Add multi2multivec-weaviate details #323
Conversation
![orca-security-eu[bot]](https://avatars.githubusercontent.com/in/276244?s=60&v=4){kind=small}
There was a problem hiding this comment.
Orca Security Scan Summary
| Status | Check | Issues by priority | |
|---|---|---|---|
 Passed |
Infrastructure as Code |  0  0  0  0 |
View in Orca |
| Passed |
SAST | 0 0 0 0 |
View in Orca |
| Passed |
Secrets | 0 0 0 0 |
View in Orca |
| Passed |
Vulnerabilities | 0 0 0 0 |
View in Orca |
| imageField: 'doc_page', | ||
| model: 'ModernVBERT/colmodernvbert', | ||
| encoding: weaviate.configure.vectorIndex.multiVector.encoding.muvera({ | ||
| ksim: 4, |
There was a problem hiding this comment.
shall we state that these muvera params are optional like in other examples, so users don't need to think about them too much?
we could also remove name (as it's only single vectorizer) and model (to utilize default) to simplify. Especially as query examples below in the documents use default vector (not named vector).
There was a problem hiding this comment.
Good points, I will try to change the vector naming in all model provider pages at some point to make the examples consistent.
| # The model provider integration will automatically vectorize the object | ||
| batch.add_object( | ||
| properties=weaviate_obj, | ||
| # vector=vector # Optionally provide a pre-obtained vector |
There was a problem hiding this comment.
maybe we shouldn't suggest passing a vector, cause the module should vectorize the it.
There was a problem hiding this comment.
I would potentially leave it as there is an option of vectorizing some of the objects and import vectors for others.
What's being changed:
colmodernVBERT) and module (multi2multivec-weaviate) in Weaviate EmbeddingsType of change:
How has this been tested?
yarn start