mirror of
https://github.com/lancedb/lancedb.git
synced 2026-01-03 10:22:56 +00:00
Merge pull request #65 from lancedb/jaichopra/add-youtube-transcript-example
This commit is contained in:
@@ -14,7 +14,7 @@ We'll also use a container to ship our Lambda code. This is a good option for La
|
||||
|
||||
# Initial setup: creating a LanceDB Table and storing it remotely on S3
|
||||
|
||||
We'll use the SIFT vector dataset as an example. To make it easier, we've already made a Lance-format SIFT dataset publically available, which we can access and use to populate our LanceDB Table.
|
||||
We'll use the SIFT vector dataset as an example. To make it easier, we've already made a Lance-format SIFT dataset publicly available, which we can access and use to populate our LanceDB Table.
|
||||
|
||||
To do this, download the Lance files locally first from:
|
||||
|
||||
@@ -91,9 +91,9 @@ def handler(event, context):
|
||||
}
|
||||
```
|
||||
|
||||
# Deploying the container to EKS
|
||||
# Deploying the container to ECR
|
||||
|
||||
The next step is to build and push the container to EKS, where it can then be used to create a new Lambda function.
|
||||
The next step is to build and push the container to ECR, where it can then be used to create a new Lambda function.
|
||||
|
||||
It's best to follow the official AWS documentation for how to do this, which you can view here:
|
||||
|
||||
|
||||
7
docs/src/examples/youtube_transcript_search.md
Normal file
7
docs/src/examples/youtube_transcript_search.md
Normal file
@@ -0,0 +1,7 @@
|
||||
# YouTube transcript search
|
||||
|
||||
## Search through youtube transcripts using natural language with LanceDB
|
||||
|
||||
<img id="splash" width="400" alt="youtube transcript search" src="https://user-images.githubusercontent.com/917119/236965568-def7394d-171c-45f2-939d-8edfeaadd88c.png">
|
||||
|
||||
This example is in a [notebook](https://github.com/lancedb/lancedb/blob/main/notebooks/youtube_transcript_search.ipynb)
|
||||
Reference in New Issue
Block a user