rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2026-01-08 21:02:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: add lancedb embedding fcn on cloud docs (#1521)

Browse Source
This commit is contained in:
Ayush Chaurasia
2024-08-09 07:21:04 +05:30
committed by GitHub
parent 9c1adff426
commit a88e9bb134
2 changed files with 12 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/src/embeddings/embedding_functions.md
View File

@@ -2,8 +2,8 @@ Representing multi-modal data as vector embeddings is becoming a standard practi
For this purpose, LanceDB introduces an **embedding functions API**, that allow you simply set up once, during the configuration stage of your project. After this, the table remembers it, effectively making the embedding functions *disappear in the background* so you don't have to worry about manually passing callables, and instead, simply focus on the rest of your data engineering pipeline.
!!! Note "LanceDB cloud doesn't support embedding functions yet"
LanceDB Cloud does not support embedding functions yet. You need to generate embeddings before ingesting into the table or querying.
!!! Note "Embedding functions on LanceDB cloud"
When using embedding functions with LanceDB cloud, the embeddings will be generated on the source device and sent to the cloud. This means that the source device must have the necessary resources to generate the embeddings.
!!! warning
Using the embedding function registry means that you don't have to explicitly generate the embeddings yourself.

20
docs/src/embeddings/index.md
View File

@@ -99,28 +99,28 @@ LanceDB registers the Sentence Transformers embeddings function in the registry
Coming Soon!
### Jina Embeddings
LanceDB registers the JinaAI embeddings function in the registry as `jina`. You can pass any supported model name to the `create`. By default it uses `"jina-clip-v1"`.
`jina-clip-v1` can handle both text and images and other models only support `text`.
You need to pass `JINA_API_KEY` in the environment variable or pass it as `api_key` to `create` method.
### Embedding function with LanceDB cloud
Embedding functions are now supported on LanceDB cloud. The embeddings will be generated on the source device and sent to the cloud. This means that the source device must have the necessary resources to generate the embeddings. Here's an example using the OpenAI embedding function:
```python
import os
import lancedb
from lancedb.pydantic import LanceModel, Vector
from lancedb.embeddings import get_registry
os.environ['JINA_API_KEY'] = "jina_*"
os.environ['OPENAI_API_KEY'] = "..."
db = lancedb.connect("/tmp/db")
func = get_registry().get("jina").create(name="jina-clip-v1")
db = lancedb.connect(
uri="db://....",
api_key="sk_...",
region="us-east-1"
)
func = get_registry().get("openai").create()
class Words(LanceModel):
text: str = func.SourceField()
vector: Vector(func.ndims()) = func.VectorField()
table = db.create_table("words", schema=Words, mode="overwrite")
table = db.create_table("words", schema=Words)
table.add(
[
{"text": "hello world"},