krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-09-30 00:18:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

point notebook links at Colab for direct run

Browse Source 
Switches the two body references to the accompanying notebook from
GitHub URLs to githubtocolab so readers can run it without cloning.
The header table's GitHub link stays for readers who want the source
view.
This commit is contained in:
Dylan Couzon
2026-05-11 21:14:59 -04:00
parent def2b3a39b
commit 5502b91064
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/documentation/tutorials-search-engineering/multi-representation-search.md
+2 -2
View File
@@ -16,7 +16,7 @@ This tutorial builds retrieval that uses each representation deliberately: named
This tutorial assumes you've built hybrid (dense plus sparse) search before, that you're comfortable with [named vectors](/documentation/manage-data/vectors/#named-vectors), the [Query API](/documentation/search/hybrid-queries/), Reciprocal Rank Fusion (RRF), and Best Matching 25 (BM25). If hybrid search is new, start with the [hybrid search section of the Text Search guide](/documentation/search/text-search/#combining-semantic-and-lexical-search-with-hybrid-search) first.
If you'd rather read the code, the [accompanying notebook](https://github.com/qdrant/examples/blob/master/multi-representation-search/multi-representation-search.ipynb) walks through this pipeline step by step with eval numbers at each stage.
If you'd rather read the code, the [accompanying notebook](https://githubtocolab.com/qdrant/examples/blob/master/multi-representation-search/multi-representation-search.ipynb) walks through this pipeline step by step with eval numbers at each stage.
## Setup
@@ -243,7 +243,7 @@ Use a reranker when the preference is "this is more relevant than that" but you
---
For the step-by-step build-up that produced this design (dense baseline, plus sparse, plus title prefetch, plus grouping, plus boosting) with eval numbers showing the lift at each step, see the [accompanying notebook](https://github.com/qdrant/examples/blob/master/multi-representation-search/multi-representation-search.ipynb). For a complementary view that varies the *query* across three representations against a single document representation, see the [Universal Query for Hybrid Retrieval demo](/course/essentials/day-5/universal-query-demo/).
For the step-by-step build-up that produced this design (dense baseline, plus sparse, plus title prefetch, plus grouping, plus boosting) with eval numbers showing the lift at each step, see the [accompanying notebook](https://githubtocolab.com/qdrant/examples/blob/master/multi-representation-search/multi-representation-search.ipynb). For a complementary view that varies the *query* across three representations against a single document representation, see the [Universal Query for Hybrid Retrieval demo](/course/essentials/day-5/universal-query-demo/).
## Wrapping Up