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.

Sign up for GitHub

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

Jump to bottom

Integrate w/ LLaMA #150

Open

rlancemartin wants to merge 2 commits into assafelovic:master from rlancemartin:rlm/ollama

rlancemartin commented Aug 23, 2023 •

edited

We use Ollama for integration w/ LLaMA:

Follow setup instructions note in the linked docs.

Note: output formatting for lists requires particular prompts.

Good topic for prompt management @efriis

I can get the app to run locally end-to-end w/ LLaMA2-7b as configured in this PR:

But, some notes as I hit a bunch of system errors running this:

Many additional pkgs needed beyond pip installs:brew install fontconfig, harfbuzz, pango, glib
Mismatch btwn chrome and chromedriver versions most likely throwing below error (seen in final prompt).

Message: Can not connect to the Service /Users/rlm/.cache/selenium/chromedriver/mac-arm64/116.0.5845.96/chromedriver

But these are issues independent of LLaMA, and I'm not sure they are reproduced for others.
In any case, the changes reflected here should enable running gpt-researcher locally w/ LLaMA.


          Integrate w/ LLaMA

084762f

rlancemartin force-pushed the rlm/ollama branch from 8e749ae to 084762f Compare

August 23, 2023 21:17


          Update prompts for returning lists

5a0bdb8

gregdrizz mentioned this pull request

integration with open source model #132

Closed

assafelovic mentioned this pull request

Local Execution Support for LLM Models #188

Closed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment