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

Difficulty Configuring Alibaba's text-embedding-v3 Model in Letta #2143

Open
ccxx2017 opened this issue Dec 3, 2024 · 1 comment
Open

Difficulty Configuring Alibaba's text-embedding-v3 Model in Letta #2143

ccxx2017 opened this issue Dec 3, 2024 · 1 comment

Comments

@ccxx2017
Copy link

ccxx2017 commented Dec 3, 2024

I'm trying to use Alibaba's "text-embedding-v3" as an embedding model in Letta, but I'm experiencing difficulties with the implementation. I've attempted the following configuration:
EmbeddingConfig(
embedding_model="text-embedding-v3",
embedding_endpoint_type="openai",
embedding_endpoint="https://dashscope.alibabyncs.com/compatible-model/v1",
embedding_dim=1024,
embedding_chunk_size=8192
)
Specific Questions:

How can I properly configure and use text-embedding-v3 in Letta?
Are there any special steps or additional configurations required?
Is this model fully supported in the current version of Letta?

@sarahwooders
Copy link
Collaborator

What the error you get when you run with the endpoint?

@sarahwooders sarahwooders reopened this Dec 6, 2024
@github-project-automation github-project-automation bot moved this from To triage to Done in 🐛 MemGPT issue tracker Dec 6, 2024
@github-project-automation github-project-automation bot moved this from Done to Backlog in 🐛 MemGPT issue tracker Dec 6, 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

No branches or pull requests

2 participants