krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-09-28 07:28:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

* docs(fastembed.md): add information about context window limit and recommended pooling strategy for embedding larger sequences

Browse Source
This commit is contained in:
NirantK
2023-10-19 21:14:48 +05:30
parent db09209bd8
commit 3c6cdd1728
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/articles/fastembed.md
+2
View File
@@ -75,6 +75,8 @@ Next, we initialize the Embedding model with the default model: [BAAI/bge-small
embedding_model = DefaultEmbedding()
```
The default model and several other models have a context window of maximum 512 tokens. This maximum limit comes from the embedding model training and design itself.If you'd like to embed sequences larger than that, we'd recommend using some pooling strategy to get a single vector out of the sequence. For example, you can use the mean of the embeddings of different chunks of a document. This is also what the [SBERT Paper recommends](https://lilianweng.github.io/posts/2021-05-31-contrastive/#sentence-bert)
This model strikes a balance between speed and accuracy, ideal for real-world applications.
```python