-
Notifications
You must be signed in to change notification settings - Fork 0
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
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- makefile updated with Django related commands - allowed host fix
* Added ollama to docker compose * Changed code to use local embedder model (provisional) * Some Todos must be done yet
This page https://docs.litellm.ai/docs/set_keys explains how to get around the issue previously described. |
* 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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)