Fix broken docs links noted in issue #609 ("Use case code examples" from "Building Generative AI Applications Using Amazon Bedrock" Amazon Skill Builder course)

articles-guides/README.md

@@ -4,18 +4,18 @@ This repository contains pre-built examples to help customers get started with t
 
 ## Contents
 
-- [Introduction to Bedrock](introduction-to-bedrock) - Learn the basics of the Bedrock service
+- [Introduction to Bedrock](../introduction-to-bedrock) - Learn the basics of the Bedrock service
 - [Prompt Engineering ](prompt-engineering) - Tips for crafting effective prompts 
-- [Bedrock Fine-tuning](bedrock-fine-tuning) - Fine-tune Bedrock models for your specific use case
-- [Custom Model Import](custom-models) - Import custom models into Bedrock
-- [Generative AI Solutions](generative-ai-solutions) - Example use cases for generative AI
-- [Knowledge Bases](knowledge-bases) - Build knowledge bases with Bedrock
-- [Retrival Augmented Generation (RAG)](rag-solutions) - Implementing RAG with Amazon Bedrock
-- [Agents](agents-for-bedrock) - Generative AI agents with Bedrock
-- [Security and Governance](security-and-governance) - Secure your Bedrock applications
-- [Responsible AI](responsible-ai) - Use Bedrock responsibly and ethically
-- [Operational Tooling](ops-tooling) - Helpful samples to help operationalize your useage of Amazon Bedrock
-- [Multimodal](multimodal) - Working with multimodal data using Amazon Bedrock
+- [Bedrock Fine-tuning](../custom-models/bedrock-fine-tuning) - Fine-tune Bedrock models for your specific use case
+- [Custom Model Import](../custom-models) - Import custom models into Bedrock
+- [Generative AI Solutions](../genai-use-cases) - Example use cases for generative AI
+- [Knowledge Bases](../rag/knowledge-bases) - Build knowledge bases with Bedrock
+- [Retrival Augmented Generation (RAG)](../rag) - Implementing RAG with Amazon Bedrock
+- [Agents](../agents-and-function-calling) - Generative AI agents with Bedrock
+- [Security and Governance](../security) - Secure your Bedrock applications
+- [Responsible AI](../responsible_ai) - Use Bedrock responsibly and ethically
+- [Operational Tooling](../evaluation-observe) - Helpful samples to help operationalize your useage of Amazon Bedrock
+- [Multimodal](../multi-modal) - Working with multimodal data using Amazon Bedrock
 
 ## Getting Started
 

docs/agents-and-function-calling/bedrock-agents/features-examples/09-create-agent-with-memory/09-create-agent-with-memory.md

@@ -515,10 +515,10 @@ If the `enable_trace` is set to `True`, each response from the agent is accompan
 To handle the memory capabilities the `memory_id` parameter is used. Once a session is ended, it will summarize the content into a new session id as part of the `memory_id`.
 
 Finally, you can also pass a session context using the `session_state` parameter. The session state allows you to share the following information with the agent:
-- **`sessionAttributes`**: attributes that persist over a session between the user and the agent. All invokeAgent calls with the same session_id belong to the same sesison and will have the sessionAttributes shared with them as long as the session time limit has not being surpassed and the user has not ended the session. The sessionAttributes are available in the lambda function but are **not** added to the agent's prompt. As a result, you can only use session attributes if your lambda function can handle them. You can find more examples of using a session attribute [here](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/agents-for-bedrock/features-examples/06-prompt-and-session-attributes). It is also a good pattern to implement fine-grained access control for certain APIs using the lambda function integration. You can find an example for it [here](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/agents-for-bedrock/features-examples/09-fine-grained-access-permissions)
+- **`sessionAttributes`**: attributes that persist over a session between the user and the agent. All invokeAgent calls with the same session_id belong to the same sesison and will have the sessionAttributes shared with them as long as the session time limit has not being surpassed and the user has not ended the session. The sessionAttributes are available in the lambda function but are **not** added to the agent's prompt. As a result, you can only use session attributes if your lambda function can handle them. You can find more examples of using a session attribute [here](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/agents-and-function-calling/bedrock-agents/features-examples/06-prompt-and-session-attributes). It is also a good pattern to implement fine-grained access control for certain APIs using the lambda function integration. You can find an example for it [here](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/agents-and-function-calling/bedrock-agents/use-case-examples/fine-grained-access-permissions-agent)
 - **`promptSessionAttributes`**: attributes that persist over a single invokeAgent call. Prompt attributes are added to the prompt and to the lambda function. You can also use the `$prompt_session_attributes$` placeholder when editing the orchestration base prompt.
-- **`invocationId`**: The id returned by the agent in the [ReturnControlPayload](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_agent-runtime_ReturnControlPayload.html) object in the returnControl field of the InvokeAgent response. This field is required if passing the answer of a Return of Control invocation. You can find an example of how to use it [here](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/agents-for-bedrock/features-examples/03-create-agent-with-return-of-control).
-- **`returnControlInvocationResults`**: the results obtained from invoking the action outside of Amazon Bedrock Agents.  This field is required if passing the answer of a Return of Control invocation. You can find an example of how to use it [here](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/agents-for-bedrock/features-examples/03-create-agent-with-return-of-control).
+- **`invocationId`**: The id returned by the agent in the [ReturnControlPayload](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_agent-runtime_ReturnControlPayload.html) object in the returnControl field of the InvokeAgent response. This field is required if passing the answer of a Return of Control invocation. You can find an example of how to use it [here](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/agents-and-function-calling/bedrock-agents/features-examples/03-create-agent-with-return-of-control).
+- **`returnControlInvocationResults`**: the results obtained from invoking the action outside of Amazon Bedrock Agents.  This field is required if passing the answer of a Return of Control invocation. You can find an example of how to use it [here](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/agents-and-function-calling/bedrock-agents/features-examples/03-create-agent-with-return-of-control).
 
 We will also use the test `agent_alias_id` set to `TSTALIASID`. This is a default value that you can use to test agents being developed. You can also [deploy your agent](https://docs.aws.amazon.com/bedrock/latest/userguide/agents-deploy.html) to create a new version of your agent and have a new agent alias id.
 

docs/agents-and-function-calling/bedrock-agents/features-examples/10-create-agent-with-code-interpreter/10-create-agent-with-code-interpreter.md

@@ -339,10 +339,10 @@ If the `enable_trace` is set to `True`, each response from the agent is accompan
 To handle the memory capabilities the `memory_id` parameter is used. Once a session is ended, it will summarize the content into a new session id as part of the `memory_id`.
 
 You can also pass a session context using the `session_state` parameter. The session state allows you to share the following information with the agent:
-- **`sessionAttributes`**: attributes that persist over a session between the user and the agent. All invokeAgent calls with the same session_id belong to the same sesison and will have the sessionAttributes shared with them as long as the session time limit has not being surpassed and the user has not ended the session. The sessionAttributes are available in the lambda function but are **not** added to the agent's prompt. As a result, you can only use session attributes if your lambda function can handle them. You can find more examples of using a session attribute [here](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/agents-for-bedrock/features-examples/06-prompt-and-session-attributes). It is also a good pattern to implement fine-grained access control for certain APIs using the lambda function integration. You can find an example for it [here](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/agents-for-bedrock/features-examples/09-fine-grained-access-permissions)
+- **`sessionAttributes`**: attributes that persist over a session between the user and the agent. All invokeAgent calls with the same session_id belong to the same sesison and will have the sessionAttributes shared with them as long as the session time limit has not being surpassed and the user has not ended the session. The sessionAttributes are available in the lambda function but are **not** added to the agent's prompt. As a result, you can only use session attributes if your lambda function can handle them. You can find more examples of using a session attribute [here](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/agents-and-function-calling/bedrock-agents/features-examples/06-prompt-and-session-attributes). It is also a good pattern to implement fine-grained access control for certain APIs using the lambda function integration. You can find an example for it [here](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/agents-and-function-calling/bedrock-agents/use-case-examples/fine-grained-access-permissions-agent)
 - **`promptSessionAttributes`**: attributes that persist over a single invokeAgent call. Prompt attributes are added to the prompt and to the lambda function. You can also use the `$prompt_session_attributes$` placeholder when editing the orchestration base prompt.
-- **`invocationId`**: The id returned by the agent in the [ReturnControlPayload](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_agent-runtime_ReturnControlPayload.html) object in the returnControl field of the InvokeAgent response. This field is required if passing the answer of a Return of Control invocation. You can find an example of how to use it [here](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/agents-for-bedrock/features-examples/03-create-agent-with-return-of-control).
-- **`returnControlInvocationResults`**: the results obtained from invoking the action outside of Amazon Bedrock Agents.  This field is required if passing the answer of a Return of Control invocation. You can find an example of how to use it [here](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/agents-for-bedrock/features-examples/03-create-agent-with-return-of-control).
+- **`invocationId`**: The id returned by the agent in the [ReturnControlPayload](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_agent-runtime_ReturnControlPayload.html) object in the returnControl field of the InvokeAgent response. This field is required if passing the answer of a Return of Control invocation. You can find an example of how to use it [here](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/agents-and-function-calling/bedrock-agents/features-examples/03-create-agent-with-return-of-control).
+- **`returnControlInvocationResults`**: the results obtained from invoking the action outside of Amazon Bedrock Agents.  This field is required if passing the answer of a Return of Control invocation. You can find an example of how to use it [here](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/agents-and-function-calling/bedrock-agents/features-examples/03-create-agent-with-return-of-control).
 
 Finally, if `show_code_use` is passed as True, the helper will print a message when the code interpreter is invoked. It turns on tracing internally to do this.