github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-03 03:59:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

community[patch]: Upstash Vector Store Namespace Support (#22251)

Browse Source 
This PR introduces namespace support for Upstash Vector Store, which
would allow users to partition their data in the vector index.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
This commit is contained in:
Fahreddin Özcan
2024-06-04 02:30:56 +02:00
committed by GitHub
parent 25cf1a74d5
commit 0061ded002
2 changed files with 154 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
docs/docs/integrations/providers/upstash.mdx
View File

@@ -61,6 +61,22 @@ store = UpstashVectorStore(
See [Upstash Vector documentation](https://upstash.com/docs/vector/features/embeddingmodels)
for more detail on embedding models.
## Namespaces
You can use namespaces to partition your data in the index. Namespaces are useful when you want to query over huge amount of data, and you want to partition the data to make the queries faster. When you use namespaces, there won't be post-filtering on the results which will make the query results more precise.
```python
from langchain_community.vectorstores.upstash import UpstashVectorStore
import os
os.environ["UPSTASH_VECTOR_REST_URL"] = "<UPSTASH_VECTOR_REST_URL>"
os.environ["UPSTASH_VECTOR_REST_TOKEN"] = "<UPSTASH_VECTOR_REST_TOKEN>"
store = UpstashVectorStore(
embedding=embeddings
namespace="my_namespace"
)
```
### Inserting Vectors
```python