prompt need to be run on the llm and the result needs to be saved to yesOrNo
so call something like

yesOrNo = llm(prompt)

@JulianSampels JulianSampels pinned this issue Feb 7, 2024
@sefeoglu sefeoglu unpinned this issue Feb 9, 2024
JulianSampels pushed a commit that referenced this issue Feb 16, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

3 participants