feat(ai): add how to query rerank models #5873
Open
Conversation
This file contains hidden or 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
RoRoJ
added
type: new content
bene2k1
reviewed
Nov 26, 2025
bene2k1
approved these changes
Nov 26, 2025
Co-authored-by: Benedikt Rollik <brollik@scaleway.com>
nerda-codes
reviewed
Nov 27, 2025
|
|
||
| For example: a query to a fast (but imprecise) model may return a list of 100 documents. A specialized reranking model can then evaluate these documents more deeply, score each on how well it matches the query, and return only the 10 most relevant documents to the first model to be used in answering the query. | ||
|
|
||
| This approach takes advantage of the strengths of each model: one that is fast but not specialized, which can generate candidates quickly, and another than is slow but specialized, to refine these candidates. It can result in reduced context windows with therefore improved relevance, and faster overall query processing time. |
Contributor
There was a problem hiding this comment.
Suggested change
| This approach takes advantage of the strengths of each model: one that is fast but not specialized, which can generate candidates quickly, and another than is slow but specialized, to refine these candidates. It can result in reduced context windows with therefore improved relevance, and faster overall query processing time. | |
| This approach takes advantage of the strengths of each model: one that is fast but not specialized, which can generate candidates quickly, and another that is slow but specialized, to refine these candidates. It can result in reduced context windows with therefore improved relevance, and faster overall query processing time. |
Comment on lines
+33
to
+34
| - Query vector: `qv = embedding(query`) | ||
| - Document vector: `dv = embedding(document content)` |
Contributor
There was a problem hiding this comment.
Suggested change
| - Query vector: `qv = embedding(query`) | |
| - Document vector: `dv = embedding(document content)` | |
| - Query vector: `qv = embedding` (query) | |
| - Document vector: `dv = embedding` (document content) |
| - Document vector: `dv = embedding(document content)` | ||
| - Relevance score: `score = (qv, dv)` (dot product) | ||
|
|
||
| Therefore, if you're performing repeated relevance scoring, you can streamline your workflow as follows: |
Contributor
There was a problem hiding this comment.
Suggested change
| Therefore, if you're performing repeated relevance scoring, you can streamline your workflow as follows: | |
| Therefore, if you are performing repeated relevance scoring, you can streamline your workflow as follows: |
Contributor
|
Ok for me 👍 |
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.
Add doc for querying rerank models