krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-09-29 07:58:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs: add late chunking parameter

Browse Source
This commit is contained in:
Wang Bo
2024-09-18 13:21:19 +02:00
committed by GitHub
parent 81067d7bde
commit eb8383208c
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/documentation/embeddings/jina-embeddings.md
+2
View File
@@ -42,6 +42,7 @@ You can reference the table below for hints on dimension vs. performance:
|:----------------------:|:---------:|:---------:|:-----------:|:---------:|:----------:|:---------:|:---------:| |:----------------------:|:---------:|:---------:|:-----------:|:---------:|:----------:|:---------:|:---------:|
| Average Retrieval Performance (nDCG@10) | 52.54 | 58.54 | 61.64 | 62.72 | 63.16 | 63.3 | 63.35 | | Average Retrieval Performance (nDCG@10) | 52.54 | 58.54 | 61.64 | 62.72 | 63.16 | 63.3 | 63.35 |
`jina-embeddings-v3` supports [Late Chunking](https://jina.ai/news/late-chunking-in-long-context-embedding-models/), the technique to leverage the model's long-context capabilities for generating contextual chunk embeddings. Include `late_chunking=True` in your request to enable contextual chunked representation. When set to true, Jina AI API will concatenate all sentences in the input field and feed them as a single string to the model. Internally, the model embeds this long concatenated string and then performs late chunking, returning a list of embeddings that matches the size of the input list.
## Example ## Example
@@ -73,6 +74,7 @@ data = {
"model": MODEL, "model": MODEL,
"dimensions": DIMENSIONS, "dimensions": DIMENSIONS,
"task": TASK, "task": TASK,
"late_chunking": True,
} }
response = requests.post(url, headers=headers, json=data) response = requests.post(url, headers=headers, json=data)