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

Embedding model change #69

Closed
davidfungf opened this issue May 10, 2024 · 5 comments
Closed

Embedding model change #69

davidfungf opened this issue May 10, 2024 · 5 comments
Labels
question Further information is requested

Comments

@davidfungf
Copy link

According to the article, If I want to change the embedding model from text-embedding-ada-002 to text-embedding-3-small. Which code shall I modify?

Your tutorial inspires my interests on RAG very much. Thank you!!

- [ ] bug report -> please search issues before submitting
- [ ] feature request
- [X] documentation issue or request
- [ ] regression (a behavior that used to work and stopped in a new release)
@davidfungf
Copy link
Author

davidfungf commented May 10, 2024

I just found the answers in the faq.md. Do I need to rebuild the code and upload the documents again?

azd env set AZURE_OPENAI_API_EMBEDDINGS_MODEL text-embedding-3-large

@glaucia86
Copy link
Contributor

glaucia86 commented May 12, 2024

Hi, @davidfungf . How are you?

It depends. If you want to use the Azure OpenAI Service, you can use AI Studio to create the embedding you want to use and change it with the command used.

Now, if you're using an LLM's Open Source you should change the file constants.ts file

@sinedied
Copy link
Contributor

Regarding the deployment, if changing the embedding model for the deployed version you need to delete the existing index in your AI Search instance in the portal:

image

This is needed as the vector length might differ.

Then you need to redeploy the app with azd up

@davidfungf
Copy link
Author

Thank you for your support!

Suggestion: You may consider using Azure Document Intelligence Layout Model to generate the Markdown components to enhance the data accuracy. I looking forward to seeing your post soon.

@sinedied sinedied added the question Further information is requested label May 16, 2024
@sinedied
Copy link
Contributor

Using Azure Document Intelligence is on our watchlist for a possible add-on, the initial idea for this one sample was to make it as simple as possible to understand.

We also have other more full-featured samples like this one, that uses Azure Document Intelligence for ingestion.

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

No branches or pull requests

3 participants