Adding configuring chunking settings notebook for blog #417
Conversation
|
Found 1 changed notebook. Review the changes at https://app.gitnotebooks.com/elastic/elasticsearch-labs/pull/417 |
| "# Install packages and connect with Elasticsearch Client\n", | ||
| "\n", | ||
| "To get started, we'll need to connect to our Elastic deployment using the Python client (version 8.12.0 or above).\n", | ||
| "Because we're using an Elastic Cloud deployment, we'll use the **Cloud ID** to identify our deployment.\n", |
There was a problem hiding this comment.
Maybe change to "Because we're using an Elastic Serverless deployment, we'll use the Serverless Endpoint to identify our deployment."?
So that it matches the below code hosts=[ELASTIC_SERVERLESS_ENDPOINT]
There was a problem hiding this comment.
Meant to update this section when I switched to serverless endpoint. I'll update this.
There was a problem hiding this comment.
Spoke with @joseph.mcelroy and was asked to switch to using cloud ID instead of serverless endpoint. I'll update all of the endpoint information to be related to cloud ID.
notebooks/document-chunking/configuring-chunking-settings-for-inference-endpoints.ipynb
Outdated
Show resolved
Hide resolved
notebooks/document-chunking/configuring-chunking-settings-for-inference-endpoints.ipynb
Show resolved
Hide resolved
| "[](https://colab.research.google.com/github/elastic/elasticsearch-labs/blob/main/notebooks/document-chunking/configuring-chunking-settings-for-inference-endpoints.ipynb)\n", | ||
| "\n", | ||
| "\n", | ||
| "Learn how to configure [chunking settings](https://www.elastic.co/guide/en/elasticsearch/reference/current/inference-apis.html#infer-chunking-config) for [Inference API](https://www.elastic.co/guide/en/elasticsearch/reference/current/inference-apis.html) endpoints." |
There was a problem hiding this comment.
Do we want to move and summarize some of the content of this wiki into an overview section to explain why users want to change chunking strategies, sizes, and overlap? Or does that not make a lot of sense since it'll distract from the overall goal of teaching people how to call the API with the new fields?
There was a problem hiding this comment.
Since this notebook will be linked from the chunking blog which explains the motivation behind various chunking setting options, I think we can leave this as is to avoid duplicating the information too many times. We could consider adding in a link to the blog once it is posted but this will have to be a follow-up change.
Adding a notebook for the configuring chunking settings blog I'm currently writing. A draft of the blog can be seen here.
Note: I've run through the steps with local testing and with a serverless trial account and confirmed that the steps succeeded.