Feature/geo aware place retrieval - #16
Open
pepecanomanuelclaver wants to merge 3 commits into
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Hi @Gerson-datacation , find here the pr for the geo-location tool.
Added geo-aware ranking as a retrieval method (it's qwen_hybrid_geo).
Pages get geocoded once via just geocode-pages (1. LLM picks up the name and stored in page_locations, 2. nominatim turns into latitude and longitude).
When querying, if it name's a place (checked with the llm), we rescale each candidate chunk's score by distance to it. Far ones never get deleted fully.
The existing qwen_hybrid retriever is plugged into eval like any other method.
Added tests for the distance.