krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-09-28 15:38:33 +02:00
Code Issues Packages Projects Releases Wiki Activity

upd links

Browse Source
This commit is contained in:
generall
2025-01-13 21:41:17 +01:00
parent a4e534d7a3
commit 78d832ef36
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/advanced-tutorials/pdf-retrieval-at-scale.md
+2 -2
View File
@@ -225,7 +225,7 @@ We choose to **preserve prefix and postfix multivectors**. Our **pooling** opera
Simplified version of pooling for **ColQwen** / **ColPali** models:
(see the full version in the [tutorial notebook](https://githubtocolab.com/qdrant/examples/blob/master/pdf-retrieval-at-scale/ColPali_ColQwen_Tutorial.ipynb))
(see the full version in the [tutorial notebook](https://githubtocolab.com/qdrant/examples/blob/master/pdf-retrieval-at-scale/ColPali_ColQwen2_Tutorial.ipynb))
```python
@@ -272,7 +272,7 @@ pooled_by_columns = torch.cat([pooled_by_columns, image_embedding[~mask]])
Upload process is trivial, the only thing to pay attention to is the compute cost for ColPali and ColQwen2 models.
In low-resource environments, it's recommended to use a smaller batch size for embedding and mean pooling.
Full version of the upload code is available in the [tutorial notebook](https://githubtocolab.com/qdrant/examples/blob/master/pdf-retrieval-at-scale/ColPali_ColQwen_Tutorial.ipynb)
Full version of the upload code is available in the [tutorial notebook](https://githubtocolab.com/qdrant/examples/blob/master/pdf-retrieval-at-scale/ColPali_ColQwen2_Tutorial.ipynb)
## Querying PDFs