[WIP] [feat](search): use elastic for lexical search #37
Conversation
This file contains 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
dtrckd
reviewed
Oct 11, 2024
app/schemas/search.py
Outdated
| @@ -10,6 +10,7 @@ class SearchRequest(BaseModel): | |||
| prompt: str | |||
| collections: List[Union[UUID, Literal[INTERNET_COLLECTION_ID]]] | |||
| k: int = Field(gt=0, description="Number of results to return") | |||
| method: Literal["vectors", "keywords", "hybrid"] = Field(default="semantic") | |||
There was a problem hiding this comment.
"semantic" is not defined in the method literal ?
I would use Literal["semantic", "lexical", "hybrid"] that seems to better reflect the choices to me.
- semantic : dense vector based similarity (embedding)
- lexical : sparse vector based similarity (bm25/tfidf)
- hybrid : combine both (with reranker, like RRF)
Ledoux
changed the title
Ledoux
force-pushed
the
feat-search-use-elastic
branch
from
b30007e
to
3d4c96f
Compare
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Outdated suggestions cannot be applied.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.
Contexte
Il faut aider nos utilisateurs de l'api albert à effectuer une recherche sur leurs documents à l'aide d'une approche elastic et sémantique.
Rendus
Recherche sur internet en hybridsearch : dans une autre feature.
Interdire la collection internet si HybridSearch dans un premier temps.