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.

Sign up for GitHub

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

Jump to bottom

Add bedrock multimodal build-in function usage example in doc #3073

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+36 −4
Open

Add bedrock multimodal build-in function usage example in doc #3073

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
40 changes: 36 additions & 4 deletions ..._inference_blueprints/bedrock_connector_titan_multimodal_embedding_blueprint.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,8 +17,9 @@ PUT /_cluster/settings

## 2. Create connector for Amazon Bedrock:

If you are using self-managed Opensearch, you should supply AWS credentials:

If you are using self-managed Opensearch, you should supply AWS credentials.
You have two different approaches to specify the pre&post process function and request body in the API:
**Use build-in function**
```json
POST /_plugins/_ml/connectors/_create
{
Expand Down Expand Up @@ -46,6 +47,21 @@ POST /_plugins/_ml/connectors/_create
"content-type": "application/json",
"x-amz-content-sha256": "required"
},
"request_body": "{\"body\":{\"inputText\": \"${parameters.inputText}\", \"inputImage\": \"${parameters.inputImage}\"}}",
"pre_process_function": "connector.pre_process.bedrock.multimodal_embedding",
Copy link
Collaborator

Choose a reason for hiding this comment

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

Explain from which version user can use this ?

"post_process_function": "connector.post_process.bedrock.embedding"
}
]
}
```
**Use painless script**
```json
POST /_plugins/_ml/connectors/_create
{
... //same above
"actions": [
{
... // same above
"request_body": "{ \"inputText\": \"${parameters.inputText:-null}\", \"inputImage\": \"${parameters.inputImage:-null}\" }",
"pre_process_function": "\n StringBuilder parametersBuilder = new StringBuilder(\"{\");\n if (params.text_docs.length > 0 && params.text_docs[0] != null) {\n parametersBuilder.append(\"\\\"inputText\\\":\");\n parametersBuilder.append(\"\\\"\");\n parametersBuilder.append(params.text_docs[0]);\n parametersBuilder.append(\"\\\"\");\n \n if (params.text_docs.length > 1 && params.text_docs[1] != null) {\n parametersBuilder.append(\",\");\n }\n }\n \n \n if (params.text_docs.length > 1 && params.text_docs[1] != null) {\n parametersBuilder.append(\"\\\"inputImage\\\":\");\n parametersBuilder.append(\"\\\"\");\n parametersBuilder.append(params.text_docs[1]);\n parametersBuilder.append(\"\\\"\");\n }\n parametersBuilder.append(\"}\");\n \n return \"{\" +\"\\\"parameters\\\":\" + parametersBuilder + \"}\";",
"post_process_function": "\n def name = \"sentence_embedding\";\n def dataType = \"FLOAT32\";\n if (params.embedding == null || params.embedding.length == 0) {\n return null;\n }\n def shape = [params.embedding.length];\n def json = \"{\" +\n \"\\\"name\\\":\\\"\" + name + \"\\\",\" +\n \"\\\"data_type\\\":\\\"\" + dataType + \"\\\",\" +\n \"\\\"shape\\\":\" + shape + \",\" +\n \"\\\"data\\\":\" + params.embedding +\n \"}\";\n return json;\n "
Expand All @@ -55,8 +71,9 @@ POST /_plugins/_ml/connectors/_create
```

If using the AWS Opensearch Service, you can provide an IAM role arn that allows access to the bedrock service.
Refer to this [AWS doc](https://docs.aws.amazon.com/opensearch-service/latest/developerguide/ml-amazon-connector.html)

Refer to this [AWS doc](https://docs.aws.amazon.com/opensearch-service/latest/developerguide/ml-amazon-connector.html)
You have two different approaches to specify the pre&post process function and request body in the API:
**Use build-in function**
```json
POST /_plugins/_ml/connectors/_create
{
Expand All @@ -82,6 +99,21 @@ POST /_plugins/_ml/connectors/_create
"content-type": "application/json",
"x-amz-content-sha256": "required"
},
"request_body": "{\"body\":{\"inputText\": \"${parameters.inputText}\", \"inputImage\": \"${parameters.inputImage}\"}}",
"pre_process_function": "connector.pre_process.bedrock.multimodal_embedding",
"post_process_function": "connector.post_process.bedrock.embedding"
}
]
}
```
**Use painless script**
```json
POST /_plugins/_ml/connectors/_create
{
... //same above
"actions": [
{
... //same above
"request_body": "{ \"inputText\": \"${parameters.inputText:-null}\", \"inputImage\": \"${parameters.inputImage:-null}\" }",
"pre_process_function": "\n StringBuilder parametersBuilder = new StringBuilder(\"{\");\n if (params.text_docs.length > 0 && params.text_docs[0] != null) {\n parametersBuilder.append(\"\\\"inputText\\\":\");\n parametersBuilder.append(\"\\\"\");\n parametersBuilder.append(params.text_docs[0]);\n parametersBuilder.append(\"\\\"\");\n \n if (params.text_docs.length > 1 && params.text_docs[1] != null) {\n parametersBuilder.append(\",\");\n }\n }\n \n \n if (params.text_docs.length > 1 && params.text_docs[1] != null) {\n parametersBuilder.append(\"\\\"inputImage\\\":\");\n parametersBuilder.append(\"\\\"\");\n parametersBuilder.append(params.text_docs[1]);\n parametersBuilder.append(\"\\\"\");\n }\n parametersBuilder.append(\"}\");\n \n return \"{\" +\"\\\"parameters\\\":\" + parametersBuilder + \"}\";",
"post_process_function": "\n def name = \"sentence_embedding\";\n def dataType = \"FLOAT32\";\n if (params.embedding == null || params.embedding.length == 0) {\n return null;\n }\n def shape = [params.embedding.length];\n def json = \"{\" +\n \"\\\"name\\\":\\\"\" + name + \"\\\",\" +\n \"\\\"data_type\\\":\\\"\" + dataType + \"\\\",\" +\n \"\\\"shape\\\":\" + shape + \",\" +\n \"\\\"data\\\":\" + params.embedding +\n \"}\";\n return json;\n "
Expand Down
Loading