-
Given
```
schema doc {
document doc {
field chunks type array {}
}
field embedding type tensor(p{}, x[384]) {}
```
You can do things like
```
rank-profile example {
in…
-
We should document somewhere what the score means; what is its range? From -1 to 1? Is it cosine similarity? Probably in the docstring on the search endpoint
-
The SWR will identify duplicates based on metadata. [https://github.com/soilwise-he/Soilwise-userstories/issues/16](url)
Origin: D1.3 [Repository architecture](https://ilvo.sharepoint.com/:w:/s/HE…
-
I noticed that the library computes the similarity between vectors in a strange manner. The scores are not really cosine similarity but cross-products. @jwijffels , do you think it is intentional?
…
-
### Have you searched existing issues? 🔎
- [X] I have searched and found no existing issues
### Desribe the bug
Dear creators of BERTopic,
Thanks for your work and this package is amazing. …
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
After doing some analysis using the LlamaDebugHandler, I noticed that all the vectors + …
-
Hey,
First, thanks for the kind words in various places :). I came across your posts, which led me here.
I also spent quite some time working on similarity models. I think they're surprisingly d…
-
### Which component is this bug for?
All Packages
### 📜 Description
Tried using Traceloop version 0.26.4 with different vector databases while trying to run a RAG application (watsonx + langchain) …
-
### What happened?
Here are my steps:
Step 1) Create embedding for document-1(a small document with 100 chunks) and save in chroma-db vector store
After Step 1) making any query relevant to documen…
-
### Checked other resources
- [X] I added a very descriptive title to this issue.
- [X] I searched the LangChain documentation with the integrated search.
- [X] I used the GitHub search to find a sim…