Skip to content

Commit 3f452b1

Browse files
Gerome-Elassaadmintlify[bot]
Gerome-Elassaad
and
mintlify[bot]
authored
Update providers/aws-bedrock.mdx
Co-Authored-By: mintlify[bot] <109931778+mintlify[bot]@users.noreply.github.com>
1 parent 0f82880 commit 3f452b1

1 file changed

Lines changed: 57 additions & 114 deletions

File tree

‎providers/aws-bedrock.mdx‎

Lines changed: 57 additions & 114 deletions
Original file line numberDiff line numberDiff line change
@@ -1,136 +1,79 @@
11
---
22
title: "AWS Bedrock"
33
sidebarTitle: "API Key"
4-
description: "Set up AWS Bedrock with CodinIT using Bedrock API Keys. Simplest setup for individual developers to access frontier models."
4+
description: "Set up AWS Bedrock with CodinIT using API Keys to access frontier models like Claude and Amazon Nova."
55
---
66

7-
### Overview
7+
Access leading AI models through AWS Bedrock with simplified API Key setup.
88

9-
- **AWS Bedrock:** A fully managed service that offers access to leading generative AI models (e.g., Anthropic Claude, Amazon Nova) through AWS.\
10-
[Learn more about AWS Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html).
11-
- **CodinIT:** A VS Code extension that acts as a coding assistant by integrating with AI models—empowering developers to generate code, debug, and analyze data.
12-
- **Developer Focus:** This guide is tailored for individual developers that want to enable access to frontier models via AWS Bedrock with a simplified setup using API Keys.
9+
**Website:** [https://docs.aws.amazon.com/bedrock/](https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html)
1310

14-
---
15-
16-
### Step 1: Prepare Your AWS Environment
17-
18-
#### 1.1 Individual user setup - Create a Bedrock API Key
11+
## Setup Steps
1912

20-
For more detailed instructions check the [documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/api-keys.html).
13+
### 1. Create Bedrock API Key
2114

22-
1. **Sign in to the AWS Management Console:**\
23-
[AWS Console](https://aws.amazon.com/console)
24-
2. **Access Bedrock Console:**
25-
- [Bedrock Console](https://console.aws.amazon.com/bedrock)
26-
- Create a new Long Lived API Key. This API Key will have by default the `AmazonBedrockLimitedAccess` IAM policy
27-
[View AmazonBedrockLimitedAccess Policy Details](https://docs.aws.amazon.com/bedrock/latest/userguide/security-iam.html#managed-policies)
15+
1. **Sign in:** [AWS Console](https://aws.amazon.com/console)
16+
2. **Access Bedrock:** Go to [Bedrock Console](https://console.aws.amazon.com/bedrock)
17+
3. **Create API Key:** Create a new Long Lived API Key
18+
- Default policy: `AmazonBedrockLimitedAccess`
19+
- [View policy details](https://docs.aws.amazon.com/bedrock/latest/userguide/security-iam.html#managed-policies)
2820

29-
#### 1.2 Create or Modify the Policy
21+
### 2. Configure IAM Permissions
3022

31-
To ensure CodinIT can interact with AWS Bedrock, your IAM user or role needs specific permissions. While the `AmazonBedrockLimitedAccess` managed policy provides comprehensive access, for a more restricted and secure setup adhering to the principle of least privilege, the following minimal permissions are sufficient for CodinIT's core model invocation functionality:
23+
**Minimal permissions required:**
24+
```json
25+
{
26+
"Version": "2012-10-17",
27+
"Statement": [{
28+
"Effect": "Allow",
29+
"Action": [
30+
"bedrock:InvokeModel",
31+
"bedrock:InvokeModelWithResponseStream",
32+
"bedrock:CallWithBearerToken"
33+
],
34+
"Resource": "*"
35+
}]
36+
}
37+
```
3238

33-
- `bedrock:InvokeModel`
34-
- `bedrock:InvokeModelWithResponseStream`
35-
- `bedrock:CallWithBearerToken`
39+
Create custom policy and attach to IAM user associated with your API key.
3640

37-
You can create a custom IAM policy with these permissions and attach it to your IAM user or role.
41+
**Important:**
42+
- For model listing in CodinIT, add `bedrock:ListFoundationModels` permission
43+
- For AWS Marketplace models (e.g., Anthropic Claude), use `AmazonBedrockLimitedAccess` policy
44+
- For Anthropic models, submit First Time Use (FTU) form via [Playground](https://console.aws.amazon.com/bedrock/home#/text-generation-playground)
3845

39-
1. In the AWS IAM console, create a new policy.
40-
2. Use the JSON editor to add the following policy document:
41-
```json
42-
{
43-
"Version": "2012-10-17",
44-
"Statement": [
45-
{
46-
"Effect": "Allow",
47-
"Action": ["bedrock:InvokeModel", "bedrock:InvokeModelWithResponseStream", "bedrock:CallWithBearerToken"],
48-
"Resource": "*" // For enhanced security, scope this to specific model ARNs if possible.
49-
}
50-
]
51-
}
52-
```
53-
3. Name the policy (e.g., `CodinITBedrockInvokeAccess`) and attach it to the IAM user associated with the key you created. The IAM user and the API key have the same prefix.
46+
### 3. Choose Region
5447

55-
**Important Considerations:**
56-
57-
- **Model Listing in CodinIT:** The minimal permissions (`bedrock:InvokeModel`, `bedrock:InvokeModelWithResponseStream`) are sufficient for CodinIT to _use_ a model if you specify the model ID directly in CodinIT's settings. If you rely on CodinIT to dynamically list available Bedrock models, you might need additional permissions like `bedrock:ListFoundationModels`.
58-
- **AWS Marketplace Subscriptions:** For third-party models (e.g., Anthropic Claude), the **`AmazonBedrockLimitedAccess`** policy grants you the necessary permissions to subscribe via the AWS Marketplace. There is no explicit access to be enabled. For Anthropic models you are still required to submit a First Time Use (FTU) form via the Console. If you get the following message in the CodinIT chat `[ERROR] Failed to process response: Model use case details have not been submitted for this account. Fill out the Anthropic use case details form before using the model.` then open the [Playground in the AWS Bedrock Console](https://console.aws.amazon.com/bedrock/home?#/text-generation-playground), select any Anthropic model and fill in the form (you might need to send a prompt first)
59-
60-
---
61-
62-
### Step 2: Verify Regional and Model Access
63-
64-
#### 2.1 Choose and Confirm a Region
65-
66-
1. **Select a Region:**\
67-
AWS Bedrock is available in multiple regions (e.g., US East, Europe, Asia Pacific). Choose the region that meets your latency and compliance needs.\
68-
[AWS Global Infrastructure](https://aws.amazon.com/about-aws/global-infrastructure/regions_az/)
69-
2. **Verify Model Access:**
70-
- **Note:** Some models are only accessible via an [Inference Profile](https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html). In such case check the box "Cross Region Inference".
71-
72-
---
48+
Select region for latency/compliance needs:
49+
- `us-east-1` (N. Virginia)
50+
- `us-west-2` (Oregon)
51+
- `eu-west-1` (Ireland)
52+
- `ap-southeast-1` (Singapore)
7353

74-
### Step 3: Configure the CodinIT VS Code Extension
54+
**Note:** Some models require [Inference Profile](https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html) - check "Cross Region Inference" box if needed.
7555

76-
#### 3.1 Install and Open CodinIT
56+
### 4. Configure CodinIT
7757

78-
1. **Install VS Code:**\
79-
Download from the [VS Code website](https://code.visualstudio.com).
80-
2. **Install the CodinIT Extension:**
81-
- Open VS Code.
82-
- Go to the Extensions Marketplace (`Ctrl+Shift+X` or `Cmd+Shift+X`).
83-
- Search for **CodinIT** and install it.
58+
1. Install CodinIT extension in VS Code
59+
2. Click settings icon (⚙️)
60+
3. Select **AWS Bedrock** as API Provider
61+
4. Enter your **API Key**
62+
5. Specify **AWS Region** (e.g., `us-east-1`)
63+
6. Select **Model** (e.g., `anthropic.claude-3-5-sonnet-20241022-v2:0`)
64+
7. Save and test
8465

85-
#### 3.2 Configure CodinIT Settings
66+
## Security Best Practices
8667

87-
1. **Open CodinIT Settings:**
88-
- Click on the settings ⚙️ to select your API Provider.
89-
2. **Select AWS Bedrock as the API Provider:**
90-
- From the API Provider dropdown, choose **AWS Bedrock**.
91-
3. **Enter Your AWS API Key:**
92-
- Input your **API Key**
93-
- Specify the correct **AWS Region** (e.g., `us-east-1` or your enterprise-approved region).
94-
4. **Select a Model:**
95-
- Choose an on-demand model (e.g., **anthropic.claude-3-5-sonnet-20241022-v2:0**).
96-
5. **Save and Test:**
97-
- Click **Done/Save** to apply your settings.
98-
- Test the integration by sending a simple prompt (e.g., "Generate a Python function to check if a number is prime.").
68+
1. **Secure access:** Prefer AWS SSO/federated roles over long-lived API keys when possible
69+
2. **Network security:** Consider [AWS PrivateLink](https://docs.aws.amazon.com/vpc/latest/userguide/endpoint-services-overview.html)
70+
3. **Monitoring:** Enable CloudTrail for API logging and CloudWatch for metrics
71+
4. **Cost management:** Use AWS Cost Explorer and set billing alerts
72+
5. **Regular audits:** Review IAM roles and CloudTrail logs periodically
9973

100-
---
101-
102-
### Step 4: Security, Monitoring, and Best Practices
103-
104-
1. **Secure Access:**
105-
- Prefer AWS SSO/federated roles over long-lived API Key when possible.
106-
- [AWS IAM Best Practices](https://docs.aws.amazon.com/IAM/latest/UserGuide/best-practices.html)
107-
2. **Enhance Network Security:**
108-
- Consider setting up [AWS PrivateLink](https://docs.aws.amazon.com/vpc/latest/userguide/endpoint-services-overview.html) to securely connect to Bedrock.
109-
3. **Monitor and Log Activity:**
110-
- Enable AWS CloudTrail to log Bedrock API calls.
111-
- Use CloudWatch to monitor metrics like invocation count, latency, and token usage.
112-
- Set up alerts for abnormal activity.
113-
4. **Handle Errors and Manage Costs:**
114-
- Implement exponential backoff for throttling errors.
115-
- Use AWS Cost Explorer and set billing alerts to track usage.\
116-
[AWS Cost Management](https://docs.aws.amazon.com/cost-management/latest/userguide/what-is-aws-cost-management.html)
117-
5. **Regular Audits and Compliance:**
118-
- Periodically review IAM roles and CloudTrail logs.
119-
- Follow internal data privacy and governance policies.
120-
121-
---
122-
123-
### Conclusion
124-
125-
By following these steps, you can quickly integrate AWS Bedrock with the CodinIT VS Code extension to accelerate development:
126-
127-
1. **Prepare Your AWS Environment:** Create a Bedrock API Key with the necessary permissions.
128-
2. **Verify Region and Model Access:** Confirm that your selected region supports your required models.
129-
3. **Configure CodinIT in VS Code:** Install and set up CodinIT with your AWS API Key and choose an appropriate model.
130-
4. **Implement Security and Monitoring:** Use best practices for IAM, network security, monitoring, and cost management.
131-
132-
For further details, consult the [AWS Bedrock Documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html). Happy coding!
133-
134-
---
74+
## Notes
13575

136-
_This guide will be updated as AWS Bedrock and CodinIT evolve. Always refer to the latest documentation and internal policies for up-to-date practices._
76+
- **Pricing:** Usage-based, see [AWS Bedrock Pricing](https://aws.amazon.com/bedrock/pricing/)
77+
- **Compliance:** HIPAA and SOC 2 Type II compliant
78+
- **Documentation:** [AWS Bedrock User Guide](https://docs.aws.amazon.com/bedrock/latest/userguide/what-is-bedrock.html)
79+
- **IAM Best Practices:** [AWS IAM Best Practices](https://docs.aws.amazon.com/IAM/latest/UserGuide/best-practices.html)

0 commit comments

Comments
 (0)