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

129 get settings from config model #136

Closed
wants to merge 22 commits into from

Conversation

jpb18
Copy link
Contributor

@jpb18 jpb18 commented Oct 29, 2024

So here's the thing:

While its easy to load variables that we're using on our own app as settings, we've an issue with the LiteLLM configurations: we must use the litellm.yaml file for its settings. As such, I was writing something that would replace the variables on the file with their equivalent in the database (see lite_llm_database_config.py) and write a new config file.

There was also the need to update the file every time we updated the model in question, unless we want to reload the app every time we change the value on the model.

I used the following conversations with ChatGPT as an inspiration for the implementation I'm doing now:

https://chatgpt.com/share/6720c298-7bb8-8006-a164-a468e1d2152f
https://chatgpt.com/share/6720c2fd-8090-8006-bc70-1631b4dff7df

(and some extra research to corroborate what the bot was saying)

kenvontucky and others added 2 commits October 28, 2024 12:30

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
- makefile updated with Django related commands
- allowed host fix
@jpb18 jpb18 linked an issue Oct 29, 2024 that may be closed by this pull request
* Added ollama to docker compose
* Changed code to use local embedder model (provisional)
* Some Todos must be done yet
@kenvontucky
Copy link
Collaborator

This page https://docs.litellm.ai/docs/set_keys explains how to get around the issue previously described.

jfrverdasca and others added 19 commits October 29, 2024 16:56
* First working version
* Makefile build added to compose up
* embeddings.py full refactor (Now in labs/embeddings/base)
* added new embeddings method in all code where old version was used
* tests correction
* Readme now have steps to run OpenAI or Local LLM model
* Fix typo in embeddings word
…om-config-model

# Conflicts:
#	config/configuration_variables.py
#	config/models/config.py
#	config/settings.py
#	labs/database/embeddings.py
#	labs/embeddings/vectorizers/chunk_vectorizer.py
#	labs/embeddings/vectorizers/python_vectorizer.py
#	labs/llm.py
#	labs/tasks/llm.py
#	tests/conftest.py
#	tests/database/test_embeddings.py
# Conflicts:
#	config/configuration_variables.py
#	config/models/config.py
#	config/settings.py
#	labs/database/embeddings.py
@kenvontucky kenvontucky closed this Nov 7, 2024
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.

Get settings from config model.
3 participants