-
Notifications
You must be signed in to change notification settings - Fork 280
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’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
additional tools for visualization and knowledge graph #228
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
left some comments
"## Query Neptune Graph with SPARQL in Natural Language Using Function Calling\n", | ||
"\n", | ||
"This notebook will walk you through the steps to create a tool that can query Amazon Neptune database via SPARQL using function calling in Bedrock Converse API. The tool will be invoked when a user wants to get object litereal information from Amazon Neptune database for a specific object id. LLM(Large Language Model) will pass the required input parameter from the user's question the function *get_objectLiteral* and the fucntion will execute the SPARQL query to fetch the results. At the end LLM(Large Language Model) will give the final response to the user including the query results.\n", | ||
"We will use the Human Disease Ontology as a dataset to load to Amazon Neptune https://www.ebi.ac.uk/ols4/ontologies/doid\n", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
is this a pre-approved dataset? have you gotten the ticket to use the dataset?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hi, it was opensource from this website: https://www.ebi.ac.uk/ols4/ontologies/doid. For which department should I open the ticket to get it approved?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The dataset is public available under https://creativecommons.org/publicdomain/zero/1.0/ , we can add this to README and I believe no further approvals are required @berilunay
"## Prerequisites\n", | ||
"1.Please make sure that you complete all the prerequisites explained in this [link](https://docs.aws.amazon.com/neptune/latest/userguide/bulk-load-data.html)\n", | ||
"\n", | ||
"2.In the security group of Neptune Database, allow TCP connections from the port 8182(default port of the instance) through the subnet CIDR range where the database instance resides.\n", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
instructions to get this?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
for which row 30?
"4.After the notebook is being created you can see it in the sagemaker console, under notebooks. The default IAM role of the notebook instance, by default, has list and read permissions for S3 in the policy. Edit the policy and add \"s3:PutObject\" in the actions and add your S3 bucket ARN in the Resources section of the IAM policy. In order to access Amazon Bedrock, attach *AmazonBedrockFullAccess* policy to the same role.\n", | ||
"\n", | ||
"After you complete all the steps you should have\n", | ||
"* Amazon Neptune database instance (Follow [creating an new neptune DB cluster](https://docs.aws.amazon.com/neptune/latest/userguide/get-started-create-cluster.html) or create manually from the AWS Console). You need to set up the cluster within VPC!\n", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is it not possible to have those automated as a support file?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I can add a code for attaching adding those 2 policy via python if that works?
"cell_type": "markdown", | ||
"id": "042cbf05", | ||
"metadata": {}, | ||
"source": [ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
add the functions required to justify this
"id": "6476ae5f", | ||
"metadata": {}, | ||
"source": [ | ||
"### After you create your S3 bucket add a folder named 'data'. You will download the Human disease ontology data into that folder in the cell below" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
add step for creation of s3 bucket
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 17, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
clean up all cells execution
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "6dd21f12-6f89-4735-baab-9f53204615fa", | ||
"metadata": {}, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
add conclusions, expected outcomes and clean up steps
@@ -0,0 +1,76 @@ | |||
import boto3 | |||
|
|||
bucket = 'bucketname' ### REPLACE WITH YOUR AMAZON S3 BUCKET |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
create bucket automatically and get this name from the resource created
bucket = 'bucketname' ### REPLACE WITH YOUR AMAZON S3 BUCKET | ||
|
||
### Setup boto3 client for Athena | ||
athena = boto3.client('athena', region_name='us-east-1') |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
make region a variable
|
||
### Insert synthetic example data | ||
transactions_data = [ | ||
(1, 'Tom Hanks', '2023-01-01', 500.00), |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
is this data generated? do we have permissions to use it?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
3e0a2a7
Issue #, if available:
Description of changes:
2 additional tool examples
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.