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

Created a function for embeddings options #732

Conversation

tedcochran
Copy link
Contributor

Chroma was not creating its vector database because embeddings were not explicitly set in the ingest.py or run_localGPT.py files. This creates a function get_embeddings() for that purpose.

@tedcochran tedcochran closed this Feb 4, 2024
@tedcochran tedcochran reopened this Feb 4, 2024
@PromtEngineer PromtEngineer merged commit c70d068 into PromtEngineer:main Feb 4, 2024
@tedcochran tedcochran deleted the issue-731-embeddings-not-callable branch February 4, 2024 12:08
@asegun-cod
Copy link

compute_device variable is missing. Also it's better you define get_embeddings outside main()

@PromtEngineer
Copy link
Owner

@asegun-cod good catch, it was an oversight from my end as well :) Moved it to utils.py and fixed the compute_device parameter. Just needs to be device_type.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants