HunterGerlach / deep-thought

A question-answering system that uses embeddings and a language model to find the most likely answer to a question, while also providing links to sources that support the answer.

GNU General Public License v3.0

8 stars 2 forks source link

add capacity for self-hosted llama model #57

Closed MichaelClifford closed 1 year ago

MichaelClifford commented 1 year ago

PR Type

[ ] Bugfix
[x] Feature
[ ] Code Style Update
[ ] Refactor
[ ] Deployment
[ ] Security Patch
[ ] Documentation Update

Summary

Added the capacity to utilize a self hosted llama2 model.

Description

Checklist

[x] I have performed a self-review of my own code
[x] I have commented my code, particularly in hard-to-understand areas
[ ] I have made corresponding changes to the documentation
[ ] I have added tests that prove my fix is effective or that my feature works
[x] I have run make lint, make test, and make test-api locally and resolved any errors

Security Checklist

[x] Data encryption
[x] No hardcoded secrets
[x] Proper access controls

Additional Context (if applicable)

Kubernetes/OpenShift Version:
LLM & Relevant Configuration:

Screenshots (if applicable)

Related Tickets

25

hemajv commented 1 year ago

@MichaelClifford @HunterGerlach I was able to test this out locally and resolve all my errors. Worked fine for me! 👍

/lgtm 🚢