Operations (sample payloads)

Main operations
Copy

AI Generation (Run Inference)
Copy

Use a wide range of Frontier and Open Source GenerativeAI models, backed by the security and privacy of AWS.

Sample Input

1
{
2
"modelId": "anthropic.claude-v2",
3
"messages": [
4
{
5
"system_content": "You are a helpful AI assistant."
6
},
7
{
8
"user_content": "What are the main differences between Python and JavaScript?"
9
}
10
],
11
"maxGenLen": 500,
12
"temperature": 0.2,
13
"topP": 1
14
}

Sample Output

1
{
2
"chatResponse": {
3
"output": {
4
"message": {
5
"role": "assistant",
6
"content": [
7
{
8
"text": "Here are the main differences between Python and JavaScript:\n\n1. Language type:\n - Python is a general-purpose programming language\n - JavaScript was originally designed for web development, but can now be used for various purposes\n\n2. Execution environment:\n - Python runs on a Python interpreter\n - JavaScript primarily runs in web browsers, but can also run on servers using Node.js\n\n3. Syntax:\n - Python uses indentation for code blocks\n - JavaScript uses curly braces {} for code blocks\n\n4. Data types:\n - Python has more built-in data types (e.g., tuples, sets)\n - JavaScript has fewer primitive data types\n\n5. Object-oriented programming:\n - Python uses class-based OOP\n - JavaScript uses prototype-based OOP\n\n6. Typing:\n - Python is dynamically typed but supports type hinting\n - JavaScript is dynamically typed\n\n7. Concurrency:\n - Python has built-in support for multi-threading and multiprocessing\n - JavaScript is single-threaded but uses an event loop for asynchronous operations\n\n8. Standard library:\n - Python has a large standard library\n - JavaScript has a smaller standard library but extensive third-party packages\n\nBoth languages have their strengths and are widely used in different domains."
9
}
10
]
11
}
12
},
13
"stopReason": "end_turn",
14
"usage": {
15
"inputTokens": 24,
16
"outputTokens": 237,
17
"totalTokens": 261
18
},
19
"metrics": {
20
"latencyMs": 2150
21
}
22
}
23
}

Create Embeddings
Copy

Turn content into vector embeddings so you can store it in a Vector database as part of your RAG pipelines (and more).

Sample Input

1
{
2
"modelGroup": {
3
"titanModelId": "amazon.titan-embed-text-v1",
4
"inputText": "Artificial intelligence is transforming various industries, from healthcare to finance.",
5
"normalize": true,
6
"dimensions": 1024
7
}
8
}

Sample Output

1
{
2
"modelResponse": "[0.023, -0.015, 0.067, ..., 0.041]"
3
}

List Models
Copy

List all possible models offered by AWS Bedrock currently.

Sample Input

1
{
2
"outputModality": "TEXT",
3
"modelNameFilter": "anthropic"
4
}

Sample Output

1
{
2
"models": [
3
{
4
"modelArn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-v2",
5
"modelId": "anthropic.claude-v2",
6
"modelName": "Claude V2",
7
"providerName": "Anthropic",
8
"inputModalities": [
9
"TEXT"
10
],
11
"outputModalities": [
12
"TEXT"
13
],
14
"responseStreamingSupported": true,
15
"customizationsSupported": [],
16
"inferenceTypesSupported": [
17
"ON_DEMAND"
18
],
19
"modelLifecycle": {
20
"status": "ACTIVE"
21
}
22
},
23
{
24
"modelArn": "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-instant-v1",
25
"modelId": "anthropic.claude-instant-v1",
26
"modelName": "Claude Instant V1",
27
"providerName": "Anthropic",
28
"inputModalities": [
29
"TEXT"
30
],
31
"outputModalities": [
32
"TEXT"
33
],
34
"responseStreamingSupported": true,
35
"customizationsSupported": [],
36
"inferenceTypesSupported": [
37
"ON_DEMAND"
38
],
39
"modelLifecycle": {
40
"status": "ACTIVE"
41
}
42
}
43
]
44
}

Raw HTTP request (advanced)
Copy

Perform a raw HTTP request with some pre-configuration and processing by the connector, such as authentication.

Sample Input

1
{
2
"method": "POST",
3
"url": {
4
"fullUrl": "https://api.aws.amazon.com/bedrock/2023-04-20/models/anthropic.claude-v2/invoke"
5
},
6
"headers": {
7
"Content-Type": "application/json",
8
"X-Amz-Content-Sha256": "UNSIGNED-PAYLOAD",
9
"X-Amz-Date": "20230915T120000Z"
10
},
11
"body": {
12
"raw": {
13
"prompt": "Human: What is the capital of France?\n\nAssistant: The capital of France is Paris.",
14
"max_tokens_to_sample": 300,
15
"temperature": 0.7,
16
"top_p": 1
17
}
18
}
19
}

Sample Output

1
{
2
"status": 200,
3
"headers": {
4
"Content-Type": "application/json",
5
"Date": "Fri, 15 Sep 2023 12:00:01 GMT",
6
"x-amzn-RequestId": "1234a567-b89c-12d3-e456-789012f34567"
7
},
8
"body": {
9
"completion": "The capital of France is indeed Paris. Paris is not only the capital city but also the largest city in France. It is a global center for art, fashion, gastronomy, and culture. Some of its famous landmarks include the Eiffel Tower, the Louvre Museum, and Notre-Dame Cathedral.",
10
"stop_reason": "stop_sequence",
11
"stop": "\n\nHuman:"
12
}
13
}

DDL operations
Copy

ListModels(DDL)
Copy

Note that DDL operations can only be called directly by Connectors API, or when using CustomJS in the Embedded solution editor for e.g. DDL-dependent data mapping

Sample Input

1
{
2
"outputModality": "TEXT",
3
"modelNameFilter": "ai21"
4
}

Sample Output

1
{
2
"result": [
3
{
4
"value": "ai21.j2-ultra-v1",
5
"text": "AI21 Labs Jurassic-2 Ultra"
6
},
7
{
8
"value": "ai21.j2-mid-v1",
9
"text": "AI21 Labs Jurassic-2 Mid"
10
},
11
{
12
"value": "ai21.j2-large-v1",
13
"text": "AI21 Labs Jurassic-2 Large"
14
}
15
]
16
}