本文為英文版的機器翻譯版本，如內容有任何歧義或不一致之處，概以英文版為準。
# 教學課程：建立處理房屋貸款申請的流程
為了熟悉 Amazon Bedrock 資源及其功能，我們將使用 CloudFormation 範本來設定[流程](flows.md)，透過結合各種 Amazon Bedrock 和其他 AWS 資源來自動化抵押貸款申請程序。
**注意**
在本教學課程中，我們將使用 *us-east-1* 區域。您可以使用支援代理程式、流程、防護機制、知識庫和提示管理的任何區域。如需依區域的功能支援資料表，請參閱 [Amazon Bedrock AWS 區域 中的 功能支援](features-regions.md)。請確定您具有在所使用的區域中建立 Amazon S3、Amazon Bedrock、Lambda 和 DynamoDB 資源的許可。
此流程並非用於部署目的，而是用做了解 Amazon Bedrock 資源的教學課程。下圖是 AWS 管理主控台中流程的視覺化呈現：
![\[房屋貸款處理流程\]](http://docs.aws.amazon.com/zh_tw/bedrock/latest/userguide/images/cloudformation/mortgage-processing-flow.png)
流程結合 Amazon Bedrock 代理人[使用 AI 代理程式自動執行應用程式中的任務](agents.md)、[提示](prompt-management.md)和 [Lambda 函式](https://docs.aws.amazon.com/lambda/latest/dg/welcome.html)，以建立房屋貸款處理流程，擷取客戶財務資訊並處理客戶是否符合貸款資格。Amazon Bedrock [知識庫](knowledge-base.md)和[防護機制](guardrails.md)也會連接到流程的代理程式，以增強回應並提供保護。如需有關流程元件的詳細資訊，請參閱[有關房屋貸款處理流程的詳細資訊](getting-started-mortgage-flow-details.md)。
**Topics**
+ [先決條件](#getting-started-mortgage-flow-prereqs)
+ [使用 建立抵押貸款處理流程 CloudFormation](#getting-started-mortgage-flow-create)
+ [測試房屋貸款處理流程](#getting-started-mortgage-flow-test)
+ [清除：刪除資源](#getting-started-mortgage-flow-delete)
+ [CloudFormation 範本](getting-started-mortgage-flow-template.md)
+ [有關房屋貸款處理流程的詳細資訊](getting-started-mortgage-flow-details.md)
## 先決條件
若要建立此流程，您要下載 .zip 檔案，並遵循指示執行指令碼，為您設定資源和範本。
**重要**
在您刪除 Amazon 資源之前，將會向您收取您所建立 Amazon 資源的費用。
然後，完成下列必要條件：
1. 下載 [cloudformation-mortgage-flow-setup.zip](samples/cloudformation-mortgage-flow-setup.zip) 檔案。
1. 解壓縮檔案。您可以在 [CloudFormation 範本](getting-started-mortgage-flow-template.md) 進一步了解內容。
1. 執行下列動作，請求存取 Amazon Bedrock 基礎模型：
1. AWS 管理主控台 使用具有使用 Amazon Bedrock 主控台之許可的 IAM 身分登入 。接著，開啟位於 [https://console.aws.amazon.com/bedrock](https://console.aws.amazon.com/bedrock) 的 Amazon Bedrock 主控台。
1. 在右上角檢查您的區域，確定您位於**美國東部 (維吉尼亞北部)** 區域。如果不是，請切換區域。
1. 選取左側導覽窗格底部的**模型存取**。
1. 選擇**修改模型存取**。
1. 執行以下任意一項：
+ 若要請求存取所有模型，請選擇**啟用所有模型**。在您前往的頁面上，所有模型旁的核取方塊都會填滿。
+ 若要請求存取特定模型，請選擇**啟用所有模型**。在您前往的頁面上，您有下列選項：
+ 若要請求供應商存取所有模型，請選取供應商名稱旁的核取方塊。
+ 若要請求存取一個模型，請選取模型名稱旁的核取方塊。
1. 基於以下教學的目的，您至少應請求存取 **Titan Embeddings G1 - Text** 和 **Claude 3 Haiku** 模型。然後選擇**下一步**。
1. 檢閱您請求存取的模型和**條款**。當您就緒時，請選擇**提交**以請求存取。
## 使用 建立抵押貸款處理流程 CloudFormation
為建立房屋貸款處理流程及其相關資源，我們將建立 CloudFormation 範本，並使用它來建立包含 Amazon Bedrock 資源的堆疊。
**重要**
在您刪除 Amazon 資源之前，將會向您收取您所建立 Amazon 資源的費用。
### 建立資源和 CloudFormation 範本檔案
首先，使用 .zip 檔案的指令碼將資源上傳至 S3 儲存貯體，並建立 CloudFormation 範本。
1. 在終端機中，執行下列命令，將資源複製到 Amazon S3 儲存貯體，並使用 S3 儲存貯體名稱填入 `main-stack.yaml` 和 `main-stack.json` 檔案，做為儲存貯體名稱參數的預設值。
```
bash deploy.sh
```
**注意**
指令碼的使用方式為 `bash deploy.sh `，其中 ** 和 ** 是選用引數。如果您不提供這些值，則會使用下列預設值：
** – 登入 AWS 資料設定中指定的預設 AWS 區域。
** – 儲存貯體將命名為 *mortgage-flow-deployment--*，其中 ** 是 AWS 您的帳戶 ID，而 ** 符合您提供的值或 AWS 登入資料設定中指定的預設 AWS 區域。
1. 確認提示。部署完成後，您應該有完整的 `main-stack.yaml` 和 `main-stack.json` 範本，以供下一個步驟使用。
**注意**
如果指令碼失敗，您可以執行下列動作來手動準備資源：
將解壓縮的 `cloudformation-mortgage-flow-setup` 資料夾的*內容* (不包括資料夾本身) 上傳至 Amazon S3 主控台中美國東部 (維吉尼亞北部) 的 S3 儲存貯體，網址為 [https://console.aws.amazon.com/s3/](https://console.aws.amazon.com/s3/)。
尋找 `templates/json/main-stack-tmp.yaml` 或 `templates/json/main-stack-tmp.json` 檔案並執行下列動作：
將 `Q01pS3BucketName` 參數的 `Default` 值從 *MortgageFlowBucket* 變更為 S3 儲存貯體名稱。
從檔案名稱中移除 `-tmp`，使其變成 `templates/json/main-stack.yaml` 或 `templates/json/main-stack.json`。
### 使用 CloudFormation 主控台建立堆疊
接下來，使用您剛儲存的範本來佈建 CloudFormation 堆疊。
1. 在 https：//[https://console.aws.amazon.com/cloudformation](https://console.aws.amazon.com/cloudformation/) 開啟 CloudFormation 主控台。在右上角檢查您的區域，確定您位於**美國東部 (維吉尼亞北部)** 區域。如果不是，請切換區域。
1. 在**堆疊**頁面上，從**建立堆疊**功能表中選擇**使用新資源 (標準)**。
1. 指定範本：
1. 在**必要條件**下，選擇**選擇現有範本**。
1. 在**指定範本**下，選擇**上傳範本檔案**。
1. 選擇**選擇檔案**，導覽至 `main-stack.yaml` 或 `main-stack.json` 範本，然後加以選取。
1. 選擇**下一步**。
1. 指定堆疊詳細資訊：
1. 在**堆疊名稱**欄位中，輸入堆疊的名稱。
1. 在**參數**欄位中，保留預設值。
**注意**
`Q01pS3BucketName` 值應與上傳此範本資源的 S3 儲存貯體名稱相符。其餘引數與知識庫的組態相關，如果您修改其中任何引數，請確定組態彼此相容。如需詳細資訊，請參閱[使用您為知識庫建立的向量存放區的先決條件](knowledge-base-setup.md)。
1. 選擇**下一步**。
1. 設定堆疊選項：
1. 在**堆疊失敗選項**下，選擇**刪除所有新建立的資源**。
**注意**
選擇此選項可避免針對刪除政策指定的資源向您收費，即使堆疊建立失敗也一樣。如需詳細資訊，請參閱《CloudFormation 使用者指南》**中的 [`DeletionPolicy` 屬性](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-attribute-deletionpolicy.html)。
1. 在**功能**下，勾選方塊以確認 CloudFormation 可能會在您的帳戶中建立 IAM 資源。
1. 選擇**下一步**。
1. 檢閱堆疊詳細資訊，然後選擇 **Submit**. CloudFormation creates the stack。建立需要幾分鐘的時間。堆疊建立完成後，您可以使用堆疊詳細資訊頁面上的**資源**索引標籤來檢視帳戶中佈建的資源。
1. 堆疊建立完成後，請執行下列動作來同步知識庫的資料來源，以便查詢知識庫：
1. AWS 管理主控台 使用具有使用 Amazon Bedrock 主控台之許可的 IAM 身分登入 。接著，開啟位於 [https://console.aws.amazon.com/bedrock](https://console.aws.amazon.com/bedrock) 的 Amazon Bedrock 主控台。
1. 從左側導覽窗格選擇**知識庫**，然後選取所建立名為 `AWSDocsTutorial-MortgageKB` 的知識庫。
1. 在**資料來源**區段中，選取所建立名為 `AWSDocsTutorial-MortgageKB-DS` 的資料來源旁的核取方塊。
1. 選擇**同步**。同步完成後，您可以測試流程。
## 測試房屋貸款處理流程
建立房屋貸款處理流程後，您可以使用 Amazon Bedrock 主控台來檢查、測試及修改流程。您也可以檢查、測試及修改流程中的個別資源。
**測試流程**
1. AWS 管理主控台 使用具有使用 Amazon Bedrock 主控台之許可的 IAM 身分登入 。接著，開啟位於 [https://console.aws.amazon.com/bedrock](https://console.aws.amazon.com/bedrock) 的 Amazon Bedrock 主控台。
1. 在左側導覽窗格中，選擇**流程**。在右上角檢查您的區域，確定您位於**美國東部 (維吉尼亞北部)** 區域。如果不是，請切換區域。
1. 在**流程**區段中，選取從 CloudFormation 範本建立的流程。它應該為 `AWSDocsTutorial-MortgageFlow`。
1. 選擇**在流程建置器中編輯**。您可以在流程中拖曳個別節點，以修改流程的視覺化呈現。
1. 在**測試流程**窗格中，在文字欄位中輸入以下內容，然後選取**執行**。
```
{
"income": 80000,
"totalDebt": 5000,
"loanTerm": 30,
"loanAmount": 600000,
"creditScore": 750,
"mlsId": "MLS-5678"
}
```
由於貸款金額大於計算出的最高可負擔貸款金額，隨即會觸發 **incomeDebt** 提示，而流程會產生拒絕函。您可以選擇**顯示追蹤**，以查看流程中執行的節點。
1. 同樣地，在**測試流程**窗格中，在文字欄位中輸入以下內容，然後選取**執行**。
```
{
"income": 120000,
"totalDebt": 5000,
"loanTerm": 30,
"loanAmount": 200000,
"creditScore": 650,
"mlsId": "MLS-3456"
}
```
由於貸款金額小於計算出的最高可負擔貸款金額，隨即會觸發 **processApplication** 提示，並傳送至 **mortgageProcessingAgent**，該提示會查詢連接的知識庫，並根據輸入值產生回應，以評估客戶是否符合貸款資格。
1. (選用) 嘗試對 JSON 物件中的欄位使用不同的值來執行流程。這些 `mlsId` 值對應至多重刊登服務上所刊登的屬性。若要尋找有效的 `mlsId` 值，請執行下列操作：
1. 登入 AWS 管理主控台 ，並在 https：//[https://console.aws.amazon.com/dynamodb/](https://console.aws.amazon.com/dynamodb/) 開啟 DynamoDB 主控台。
1. 在左側導覽窗格中，選取**資料表**。
1. 選取顯示 **AWSDocsTutorial-PropertyListing** 的資料表。
1. 選擇**探索資料表項目**。
1. 您可以使用流程輸入中 **mls\$1id** 欄中的任何值。
您也可以導覽至 中的**客服人員**、**知識庫**、**護欄**和**提示管理**頁面， AWS 管理主控台 以獨立檢查流程中使用的每個 Amazon Bedrock 資源。若要進一步了解流程並更詳細了解元件，請參閱 [有關房屋貸款處理流程的詳細資訊](getting-started-mortgage-flow-details.md)。
## 清除：刪除資源
在您探索資源並更加了解不同 Amazon Bedrock 資源的功能之後，我們將刪除堆疊及其包含的資源。
**重要**
在您刪除 Amazon 資源之前，將會向您收取您所建立 Amazon 資源的費用。
1. 開啟 [https://console.aws.amazon.com/cloudformation](https://console.aws.amazon.com/cloudformation/)。
1. 在左側導覽窗格中，選擇**堆疊**。
1. 選擇您從範本建立的堆疊。然後選擇**刪除**，並確認**刪除**。
CloudFormation 會啟動刪除主要堆疊、其所有巢狀堆疊，以及堆疊中包含的所有資源。
# CloudFormation 範本
您下載的 `cloudformation-mortgage-flow-setup.zip` 檔案包含下列檔案：
+ `deploy.sh` – 殼層指令碼，可部署您的資源並準備您將使用的主要 CloudFormation 範本。
+ `artifacts` – 包含 .zip 檔案的資料夾，其中包含代理程式和知識庫範本的函數：
+ 代理程式動作群組的 Lambda 函式
+ `agent_loan_calculator.zip`
+ `mls_lookup.zip`
+ `loader_deployment_package.zip`
+ 用於設定知識庫的函數
+ `custom-resource-lambda.zip`
+ `opensearchpy-layer.zip`
+ `provider-event-handler.zip`
+ `api-schema` – 包含動作群組 API 結構描述的資料夾。
+ `knowledge-base-data-source` – 包含《[Fannie Mae 銷售指南](https://selling-guide.fanniemae.com/)》PDF 的資料夾。
+ `templates` – 包含此流程中資源範本的資料夾，包括 JSON 和 YAML 格式：
+ `main-stack-tmp` – 將其餘範本部署為巢狀堆疊的主要範本。部署指令碼執行後，此檔案會變成 `main-stack`。
+ `guardrails-template` – 要與代理程式建立關聯的防護機制範本。
+ `prompts-template` – 要在流程中使用的提示範本。
+ `kb-role-template` – 供 OpenSearch 範本和知識庫範本使用的知識庫角色範本。
+ `oss-infra-template` – 用於知識庫的 Amazon OpenSearch Serverless 向量存放區的範本。
+ `kb-infra-template` – 要與代理程式建立關聯的房屋貸款知識庫範本。
+ `agent-template` – 要在流程中使用的房屋貸款處理代理程式範本。
+ `mortgage-flow-template` – 合併所有資源的房屋貸款處理流程範本。
+ `README.md` – README 檔案，描述使用範本的步驟。
下列主題顯示用於每個堆疊的 CloudFormation 範本。主要堆疊會將剩餘的堆疊部署為[巢狀堆疊](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/using-cfn-nested-stacks.html)。
**Topics**
+ [主要堆疊](#getting-started-mortgage-templates-main)
+ [Amazon Bedrock 防護機制堆疊](#getting-started-mortgage-guardrail-templates)
+ [Amazon Bedrock 提示管理堆疊](#getting-started-mortgage-prompts-templates)
+ [Amazon Bedrock 知識庫堆疊](#getting-started-mortgage-kb-templates)
## 主要堆疊
主要堆疊會定義您在上傳範本時可以定義的參數。這些值會傳遞至每個剩餘的巢狀堆疊。部署指令碼會將 `Q01pS3BucketName` 參數預設值的 *MortgageFlowBucket* 取代為您包含指令碼所部署之資源的實際 S3 儲存貯體。
------
#### [ YAML ]
```
AWSTemplateFormatVersion: '2010-09-09'
Description: "[AWSDocs] AmazonBedrockDocs: getting-started-mortgage-flow"
Parameters:
Q01pS3BucketName:
Type: String
Description: Provide existing S3 bucket name where data is already stored
Default: MortgageFlowBucket
Q02pFlowName:
Type: String
Description: Name for the flow
Default: MortgageFlow
Q03pGuardrailName:
Type: String
Description: Name for guardrail to attach to agent
Default: MortgageGR
Q04pKnowledgeBaseName:
Type: String
Description: Name for knowledge base to associate with agent
Default: MortgageKB
Q05pAgentName:
Type: String
Description: Name for agent to create
Default: MortgageAgent
Q06pKBEmbedModel:
Type: String
Description: Select Embedding model
Default: amazon.titan-embed-text-v1
Q07pKBChunkingStrategy:
Type: String
Description: Select Chunking strategy
AllowedValues:
- Default chunking
- Fixed-size chunking
- No chunking
Default: Default chunking
Q08pKBMaxTokens:
Type: Number
Description: Maximum number of tokens in a chunk
Default: 300
Q09pKBOverlapPercentage:
Type: Number
Description: Percent overlap in each chunk
Default: 20
Q10pKBVectorStore:
Type: String
Description: Select vector store
AllowedValues:
- Open-Search-Serverless
Default: Open-Search-Serverless
Q11pOSSCollectionName:
Type: String
Description: Name of the Collection
MinLength: 1
MaxLength: 63
Default: mortgage-kb-collection
AllowedPattern: ^[a-z0-9](-*[a-z0-9])*
ConstraintDescription: Must be lowercase or numbers with a length of 1-32 characters
Q12pOSSIndexName:
Type: String
Description: Index name to be created in vector store
MinLength: 1
MaxLength: 63
Default: mortgage-kb-index
AllowedPattern: ^[a-z0-9](-*[a-z0-9])*
ConstraintDescription: Must be lowercase or numbers with a length of 1-63 characters
# Q13pVectorFieldName:
# Type: String
# Description: Vector field name
# Default: bedrock-knowledge-base-default-vector
# Q14pMetaDataFieldName:
# Type: String
# Description: Metadata field name
# Default: AMAZON_BEDROCK_METADATA
# Q15pTextFieldName:
# Type: String
# Description: Text field name
# Default: AMAZON_BEDROCK_TEXT_CHUNK
Resources:
KBRoleStack:
Type: AWS::CloudFormation::Stack
Properties:
TemplateURL: !Sub https://${Q01pS3BucketName}.s3.amazonaws.com/templates/yaml/kb-role-template.yaml
TimeoutInMinutes: 15
Parameters:
Q01pS3BucketName:
Ref: Q01pS3BucketName
OSSStack:
Type: AWS::CloudFormation::Stack
DependsOn: KBRoleStack
Properties:
TemplateURL: !Sub https://${Q01pS3BucketName}.s3.amazonaws.com/templates/yaml/oss-infra-template.yaml
TimeoutInMinutes: 15
Parameters:
Q01pS3BucketName:
Ref: Q01pS3BucketName
Q06pKBEmbedModel:
Ref: Q06pKBEmbedModel
Q11pOSSCollectionName:
Ref: Q11pOSSCollectionName
Q12pOSSIndexName:
Ref: Q12pOSSIndexName
pKBRole:
Fn::GetAtt:
- KBRoleStack
- Outputs.KBRole
pKBRoleArn:
Fn::GetAtt:
- KBRoleStack
- Outputs.KBRoleArn
KBStack:
Type: AWS::CloudFormation::Stack
DependsOn: OSSStack
Properties:
TemplateURL: !Sub https://${Q01pS3BucketName}.s3.amazonaws.com/templates/yaml/kb-infra-template.yaml
TimeoutInMinutes: 15
Parameters:
KnowledgeBaseName:
Ref: Q04pKnowledgeBaseName
Q01pS3BucketName:
Ref: Q01pS3BucketName
Q06pKBEmbedModel:
Ref: Q06pKBEmbedModel
Q07pKBChunkingStrategy:
Ref: Q07pKBChunkingStrategy
Q08pKBMaxTokens:
Ref: Q08pKBMaxTokens
Q09pKBOverlapPercentage:
Ref: Q09pKBOverlapPercentage
Q11pOSSCollectionName:
Ref: Q11pOSSCollectionName
Q12pOSSIndexName:
Ref: Q12pOSSIndexName
# Q13pVectorFieldName:
# Ref: Q13pVectorFieldName
# Q14pMetaDataFieldName:
# Ref: Q14pMetaDataFieldName
# Q15pTextFieldName:
# Ref: Q15pTextFieldName
pCollectionArn:
Fn::GetAtt:
- OSSStack
- Outputs.CollectionArn
pKBRoleArn:
Fn::GetAtt:
- KBRoleStack
- Outputs.KBRoleArn
pKBRole:
Fn::GetAtt:
- KBRoleStack
- Outputs.KBRole
GRStack:
Type: AWS::CloudFormation::Stack
Properties:
TemplateURL: !Sub https://${Q01pS3BucketName}.s3.amazonaws.com/templates/yaml/guardrails-template.yaml
TimeoutInMinutes: 15
Parameters:
GuardrailName:
Ref: Q03pGuardrailName
AgentStack:
Type: AWS::CloudFormation::Stack
DependsOn:
- KBStack
- GRStack
Properties:
TemplateURL: !Sub https://${Q01pS3BucketName}.s3.amazonaws.com/templates/yaml/agent-template.yaml
TimeoutInMinutes: 15
Parameters:
Q01pS3BucketName:
Ref: Q01pS3BucketName
KnowledgeBaseId:
Fn::GetAtt:
- KBStack
- Outputs.KBId
GuardrailArn:
Fn::GetAtt:
- GRStack
- Outputs.GuardrailArn
GuardrailVersion:
Fn::GetAtt:
- GRStack
- Outputs.GuardrailVersion
PromptsStack:
Type: AWS::CloudFormation::Stack
Properties:
TemplateURL: !Sub https://${Q01pS3BucketName}.s3.amazonaws.com/templates/yaml/prompts-template.yaml
TimeoutInMinutes: 15
FlowStack:
Type: AWS::CloudFormation::Stack
DependsOn:
- AgentStack
- PromptsStack
Properties:
TemplateURL: !Sub https://${Q01pS3BucketName}.s3.amazonaws.com/templates/yaml/mortgage-flow-template.yaml
TimeoutInMinutes: 15
Parameters:
FlowName:
Ref: Q02pFlowName
Q01pS3BucketName:
Ref: Q01pS3BucketName
ProcessApplicationPromptArn:
Fn::GetAtt:
- PromptsStack
- Outputs.ProcessApplicationPromptArn
RejectionPromptArn:
Fn::GetAtt:
- PromptsStack
- Outputs.RejectionPromptArn
AgentId:
Fn::GetAtt:
- AgentStack
- Outputs.AgentId
```
------
#### [ JSON ]
```
{
"AWSTemplateFormatVersion": "2010-09-09",
"Description": "[AWSDocs] AmazonBedrockDocs: getting-started-mortgage-flow",
"Parameters": {
"Q01pS3BucketName": {
"Type": "String",
"Description": "Provide existing S3 bucket name where data is already stored",
"Default": "MortgageFlowBucket"
},
"Q02pFlowName": {
"Type": "String",
"Description": "Name for the flow",
"Default": "MortgageFlow"
},
"Q03pGuardrailName": {
"Type": "String",
"Description": "Name for guardrail to attach to agent",
"Default": "MortgageGR"
},
"Q04pKnowledgeBaseName": {
"Type": "String",
"Description": "Name for knowledge base to associate with agent",
"Default": "MortgageKB"
},
"Q05pAgentName": {
"Type": "String",
"Description": "Name for agent to create",
"Default": "MortgageAgent"
},
"Q06pKBEmbedModel": {
"Type": "String",
"Description": "Select Embedding model",
"Default": "amazon.titan-embed-text-v1"
},
"Q07pKBChunkingStrategy": {
"Type": "String",
"Description": "Select Chunking strategy",
"AllowedValues": [
"Default chunking",
"Fixed-size chunking",
"No chunking"
],
"Default": "Default chunking"
},
"Q08pKBMaxTokens": {
"Type": "Number",
"Description": "Maximum number of tokens in a chunk",
"Default": 300
},
"Q09pKBOverlapPercentage": {
"Type": "Number",
"Description": "Percent overlap in each chunk",
"Default": 20
},
"Q10pKBVectorStore": {
"Type": "String",
"Description": "Select vector store",
"AllowedValues": [
"Open-Search-Serverless"
],
"Default": "Open-Search-Serverless"
},
"Q11pOSSCollectionName": {
"Type": "String",
"Description": "Name of the Collection",
"MinLength": 1,
"MaxLength": 63,
"Default": "mortgage-kb-collection",
"AllowedPattern": "^[a-z0-9](-*[a-z0-9])*",
"ConstraintDescription": "Must be lowercase or numbers with a length of 1-32 characters"
},
"Q12pOSSIndexName": {
"Type": "String",
"Description": "Index name to be created in vector store",
"MinLength": 1,
"MaxLength": 63,
"Default": "mortgage-kb-index",
"AllowedPattern": "^[a-z0-9](-*[a-z0-9])*",
"ConstraintDescription": "Must be lowercase or numbers with a length of 1-63 characters"
}
},
"Resources": {
"KBRoleStack": {
"Type": "AWS::CloudFormation::Stack",
"Properties": {
"TemplateURL": {
"Fn::Sub": "https://${Q01pS3BucketName}.s3.amazonaws.com/templates/json/kb-role-template.json"
},
"TimeoutInMinutes": 15,
"Parameters": {
"Q01pS3BucketName": {
"Ref": "Q01pS3BucketName"
}
}
}
},
"OSSStack": {
"Type": "AWS::CloudFormation::Stack",
"DependsOn": "KBRoleStack",
"Properties": {
"TemplateURL": {
"Fn::Sub": "https://${Q01pS3BucketName}.s3.amazonaws.com/templates/json/oss-infra-template.json"
},
"TimeoutInMinutes": 15,
"Parameters": {
"Q01pS3BucketName": {
"Ref": "Q01pS3BucketName"
},
"Q06pKBEmbedModel": {
"Ref": "Q06pKBEmbedModel"
},
"Q11pOSSCollectionName": {
"Ref": "Q11pOSSCollectionName"
},
"Q12pOSSIndexName": {
"Ref": "Q12pOSSIndexName"
},
"pKBRole": {
"Fn::GetAtt": [
"KBRoleStack",
"Outputs.KBRole"
]
},
"pKBRoleArn": {
"Fn::GetAtt": [
"KBRoleStack",
"Outputs.KBRoleArn"
]
}
}
}
},
"KBStack": {
"Type": "AWS::CloudFormation::Stack",
"DependsOn": "OSSStack",
"Properties": {
"TemplateURL": {
"Fn::Sub": "https://${Q01pS3BucketName}.s3.amazonaws.com/templates/json/kb-infra-template.json"
},
"TimeoutInMinutes": 15,
"Parameters": {
"KnowledgeBaseName": {
"Ref": "Q04pKnowledgeBaseName"
},
"Q01pS3BucketName": {
"Ref": "Q01pS3BucketName"
},
"Q06pKBEmbedModel": {
"Ref": "Q06pKBEmbedModel"
},
"Q07pKBChunkingStrategy": {
"Ref": "Q07pKBChunkingStrategy"
},
"Q08pKBMaxTokens": {
"Ref": "Q08pKBMaxTokens"
},
"Q09pKBOverlapPercentage": {
"Ref": "Q09pKBOverlapPercentage"
},
"Q11pOSSCollectionName": {
"Ref": "Q11pOSSCollectionName"
},
"Q12pOSSIndexName": {
"Ref": "Q12pOSSIndexName"
},
"pCollectionArn": {
"Fn::GetAtt": [
"OSSStack",
"Outputs.CollectionArn"
]
},
"pKBRoleArn": {
"Fn::GetAtt": [
"KBRoleStack",
"Outputs.KBRoleArn"
]
},
"pKBRole": {
"Fn::GetAtt": [
"KBRoleStack",
"Outputs.KBRole"
]
}
}
}
},
"GRStack": {
"Type": "AWS::CloudFormation::Stack",
"Properties": {
"TemplateURL": {
"Fn::Sub": "https://${Q01pS3BucketName}.s3.amazonaws.com/templates/json/guardrails-template.json"
},
"TimeoutInMinutes": 15,
"Parameters": {
"GuardrailName": {
"Ref": "Q03pGuardrailName"
}
}
}
},
"AgentStack": {
"Type": "AWS::CloudFormation::Stack",
"DependsOn": [
"KBStack",
"GRStack"
],
"Properties": {
"TemplateURL": {
"Fn::Sub": "https://${Q01pS3BucketName}.s3.amazonaws.com/templates/json/agent-template.json"
},
"TimeoutInMinutes": 15,
"Parameters": {
"Q01pS3BucketName": {
"Ref": "Q01pS3BucketName"
},
"KnowledgeBaseId": {
"Fn::GetAtt": [
"KBStack",
"Outputs.KBId"
]
},
"GuardrailArn": {
"Fn::GetAtt": [
"GRStack",
"Outputs.GuardrailArn"
]
},
"GuardrailVersion": {
"Fn::GetAtt": [
"GRStack",
"Outputs.GuardrailVersion"
]
}
}
}
},
"PromptsStack": {
"Type": "AWS::CloudFormation::Stack",
"Properties": {
"TemplateURL": {
"Fn::Sub": "https://${Q01pS3BucketName}.s3.amazonaws.com/templates/json/prompts-template.json"
},
"TimeoutInMinutes": 15
}
},
"FlowStack": {
"Type": "AWS::CloudFormation::Stack",
"DependsOn": [
"AgentStack",
"PromptsStack"
],
"Properties": {
"TemplateURL": {
"Fn::Sub": "https://${Q01pS3BucketName}.s3.amazonaws.com/templates/json/mortgage-flow-template.json"
},
"TimeoutInMinutes": 15,
"Parameters": {
"FlowName": {
"Ref": "Q02pFlowName"
},
"Q01pS3BucketName": {
"Ref": "Q01pS3BucketName"
},
"ProcessApplicationPromptArn": {
"Fn::GetAtt": [
"PromptsStack",
"Outputs.ProcessApplicationPromptArn"
]
},
"RejectionPromptArn": {
"Fn::GetAtt": [
"PromptsStack",
"Outputs.RejectionPromptArn"
]
},
"AgentId": {
"Fn::GetAtt": [
"AgentStack",
"Outputs.AgentId"
]
}
}
}
}
}
}
```
------
## Amazon Bedrock 防護機制堆疊
此堆疊會建立下列與[防護機制](guardrails.md)相關的資源：
+ AgentGuardrail ([AWS::Bedrock::Guardrail](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide /aws-resource-bedrock-guardrail.html)) – 提供內容篩選、主題政策和 PII 保護的防護機制。此防護機制將連接到代理程式堆疊中的代理程式。
+ AgentGuardrailVersion ([AWS::Bedrock::GuardrailVersion](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide /aws-resource-bedrock-guardrailversion.html)) – 套用至代理程式的 `AgentGuardrail` 資源之版本。
------
#### [ YAML ]
```
AWSTemplateFormatVersion: "2010-09-09"
Description: "[AWSDocs] AmazonBedrockDocs: getting-started-mortgage-flow"
Parameters:
GuardrailName:
Type: String
Description: Name for guardrail
Default: MortgageGuardrail
Resources:
AgentGuardrail:
Type: AWS::Bedrock::Guardrail
Properties:
Name: !Sub AWSDocsTutorial-${GuardrailName}
Description: Guardrail for mortgage processing with investment advice blocking, content filtering, and PII protection
BlockedInputMessaging: "Sorry, the model cannot answer this question."
BlockedOutputsMessaging: "Sorry, the model cannot answer this question."
TopicPolicyConfig:
TopicsConfig:
- Name: InvestmentAdvice
Definition: "Investment advice refers to inquires, guidance or recommendations regarding the management or allocation of fund or asset with the goal of generating returns or achieving specific financial objectives"
Examples:
- "Is investing in the stocks better than bonds?"
- "Should I invest in gold?"
Type: DENY
ContentPolicyConfig:
FiltersConfig:
- Type: VIOLENCE
InputStrength: HIGH
OutputStrength: HIGH
- Type: PROMPT_ATTACK
InputStrength: HIGH
OutputStrength: NONE
- Type: MISCONDUCT
InputStrength: HIGH
OutputStrength: HIGH
- Type: HATE
InputStrength: HIGH
OutputStrength: HIGH
- Type: SEXUAL
InputStrength: HIGH
OutputStrength: HIGH
- Type: INSULTS
InputStrength: HIGH
OutputStrength: HIGH
WordPolicyConfig:
WordsConfig:
- Text: "crypto currency"
- Text: "bitcoin"
ManagedWordListsConfig:
- Type: PROFANITY
SensitiveInformationPolicyConfig:
PiiEntitiesConfig:
- Type: EMAIL
Action: ANONYMIZE
- Type: CREDIT_DEBIT_CARD_NUMBER
Action: BLOCK
ContextualGroundingPolicyConfig:
FiltersConfig:
- Type: GROUNDING
Threshold: 0.85
- Type: RELEVANCE
Threshold: 0.5
AgentGuardrailVersion:
Type: AWS::Bedrock::GuardrailVersion
Properties:
GuardrailIdentifier: !Ref AgentGuardrail
Description: Version 1 of the mortgage agent guardrail
Outputs:
GuardrailArn:
Value:
Ref: AgentGuardrail
Description: ARN of guardrail to associate with agent
GuardrailVersion:
Value:
Fn::GetAtt:
- AgentGuardrailVersion
- Version
Description: Version of guardrail to associate with agent
```
------
#### [ JSON ]
```
{
"AWSTemplateFormatVersion": "2010-09-09",
"Description": "[AWSDocs] AmazonBedrockDocs: getting-started-mortgage-flow",
"Parameters": {
"GuardrailName": {
"Type": "String",
"Description": "Name for guardrail",
"Default": "MortgageGuardrail"
}
},
"Resources": {
"AgentGuardrail": {
"Type": "AWS::Bedrock::Guardrail",
"Properties": {
"Name": {
"Fn::Sub": "AWSDocsTutorial-${GuardrailName}"
},
"Description": "Guardrail for mortgage processing with investment advice blocking, content filtering, and PII protection",
"BlockedInputMessaging": "Sorry, the model cannot answer this question.",
"BlockedOutputsMessaging": "Sorry, the model cannot answer this question.",
"TopicPolicyConfig": {
"TopicsConfig": [
{
"Name": "InvestmentAdvice",
"Definition": "Investment advice refers to inquires, guidance or recommendations regarding the management or allocation of fund or asset with the goal of generating returns or achieving specific financial objectives",
"Examples": [
"Is investing in the stocks better than bonds?",
"Should I invest in gold?"
],
"Type": "DENY"
}
]
},
"ContentPolicyConfig": {
"FiltersConfig": [
{
"Type": "VIOLENCE",
"InputStrength": "HIGH",
"OutputStrength": "HIGH"
},
{
"Type": "PROMPT_ATTACK",
"InputStrength": "HIGH",
"OutputStrength": "NONE"
},
{
"Type": "MISCONDUCT",
"InputStrength": "HIGH",
"OutputStrength": "HIGH"
},
{
"Type": "HATE",
"InputStrength": "HIGH",
"OutputStrength": "HIGH"
},
{
"Type": "SEXUAL",
"InputStrength": "HIGH",
"OutputStrength": "HIGH"
},
{
"Type": "INSULTS",
"InputStrength": "HIGH",
"OutputStrength": "HIGH"
}
]
},
"WordPolicyConfig": {
"WordsConfig": [
{
"Text": "crypto currency"
},
{
"Text": "bitcoin"
}
],
"ManagedWordListsConfig": [
{
"Type": "PROFANITY"
}
]
},
"SensitiveInformationPolicyConfig": {
"PiiEntitiesConfig": [
{
"Type": "EMAIL",
"Action": "ANONYMIZE"
},
{
"Type": "CREDIT_DEBIT_CARD_NUMBER",
"Action": "BLOCK"
}
]
},
"ContextualGroundingPolicyConfig": {
"FiltersConfig": [
{
"Type": "GROUNDING",
"Threshold": 0.85
},
{
"Type": "RELEVANCE",
"Threshold": 0.5
}
]
}
}
},
"AgentGuardrailVersion": {
"Type": "AWS::Bedrock::GuardrailVersion",
"Properties": {
"GuardrailIdentifier": {
"Ref": "AgentGuardrail"
},
"Description": "Version 1 of the mortgage agent guardrail"
}
}
},
"Outputs": {
"GuardrailArn": {
"Value": {
"Ref": "AgentGuardrail"
},
"Description": "ARN of guardrail to associate with agent"
},
"GuardrailVersion": {
"Value": {
"Fn::GetAtt": [
"AgentGuardrailVersion",
"Version"
]
},
"Description": "Version of guardrail to associate with agent"
}
}
}
```
------
## Amazon Bedrock 提示管理堆疊
此堆疊會建立下列[提示](prompt-management.md) ([AWS::IAM::Prompt](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide /aws-resource-bedrock-prompt.html)) 資源，這些資源會新增至流程：
+ RejectionPrompt – 根據財務資訊傳回所產生拒絕信件的提示。
+ ProcessApplicationPrompt – 將客戶財務資訊傳送給代理程式的提示，並提示代理程式評估客戶是否符合貸款資格。
------
#### [ YAML ]
```
AWSTemplateFormatVersion: "2010-09-09"
Description: "[AWSDocs] AmazonBedrockDocs: getting-started-mortgage-flow"
Resources:
RejectionPrompt:
Type: AWS::Bedrock::Prompt
Properties:
Name: !Sub AWSDocsTutorial-RejectionPrompt
Description: "Use this prompt to generate a rejection letter triggered by an unsatisfactory income to debt ratio"
DefaultVariant: variantOne
Variants:
- Name: variantOne
TemplateType: TEXT
ModelId: anthropic.claude-3-haiku-20240307-v1:0
TemplateConfiguration:
Text:
Text: |
Write a mortgage loan rejection letter for a candiate with income {{income}}, totalDebt {{totalDebt}}, loanAmount {{loanAmount}}.
The reason for rejection is their income to debt ratio.
Do not mention any other reason.
Make the letter as concise as possible.
Treat all numeric inputs as whole numbers.
Let the general structure be like the below:
Dear [Applicant's Name],
We appreciate your interest in obtaining a mortgage loan with our institution...
The primary reason for this decision is that ...
While we understand that this news may be disappointing, ...
Thank you again for your interest, and we wish you the best in your future endeavors...
Sincerely,
[Your Institution's Name]
InputVariables:
- Name: income
- Name: totalDebt
- Name: loanAmount
InferenceConfiguration:
Text:
MaxTokens: 2000
Temperature: 0.0
TopP: 0.999
StopSequences:
- "\n\nHuman:"
AdditionalModelRequestFields:
top_k: 250
ProcessApplicationPrompt:
Type: AWS::Bedrock::Prompt
Properties:
Name: !Sub AWSDocsTutorial-ProcessApplicationPrompt
Description: "Use this prompt to generate a question for an agent to process the mortgage application"
DefaultVariant: variantOne
Variants:
- Name: variantOne
TemplateType: TEXT
ModelId: anthropic.claude-3-haiku-20240307-v1:0
TemplateConfiguration:
Text:
Text: |
Generate a question asking if the user will qualify for a loan for the specified criteria.
Include instruction to base the answer on key features of the property retrieved from MLS listing.
Start with "will an applicant...".
{ "income": {{income}}, "creditScore": {{creditScore}}, "totalDebt": {{totalDebt}}, "loanAmount": {{loanAmount}}, "mlsId": {{mlsId}} }
Include a second question on loan requirements an applicant with the below attributes should consider for a Fannie Mae backed loan (other than debt to income).
InputVariables:
- Name: income
- Name: creditScore
- Name: totalDebt
- Name: loanAmount
- Name: mlsId
InferenceConfiguration:
Text:
MaxTokens: 2000
Temperature: 0.0
TopP: 0.999
StopSequences:
- "\n\nHuman:"
AdditionalModelRequestFields:
top_k: 250
Outputs:
ProcessApplicationPromptArn:
Value:
Ref: ProcessApplicationPrompt
Description: ARN of the prompt to process a mortgage application
RejectionPromptArn:
Value:
Ref: RejectionPrompt
Description: ARN of the prompt to reject a mortgage application
```
------
#### [ JSON ]
```
{
"AWSTemplateFormatVersion": "2010-09-09",
"Description": "[AWSDocs] AmazonBedrockDocs: getting-started-mortgage-flow",
"Resources": {
"RejectionPrompt": {
"Type": "AWS::Bedrock::Prompt",
"Properties": {
"Name": {
"Fn::Sub": "AWSDocsTutorial-RejectionPrompt"
},
"Description": "Use this prompt to generate a rejection letter triggered by an unsatisfactory income to debt ratio",
"DefaultVariant": "variantOne",
"Variants": [
{
"Name": "variantOne",
"TemplateType": "TEXT",
"ModelId": "anthropic.claude-3-haiku-20240307-v1:0",
"TemplateConfiguration": {
"Text": {
"Text": "Write a mortgage loan rejection letter for a candiate with income {{income}}, totalDebt {{totalDebt}}, loanAmount {{loanAmount}}. \nThe reason for rejection is their income to debt ratio. \nDo not mention any other reason. \nMake the letter as concise as possible. \nTreat all numeric inputs as whole numbers.\nLet the general structure be like the below:\n\nDear [Applicant's Name],\nWe appreciate your interest in obtaining a mortgage loan with our institution...\nThe primary reason for this decision is that ...\nWhile we understand that this news may be disappointing, ...\nThank you again for your interest, and we wish you the best in your future endeavors...\n\nSincerely,\n[Your Institution's Name]\n",
"InputVariables": [
{
"Name": "income"
},
{
"Name": "totalDebt"
},
{
"Name": "loanAmount"
}
]
}
},
"InferenceConfiguration": {
"Text": {
"MaxTokens": 2000,
"Temperature": 0.0,
"TopP": 0.999,
"StopSequences": [
"\n\nHuman:"
]
}
},
"AdditionalModelRequestFields": {
"top_k": 250
}
}
]
}
},
"ProcessApplicationPrompt": {
"Type": "AWS::Bedrock::Prompt",
"Properties": {
"Name": {
"Fn::Sub": "AWSDocsTutorial-ProcessApplicationPrompt"
},
"Description": "Use this prompt to generate a question for an agent to process the mortgage application",
"DefaultVariant": "variantOne",
"Variants": [
{
"Name": "variantOne",
"TemplateType": "TEXT",
"ModelId": "anthropic.claude-3-haiku-20240307-v1:0",
"TemplateConfiguration": {
"Text": {
"Text": "Generate a question asking if the user will qualify for a loan for the specified criteria. \n\nInclude instruction to base the answer on key features of the property retrieved from MLS listing. \n\nStart with \"will an applicant...\".\n\n{ \"income\": {{income}}, \"creditScore\": {{creditScore}}, \"totalDebt\": {{totalDebt}}, \"loanAmount\": {{loanAmount}}, \"mlsId\": {{mlsId}} }\n\nInclude a second question on loan requirements an applicant with the below attributes should consider for a Fannie Mae backed loan (other than debt to income).\n",
"InputVariables": [
{
"Name": "income"
},
{
"Name": "creditScore"
},
{
"Name": "totalDebt"
},
{
"Name": "loanAmount"
},
{
"Name": "mlsId"
}
]
}
},
"InferenceConfiguration": {
"Text": {
"MaxTokens": 2000,
"Temperature": 0.0,
"TopP": 0.999,
"StopSequences": [
"\n\nHuman:"
]
}
},
"AdditionalModelRequestFields": {
"top_k": 250
}
}
]
}
}
},
"Outputs": {
"ProcessApplicationPromptArn": {
"Value": {
"Ref": "ProcessApplicationPrompt"
},
"Description": "ARN of the prompt to process a mortgage application"
},
"RejectionPromptArn": {
"Value": {
"Ref": "RejectionPrompt"
},
"Description": "ARN of the prompt to reject a mortgage application"
}
}
}
```
------
## Amazon Bedrock 知識庫堆疊
此範本會建立[知識庫](knowledge-base.md)及其資料來源，其中包含貸款準則：
+ KnowledgeBase ([AWS::Bedrock::KnowledgeBase](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide /aws-resource-bedrock-knowledgebase.html))
+ KnowledgeBaseDataSource ([AWS::Bedrock::DataSource](https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide /aws-resource-bedrock-datasource.html))
------
#### [ YAML ]
```
AWSTemplateFormatVersion: '2010-09-09'
Description: "[AWSDocs] AmazonBedrockDocs: getting-started-mortgage-flow"
Parameters:
KnowledgeBaseName:
Type: String
Description: Name of knowledge base
Default: MortgageKB
Q01pS3BucketName:
Type: String
Description: Name of S3 bucket where knowledge base data is stored
Q06pKBEmbedModel:
Type: String
Description: Selected Embedding model
Q07pKBChunkingStrategy:
Type: String
Description: Selected Chunking strategy
Q08pKBMaxTokens:
Type: Number
Description: Maximum number of tokens in a chunk
Q09pKBOverlapPercentage:
Type: Number
Description: Percent overlap in each chunk
Q11pOSSCollectionName:
Type: String
Description: Name of the Collection
Q12pOSSIndexName:
Type: String
Description: Index name to be created in vector store
Q13pVectorFieldName:
Type: String
Description: Vector field name
Default: bedrock-knowledge-base-default-vector
Q14pMetaDataFieldName:
Type: String
Description: Metadata field name
Default: AMAZON_BEDROCK_METADATA
Q15pTextFieldName:
Type: String
Description: Text field name
Default: AMAZON_BEDROCK_TEXT_CHUNK
pCollectionArn:
Type: String
Description: Name of the Collection Arn
pKBRole:
Type: String
Description: KB role for e2e RAG
pKBRoleArn:
Type: String
Description: KB role Arn for e2e RAG
Conditions:
IsChunkingStrategyFixed:
Fn::Equals:
- Ref: Q07pKBChunkingStrategy
- Fixed-size chunking
IsChunkingStrategyDefault:
Fn::Equals:
- Ref: Q07pKBChunkingStrategy
- Default chunking
IsChunkingStrategyNoChunking:
Fn::Equals:
- Ref: Q07pKBChunkingStrategy
- No chunking
IsChunkingStrategyFixedOrDefault:
Fn::Or:
- Condition: IsChunkingStrategyFixed
- Condition: IsChunkingStrategyDefault
Resources:
KnowledgeBase:
Type: AWS::Bedrock::KnowledgeBase
Properties:
Description: Test KB Deployment
KnowledgeBaseConfiguration:
Type: VECTOR
VectorKnowledgeBaseConfiguration:
EmbeddingModelArn:
Fn::Sub: arn:aws:bedrock:${AWS::Region}::foundation-model/${Q06pKBEmbedModel}
Name: !Sub AWSDocsTutorial-${KnowledgeBaseName}
RoleArn:
Ref: pKBRoleArn
StorageConfiguration:
OpensearchServerlessConfiguration:
CollectionArn:
Ref: pCollectionArn
FieldMapping:
MetadataField:
Ref: Q14pMetaDataFieldName
TextField:
Ref: Q15pTextFieldName
VectorField:
Ref: Q13pVectorFieldName
VectorIndexName:
Ref: Q12pOSSIndexName
Type: OPENSEARCH_SERVERLESS
KnowledgeBaseDataSource:
Type: AWS::Bedrock::DataSource
DependsOn:
- KnowledgeBase
Properties:
DataSourceConfiguration:
Type: S3
S3Configuration:
BucketArn:
Fn::Sub: arn:aws:s3:::${Q01pS3BucketName}
InclusionPrefixes:
- knowledge-base-data-source/
Description: Knowledge base data source
KnowledgeBaseId:
Ref: KnowledgeBase
Name: !Sub AWSDocsTutorial-${KnowledgeBaseName}-DS
VectorIngestionConfiguration:
ChunkingConfiguration:
Fn::If:
- IsChunkingStrategyFixed
- ChunkingStrategy: FIXED_SIZE
FixedSizeChunkingConfiguration:
MaxTokens: !Ref Q08pKBMaxTokens
OverlapPercentage: !Ref Q09pKBOverlapPercentage
- Fn::If:
- IsChunkingStrategyDefault
- ChunkingStrategy: FIXED_SIZE
FixedSizeChunkingConfiguration:
MaxTokens: 300
OverlapPercentage: 20
- Fn::If:
- IsChunkingStrategyNoChunking
- ChunkingStrategy: NONE
- !Ref AWS::NoValue
Outputs:
KBId:
Value:
Ref: KnowledgeBase
Description: KnowledgeBase ID
DS:
Value:
Ref: KnowledgeBaseDataSource
Description: KnowledgeBase Datasource
```
------
#### [ JSON ]
```
{
"AWSTemplateFormatVersion": "2010-09-09",
"Description": "[AWSDocs] AmazonBedrockDocs: getting-started-mortgage-flow",
"Parameters": {
"KnowledgeBaseName": {
"Type": "String",
"Description": "Name of knowledge base",
"Default": "MortgageKB"
},
"Q01pS3BucketName": {
"Type": "String",
"Description": "Name of S3 bucket where knowledge base data is stored"
},
"Q06pKBEmbedModel": {
"Type": "String",
"Description": "Selected Embedding model"
},
"Q07pKBChunkingStrategy": {
"Type": "String",
"Description": "Selected Chunking strategy"
},
"Q08pKBMaxTokens": {
"Type": "Number",
"Description": "Maximum number of tokens in a chunk"
},
"Q09pKBOverlapPercentage": {
"Type": "Number",
"Description": "Percent overlap in each chunk"
},
"Q11pOSSCollectionName": {
"Type": "String",
"Description": "Name of the Collection"
},
"Q12pOSSIndexName": {
"Type": "String",
"Description": "Index name to be created in vector store"
},
"Q13pVectorFieldName": {
"Type": "String",
"Description": "Vector field name",
"Default": "bedrock-knowledge-base-default-vector"
},
"Q14pMetaDataFieldName": {
"Type": "String",
"Description": "Metadata field name",
"Default": "AMAZON_BEDROCK_METADATA"
},
"Q15pTextFieldName": {
"Type": "String",
"Description": "Text field name",
"Default": "AMAZON_BEDROCK_TEXT_CHUNK"
},
"pCollectionArn": {
"Type": "String",
"Description": "Name of the Collection Arn"
},
"pKBRole": {
"Type": "String",
"Description": "KB role for e2e RAG"
},
"pKBRoleArn": {
"Type": "String",
"Description": "KB role Arn for e2e RAG"
}
},
"Conditions": {
"IsChunkingStrategyFixed": {
"Fn::Equals": [
{
"Ref": "Q07pKBChunkingStrategy"
},
"Fixed-size chunking"
]
},
"IsChunkingStrategyDefault": {
"Fn::Equals": [
{
"Ref": "Q07pKBChunkingStrategy"
},
"Default chunking"
]
},
"IsChunkingStrategyNoChunking": {
"Fn::Equals": [
{
"Ref": "Q07pKBChunkingStrategy"
},
"No chunking"
]
},
"IsChunkingStrategyFixedOrDefault": {
"Fn::Or": [
{
"Condition": "IsChunkingStrategyFixed"
},
{
"Condition": "IsChunkingStrategyDefault"
}
]
}
},
"Resources": {
"KnowledgeBase": {
"Type": "AWS::Bedrock::KnowledgeBase",
"Properties": {
"Description": "Test KB Deployment",
"KnowledgeBaseConfiguration": {
"Type": "VECTOR",
"VectorKnowledgeBaseConfiguration": {
"EmbeddingModelArn": {
"Fn::Sub": "arn:aws:bedrock:${AWS::Region}::foundation-model/${Q06pKBEmbedModel}"
}
}
},
"Name": {
"Fn::Sub": "AWSDocsTutorial-${KnowledgeBaseName}"
},
"RoleArn": {
"Ref": "pKBRoleArn"
},
"StorageConfiguration": {
"OpensearchServerlessConfiguration": {
"CollectionArn": {
"Ref": "pCollectionArn"
},
"FieldMapping": {
"MetadataField": {
"Ref": "Q14pMetaDataFieldName"
},
"TextField": {
"Ref": "Q15pTextFieldName"
},
"VectorField": {
"Ref": "Q13pVectorFieldName"
}
},
"VectorIndexName": {
"Ref": "Q12pOSSIndexName"
}
},
"Type": "OPENSEARCH_SERVERLESS"
}
}
},
"KnowledgeBaseDataSource": {
"Type": "AWS::Bedrock::DataSource",
"DependsOn": [
"KnowledgeBase"
],
"Properties": {
"DataSourceConfiguration": {
"Type": "S3",
"S3Configuration": {
"BucketArn": {
"Fn::Sub": "arn:aws:s3:::${Q01pS3BucketName}"
},
"InclusionPrefixes": [
"knowledge-base-data-source/"
]
}
},
"Description": "Knowledge base data source",
"KnowledgeBaseId": {
"Ref": "KnowledgeBase"
},
"Name": {
"Fn::Sub": "AWSDocsTutorial-${KnowledgeBaseName}-DS"
},
"VectorIngestionConfiguration": {
"ChunkingConfiguration": {
"Fn::If": [
"IsChunkingStrategyFixed",
{
"ChunkingStrategy": "FIXED_SIZE",
"FixedSizeChunkingConfiguration": {
"MaxTokens": {
"Ref": "Q08pKBMaxTokens"
},
"OverlapPercentage": {
"Ref": "Q09pKBOverlapPercentage"
}
}
},
{
"Fn::If": [
"IsChunkingStrategyDefault",
{
"ChunkingStrategy": "FIXED_SIZE",
"FixedSizeChunkingConfiguration": {
"MaxTokens": 300,
"OverlapPercentage": 20
}
},
{
"Fn::If": [
"IsChunkingStrategyNoChunking",
{
"ChunkingStrategy": "NONE"
},
{
"Ref": "AWS::NoValue"
}
]
}
]
}
]
}
}
}
}
},
"Outputs": {
"KBId": {
"Value": {
"Ref": "KnowledgeBase"
},
"Description": "KnowledgeBase ID"
},
"DS": {
"Value": {
"Ref": "KnowledgeBaseDataSource"
},
"Description": "KnowledgeBase Datasource"
}
}
}
```
------
# 有關房屋貸款處理流程的詳細資訊
中抵押貸款處理流程的視覺化呈現 AWS 管理主控台 方式如下：
![\[房屋貸款處理流程\]](http://docs.aws.amazon.com/zh_tw/bedrock/latest/userguide/images/cloudformation/mortgage-processing-flow.png)
## 流程中的步驟
流程中會發生下列步驟：
1. 來自輸入的客戶財務資訊會傳送至 `loanCalculator` Lambda 函式，以計算客戶可負擔的最高貸款。
1. 來自 `loanCalculator` 函數的輸出 (`maximumAffordableLoan`) 和來自輸入的 `loanAmount` 值會傳送至條件節點，然後評估如下：
+ 如果 `loanAmount` 大於 `maximumAffordableLoan`，則會觸發 `incomeDebt` 提示，並產生貸款的拒絕函。
+ 否則，`processApplication` 提示會將客戶的財務資訊傳送至 `mortgageProcessingAgent`。代理程式會套用貸款計算器函數，以及多重刊登服務 (MLS) 查詢函數，以查詢 DynamoDB 資料表，並評估客戶與輸入中所指定 MLS 屬性相關的資訊。此外，代理程式會從知識庫查詢資訊，其中包含 Fannie Mae 銷售指南。代理程式會使用所有此資訊來產生回應，分析客戶申請貸款金額的資格。