Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add notebook for integration of BentoML and Milvus to implement RAG #1290

Closed
wants to merge 0 commits into from

Conversation

Jacksonxhx
Copy link

@Jacksonxhx Jacksonxhx commented Apr 22, 2024

  • A reference to a related issue in your repository.

    Each PR is related to an issue, and you need to list that issue.

  • A description of the changes proposed in the pull request.

    A brief introduction to this PR.

  • Add delight to the experience when all tasks are complete 馃帀

@sre-ci-robot
Copy link

Welcome @Jacksonxhx! It looks like this is your first PR to milvus-io/bootcamp 馃帀

@jaelgu
Copy link
Contributor

jaelgu commented Apr 22, 2024

Review via ReviewNB: https://app.reviewnb.com/milvus-io/bootcamp/pull/1290/

Copy link

Check out this pull request on聽 ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

@@ -0,0 +1,588 @@
{
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Since this is a demo about Zilliz Cloud + BentoCloud. Let's replace all usage of Milvus to Zilliz Cloud (except for function names such as MilvusClient()).

E.g.,

In this demo, we show how to use open-source embedding model and LLM on BentoCloud with vector database on Zilliz Cloud to build a RAG application.

BentoCloud offers serverless infrastructure tailored for model inference, operating in conjunction with BentoML, an open-source model serving framework, to facilitate the easy creation and deployment of high-performance model services. Zilliz Cloud is fully-managed service for open-source vector database - Milvus, with flexible pricing and ease of management. You can sign-up for free on BentoCloud and Zilliz Cloud. Later we will use the API keys from both services to finish the demo.

On BentoCloud, you can setup model services in Deployments, and the corresponding END_POINT and API are located in Playground -> Python. On Zilliz Cloud, we can get endpoint and token in Cluster Details.

After we get API credentials from both platform and the corresponding endpoint, we can start to do RAG!


Reply via ReviewNB

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No problem, fixed

@@ -0,0 +1,588 @@
{
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Line #2.    COLLECTION_NAME = "bmo_test"

what is bmo?


Reply via ReviewNB

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I fix it to "Bento_Zilliz_RAG"

@@ -0,0 +1,588 @@
{
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Line #4.    # add index

use AUTO INDEX instead?


Reply via ReviewNB

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No problem

@@ -0,0 +1,588 @@
{
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Line #5.                                token=YOUR_API_TOKEN)

indent


Reply via ReviewNB

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

fixed

@@ -0,0 +1,588 @@
{
Copy link
Contributor

@jaelgu jaelgu Apr 22, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Line #9.               for embedding in embedding_split:
  1. make sure embedding_split is a list of embeddings
  2. replace line 9 & 10 with embeddings += embedding_split

Reply via ReviewNB

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

fixed

@sre-ci-robot
Copy link

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: Jacksonxhx

The full list of commands accepted by this bot can be found here.

Needs approval from an approver in each of these files:

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

4 participants