Merge pull request #271 from APIParkLab/feature/1.6-liujian

update tongyi,bedrock define

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -45,19 +45,18 @@ body:
           label: Steps to Reproduce
           description: Share the steps you took so that we can reproduce the issue. Reports without proper steps details will likely be closed.
           placeholder: |
-              1. Run apinto via the Docker image.
-              2. Create a Route with the Admin API.
-              3. Try configuring ...
-              4. ...
+              1. Run APIPark via the Docker image.
+              2. Try configuring ...
+              3. ...
       validations:
-          required: true
+          required: false
     - type: textarea
       id: environment
       attributes:
           label: Environment
           description: Share your environment details. Reports without proper environment details will likely be closed.
           value: |
-              - APINTO Dashboard version (run `apinto dashboard version`):
+              - ApiPark version:
               - Operating system (run `uname -a`):
       validations:
           required: true

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -1,5 +1,5 @@
 name: "Feature Request"
-description: Suggest an enhancement to APINTO.
+description: Suggest an enhancement to APIPark.
 title: "feat: As a user, I want to ..., so that ..."
 body:
   - type: markdown
@@ -20,4 +20,4 @@ body:
       placeholder: |
         As a user, I want to ..., so that...
     validations:
-      required: true
+      required: true

.github/ISSUE_TEMPLATE/request_help.yml

@@ -25,7 +25,7 @@ body:
       label: Environment
       description: Share your environment details. Reports without proper environment details will likely be closed.
       value: |
-        - APIPark version (run `apinto dashboard version`):
+        - APIPark version:
         - Operating system (run `uname -a`):
     validations:
       required: true

.github/workflows/release.yaml

@@ -25,7 +25,7 @@ jobs:
           echo "Build frontend..."
           cd ./frontend && pnpm run build
       - name: upload frontend release
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
         with:
           name: frontend-package
           path: frontend/dist
@@ -41,7 +41,7 @@ jobs:
       - name: Checkout  #Checkout代码
         uses: actions/checkout@v3
       - name: download frontend release
-        uses: actions/download-artifact@v2
+        uses: actions/download-artifact@v4
         with:
           name: frontend-package
           path: frontend/dist
@@ -71,7 +71,7 @@ jobs:
       - uses: actions/checkout@v3
 
       - name: download frontend release
-        uses: actions/download-artifact@v2
+        uses: actions/download-artifact@v4
         with:
           name: frontend-package
           path: frontend/dist

.gitignore

@@ -3,4 +3,8 @@
 /config.yml
 /build/
 /apipark
-/aoplatform
+.gitlab-ci.yml
+/.vscode/
+.air.toml
+/tmp/
+/work

README.md

@@ -1,29 +1,55 @@
-![image]( https://github.com/user-attachments/assets/96e36db5-2733-49c8-8e1e-ecbcc60a3943 )
+![image](https://github.com/user-attachments/assets/96e36db5-2733-49c8-8e1e-ecbcc60a3943)
 
 <p align="center">
-  English
+  <a href="/README.md">English</a>
+  | 
+  <a href="/readme/readme-jp.md">日本語</a>
   | 
   <a href="/readme/readme-zh-cn.md">简体中文</a>
+  | 
+  <a href="/readme/readme-zh-tw.md">繁體中文</a>
 </p>
 
-APIPark is the world's first open-source enterprise API open platform, helping organizations quickly build internal API portals/marketplaces and enjoy ultimate forwarding performance, API observability, service governance, multi tenant management, subscription approval processes, and many other benefits.
+<b>🦄 APIPark is an open-source, all-in-one AI gateway and API developer portal, helping developers and enterprises easily manage, integrate, and deploy AI services. APIPark is open-sourced under the Apache 2.0 license, which means it's free for commercial use!</b>
 
 <br>
 
-# ✨  Quick Start
-APIPark is committed to providing one-stop API open and access products for global enterprises, and creating a new generation of API asset governance standards. APIPark is open sourced using the Apache 2.0 protocol.
+✨ With APIPark, you can:
+1. Quickly connect to 100+ AI models, supporting all mainstream AI Companies!
+2. Combine AI models and prompt templates into APIs, such as creating a sentiment analysis API, translation API, or data analysis API based on OpenAI GPT-4 and some custom prompts.
+3. Standardize the data format of all AI API requests, so switching AI models or modifying prompts won’t affect your APP or microservices, simplifying your AI usage and maintenance costs.
+4. Share APIs within the team through APIPark's developer portal.
+5. Manage calling applications and API keys to ensure your API's security and stability.
+6. Monitor your AI API usage with clear charts.
+7. Quickly export API request logs to third-party logging platforms.
 
-APIPark is committed to addressing several key challenges that enterprises face in API management:
-- Complex API call relationships: Simplifies API interactions in complex system architectures.
-- Data usage tracking: Provides comprehensive API usage monitoring and reporting.
-- Compliance management: Ensure that APIs comply with organizational and regulatory standards.
-- Fault detection and troubleshooting: Simplify the identification and resolution of system issues.
-- Quantifying the Value of Data Assets: Enhancing the Visibility and Valuation of Data Assets.
+<br>
+
+✨ APIPark is also a powerful cloud-native API gateway:
+1. It outperforms Nginx with higher performance, supports cluster deployment, and handles large-scale traffic.
+2. Share REST APIs within the team, manage API call relationships, and prevent management costs and data breaches caused by chaotic API calls.
 
 
 <br>
 
-😍 APIPark deployment is very simple, just one command line can deploy your API open platform in 5 minutes.
+# 💌 Why Did We Build APIPark?
+Before building APIPark, we spent seven years developing an API development and automated testing platform with over 1 million developer users, 500+ enterprise customers, and multi-million-dollar investment from Sequoia Capital.
+
+As AI and Agents evolved, we noticed many enterprises wanted to integrate AI into both internal and third-party APIs, enabling AI agents to perform more complex tasks beyond being just knowledge-based Q&A bots. Hence, we built APIPark—your all-in-one AI gateway and API developer portal to accelerate your AI API development and quickly build your product or AI agent!
+
+<br>
+
+# ✨ Quick Start
+APIPark is designed to solve the following problems:
+- Seamlessly connect to various AI models and package these AI capabilities into APIs for easy calling, significantly reducing the barrier to using AI models.
+- Manage complex AI & API call relationships.
+- Manage API creation, monitoring, and security.
+- Fault detection and troubleshooting: Simplifying system issue identification and resolution.
+- Quantify data asset value: Enhance the visibility and valuation of data assets.
+
+<br>
+
+😍 Deploying APIPark is incredibly simple. With just one command line, you can deploy your AI gateway and API developer portal in under 5 minutes.
 
 ```
 curl -sSO  https://download.apipark.com/install/quick-start.sh ;  bash quick-start.sh
@@ -31,131 +57,161 @@ curl -sSO  https://download.apipark.com/install/quick-start.sh ;  bash quick-sta
 
 <br>
 
-# 🔥  characteristic
+# 🔥 Features
 <table>
-<tr>
-<th>
-Centralize management and display of all API services within the enterprise
-</th>
-<th>
-Covering the entire process of API design, release, operation, and deployment
-</th>
+  <tr>
+    <th>
+      Connect to 100+ AI models
+    </th>
+    <th>
+      Unified API to use all AI
+    </th>
 
-</tr>
+  </tr>
 
-<tr>
-<td width="50%">
-<img src="https://apipark.com/wp-content/uploads/2024/08/%E9%A1%B5%E9%9D%A2-1.png" />
-API Service Square is one of the core functions of APIPark, aimed at solving the problem of scattered and chaotic management of APIs within enterprises. Through API Service Square, enterprises can display all API services on a unified platform, making it easy for different departments and teams to find and use the required API services.
-</td>
-<td width="50%">
-<img src="https://apipark.com/wp-content/uploads/2024/08/Life-Cycle.png" />
-The API lifecycle management function helps enterprises standardize the API management process, manage API traffic forwarding and load balancing, and manage all API versions released to the public. Improve the quality and maintainability of APIs. Through this feature, enterprises can achieve efficient API development and stable operation, thereby supporting rapid business development and innovation.
-</td>
-</tr>
+  <tr>
+    <td width="50%">
+        <img src="https://apipark.com/wp-content/uploads/2024/10/AI-Gateway.png" />
+    </td>
+    <td width="50%">
+        <img src="https://apipark.com/wp-content/uploads/2024/10/Unified-API.png" />
+    </td>
+  </tr>
+
+  <tr>
+    <th>
+      Transform AI & Prompt to REST API
+    </th>
+    <th>
+      API Developer Portal
+    </th>
+
+  </tr>
+
+  <tr>
+    <td width="50%">
+        <img src="https://apipark.com/wp-content/uploads/2024/10/Prompt-template.png" />
+    </td>
+    <td width="50%">
+        <img src="https://apipark.com/wp-content/uploads/2024/10/developer-portal.png" />
+    </td>
+  </tr>
+
+  <tr>
+    <th>
+      High Performance
+    </th>
+    <th>
+      Manage API lifecycle
+    </th>
+
+  </tr>
+
+  <tr>
+    <td width="50%">
+        <img src="https://apipark.com/wp-content/uploads/2024/10/hyper-performance.png" />
+    </td>
+    <td width="50%">
+        <img src="https://apipark.com/wp-content/uploads/2024/08/Life-Cycle.png" />
+    </td>
+  </tr>
   
-<tr>
-<th>
-Manage multiple tenants to ensure data isolation and security
-</th>
-<th>
-API resources need to be applied for and approved before they can be called
-</th>
+  <tr>
+    <th>
+      Review subscription before allowing API requests
+    </th>
+    <th>
+      Manage subscriber
+    </th>
+  </tr>
 
-</tr>
+  <tr>
+    <td width="50%">
+            <img src="https://apipark.com/wp-content/uploads/2024/08/Application.png" />
+    </td>
+    <td width="50%">
+        <img src="https://apipark.com/wp-content/uploads/2024/08/Multi-tenant.png" />
+    </td>
+  </tr>
 
-<tr>
-<td width="50%">
-<img src="https://apipark.com/wp-content/uploads/2024/08/Multi-tenant.png" />
-The multi tenant management function provides enterprises with the ability to manage multiple tenants on the same platform. Each tenant can have independent resource, user, and permission settings, ensuring the isolation of data and operations, and helping to improve resource utilization efficiency and management convenience.
-</td>
-<td width="50%">
-<img src="https://apipark.com/wp-content/uploads/2024/08/Application.png" />
-APIPark provides a process approval function for all API resources to avoid violating regulations or bypassing the platform to call APIs. The caller needs to first apply for API resources and wait for the service provider's approval before officially calling the API.
-</td>
-</tr>
+  <tr>
+    <th>
+      Logging
+    </th>
+    <th>
+      Analysis
+    </th>
+  </tr>
 
-<tr>
-<th>
-Assist in troubleshooting API access at any given time through detailed call logs
-</th>
-<th>
-Rich statistical reports*
-</th>
-
-</tr>
-
-<tr>
-<td width="50%">
-<img src="https://apipark.com/wp-content/uploads/2024/08/Chart-1.png" />
-The API call log function provides comprehensive logging capabilities for enterprises, detailing all relevant information of each API call. Through these logs, enterprises can quickly track and troubleshoot issues in API calls, ensuring stable system operation and data security.
-</td>
-<td width="50%">
-<img src="https://apipark.com/wp-content/uploads/2024/08/Chart.png" />
-By analyzing historical call data, APIPark can display the long-term call trends and performance changes of APIs, helping enterprises to conduct preventive maintenance before problems occur.
-</td>
-</tr>
+  <tr>
+    <td width="50%">
+        <img src="https://apipark.com/wp-content/uploads/2024/08/Chart-1.png" />
+    </td>
+    <td width="50%">
+            <img src="https://apipark.com/wp-content/uploads/2024/08/Chart.png" />
+    </td>
+  </tr>
   
 </table>
 
+<br>
+
+# 🚀 Use Cases
+## Simplify AI Integration Costs
+  - Connect to 100+ major models from all mainstream AI vendors, with standardized API calls requiring no additional adaptation work.
+  - Combine AI models and prompt templates to create new AI APIs, simplifying AI API development.
+  - Quickly share AI APIs within the team.
+
+## Enhance Operational Efficiency
+  - Quickly build an internal API developer portal.
+  - Efficiently manage and call APIs.
+  - Reduce complex system call relationships.
+
+## Ensure Compliance and Security
+  - Powerful service governance and compliance management features.
+  - Granular permission management for application calls.
+  - Ensure API call security and compliance, reducing enterprise risk.
+
+## Simplify System Troubleshooting
+  - Use monitoring and diagnostic tools to quickly identify and resolve issues.
+  - Reduce downtime and improve system stability.
+
+## Multi-Tenant Management and Flexible Subscription
+  - Supports multi-tenant management to meet different business unit needs.
+  - Flexible subscription and approval processes simplify API usage and management.
+
+## Improve API Observability
+  - Real-time monitoring and tracking of API usage.
+  - Fully understand data flow to enhance data usage transparency.
 
 <br>
 
-# 🚩 Applicable scenarios
-## Improve operational efficiency
-- Quickly build an internal API portal.
-- Efficient management and API calling.
-- Reduce complex inter system call relationships.
+# 🚩 Roadmap
+We’ve set exciting goals for APIPark: enabling everyone to quickly create their own products and AI agents using AI and APIs!
 
-## Ensure compliance and safety
-- Powerful service governance and compliance management capabilities.
-- Refine the management of application call permissions.
-- Ensure the security and compliance of API calls to reduce enterprise risks.
-
-## Simplify system troubleshooting
-- Utilize monitoring and fault diagnosis tools to quickly identify and solve problems.
-- Reduce downtime and improve system stability.
-
-## Multi tenant management and flexible subscriptions
-- Support multi tenant management to meet the needs of different business units.
-- Flexible subscription and approval processes simplify the use and management of APIs.
-
-## Enhance API observability
-- Real time monitoring and tracking of API usage.
-- Fully grasp the flow of data and enhance the transparency of data usage.
-
-## Enhance the value of data assets
-- Quantify and analyze API usage to better evaluate and enhance the value of data assets.
-- Provide data support for decision-making.
+To achieve this goal, we plan to add new features to APIPark, including:
+1. Integrating with API marketplaces such as Postman, RapidAPI, APISpace, APILayer, etc. You can directly use APIs from various API marketplaces through APIPark and make them smarter using AI.
+2. Integrating AI Agents such as Langchain, AgentGPT, Auto-GPT, Dify, and more, allowing AI Agents to access your internal or third-party APIs through APIPark to complete more complex tasks.
+3. Intelligent API orchestration: APIPark will provide a unified API entry point and automatically orchestrate multiple APIs to fulfill your requests based on the API content.
 
 <br>
 
-# 🚀 One click deployment
-APIPark deployment is very simple, just one command line can deploy your API asset open platform in 5 minutes.
-
-```
-curl -sSO  https://download.apipark.com/install/quick-start.sh ;  bash quick-start.sh
-```
+# 📕 Documentation
+Visit [APIPark Documentation](https://docs.apipark.com/docs/deploy) for detailed installation guides, API references, and usage instructions.
 
 <br>
 
-## 📕 file
-Visit [APIPark Document]（ https://docs.apipark.com/docs/install ）Get detailed installation guides, API references, and usage instructions.
+# 🧾 License
+APIPark uses the Apache 2.0 License. For more details, please refer to the LICENSE file.
 
 <br>
 
-## 🧾 licence
-APIPark uses the Apache 2.0 license. For more details, please refer to the LICENSE document.
-
-
-<br>
-
-## 💌 contact us
-For enterprise level functionality and professional technical support, please contact pre-sales experts for personalized demonstrations, customized solutions, and pricing.
+# 💌 Contact Us
+For enterprise-level features and professional technical support, contact our pre-sales experts for personalized demos, customized solutions, and pricing.
 
 - Website: https://apipark.com
-- Email: dev@apipark.com
+- Email: contact@apipark.com
 
 <br>
 
-Thank you for choosing APIPark, the next-generation API Open platform.
+🙏 A big thanks to everyone who helped shape APIPark. We are thrilled to hear the community’s thoughts! Let’s make the world of APIs and AI stronger and more fun together. 🎉

ai-provider/local/entity.go

@@ -0,0 +1,22 @@
+package ai_provider_local
+
+import "time"
+
+type Model struct {
+	Name       string       `json:"name"`
+	Model      string       `json:"model"`
+	ModifiedAt time.Time    `json:"modified_at"`
+	Size       int64        `json:"size"`
+	Digest     string       `json:"digest"`
+	Details    ModelDetails `json:"details,omitempty"`
+}
+
+// ModelDetails provides details about a model.
+type ModelDetails struct {
+	ParentModel       string   `json:"parent_model"`
+	Format            string   `json:"format"`
+	Family            string   `json:"family"`
+	Families          []string `json:"families"`
+	ParameterSize     string   `json:"parameter_size"`
+	QuantizationLevel string   `json:"quantization_level"`
+}

ai-provider/local/executor.go

@@ -0,0 +1,336 @@
+package ai_provider_local
+
+import (
+	"context"
+	"fmt"
+	"sync"
+
+	"github.com/ollama/ollama/progress"
+
+	"github.com/eolinker/eosc"
+	"github.com/ollama/ollama/api"
+)
+
+var (
+	taskExecutor = NewAsyncExecutor(100)
+)
+
+// Pipeline 结构体，表示每个用户的管道
+type Pipeline struct {
+	id      string
+	channel chan PullMessage
+	ctx     context.Context
+	cancel  context.CancelFunc
+}
+
+func (p *Pipeline) Message() <-chan PullMessage {
+	return p.channel
+}
+
+// AsyncExecutor 结构体，管理不同模型的管道和任务队列
+type AsyncExecutor struct {
+	ctx       context.Context
+	cancel    context.CancelFunc
+	mu        sync.Mutex
+	pipelines map[string]*modelPipeline // 以模型为 key，存管道列表
+	msgQueue  chan messageTask          // 消息队列
+}
+
+type modelPipeline struct {
+	ctx       context.Context
+	cancel    context.CancelFunc
+	pipelines eosc.Untyped[string, *Pipeline]
+	pullFn    PullCallback
+	maxSize   int
+}
+
+func (m *modelPipeline) List() []*Pipeline {
+	return m.pipelines.List()
+}
+
+func (m *modelPipeline) Get(id string) (*Pipeline, bool) {
+	return m.pipelines.Get(id)
+}
+
+func (m *modelPipeline) Set(id string, p *Pipeline) error {
+	_, ok := m.pipelines.Get(id)
+	if !ok {
+		if m.pipelines.Count() > m.maxSize {
+			return fmt.Errorf("pipeline size exceed %d", m.maxSize)
+		}
+	}
+	m.pipelines.Set(id, p)
+	return nil
+}
+
+func (m *modelPipeline) AddPipeline(id string) (*Pipeline, error) {
+	ctx, cancel := context.WithCancel(m.ctx)
+	pipeline := &Pipeline{
+		ctx:     ctx,
+		cancel:  cancel,
+		id:      id,
+		channel: make(chan PullMessage, 10), // 带缓冲，防止阻塞
+	}
+	err := m.Set(id, pipeline)
+	if err != nil {
+		return nil, err
+	}
+	return pipeline, nil
+}
+
+func (m *modelPipeline) Close() {
+	m.cancel()
+	ids := m.pipelines.Keys()
+	for _, id := range ids {
+		m.ClosePipeline(id)
+	}
+	return
+}
+
+func (m *modelPipeline) ClosePipeline(id string) {
+	// 关闭管道
+	p, has := m.pipelines.Del(id)
+	if !has {
+		return
+	}
+	p.cancel()
+	close(p.channel)
+}
+
+func newModelPipeline(ctx context.Context, maxSize int) *modelPipeline {
+	ctx, cancel := context.WithCancel(ctx)
+	return &modelPipeline{
+		pipelines: eosc.BuildUntyped[string, *Pipeline](),
+		ctx:       ctx,
+		cancel:    cancel,
+		maxSize:   maxSize,
+	}
+}
+
+// messageTask 结构体，包含模型名和消息内容
+type messageTask struct {
+	message PullMessage
+}
+
+type PullMessage struct {
+	Model     string
+	Status    string
+	Digest    string
+	Total     int64
+	Completed int64
+	Msg       string
+}
+
+// NewAsyncExecutor 创建一个新的异步任务执行器
+func NewAsyncExecutor(queueSize int) *AsyncExecutor {
+	ctx, cancel := context.WithCancel(context.Background())
+	executor := &AsyncExecutor{
+		ctx:       ctx,
+		cancel:    cancel,
+		pipelines: make(map[string]*modelPipeline), // 以模型为 key，存管道列表
+		msgQueue:  make(chan messageTask, queueSize),
+	}
+	executor.StartMessageDistributor()
+
+	return executor
+}
+
+func (e *AsyncExecutor) GetModelPipeline(model string) (*modelPipeline, bool) {
+	e.mu.Lock()
+	defer e.mu.Unlock()
+
+	mp, ok := e.pipelines[model]
+	return mp, ok
+}
+
+func (e *AsyncExecutor) SetModelPipeline(model string, mp *modelPipeline) {
+	e.mu.Lock()
+	defer e.mu.Unlock()
+	e.pipelines[model] = mp
+}
+
+// ClosePipeline 关闭管道并移除
+func (e *AsyncExecutor) ClosePipeline(model string, id string) {
+	e.mu.Lock()
+	defer e.mu.Unlock()
+	mp, ok := e.pipelines[model]
+	if !ok {
+		return
+	}
+	mp.ClosePipeline(id)
+}
+
+// CloseModelPipeline 关闭当前模型所有管道
+func (e *AsyncExecutor) CloseModelPipeline(model string) {
+	e.mu.Lock()
+	defer e.mu.Unlock()
+	mp, ok := e.pipelines[model]
+	if !ok {
+		return
+	}
+	mp.Close()
+	delete(e.pipelines, model)
+}
+
+// StartMessageDistributor 启动消息分发器
+func (e *AsyncExecutor) StartMessageDistributor() {
+	go func() {
+		for task := range e.msgQueue {
+			msg := task.message
+			e.DistributeToModelPipelines(msg.Model, msg)
+			if msg.Status == "error" || msg.Status == "success" {
+				mp, has := e.GetModelPipeline(msg.Model)
+				if has && mp.pullFn != nil {
+					mp.pullFn(msg)
+				}
+				e.CloseModelPipeline(msg.Model)
+				continue
+			}
+		}
+	}()
+}
+
+// DistributeToModelPipelines 仅将消息分发给指定模型的管道
+func (e *AsyncExecutor) DistributeToModelPipelines(model string, msg PullMessage) {
+	e.mu.Lock()
+	defer e.mu.Unlock()
+	pipelines, ok := e.pipelines[model]
+	if !ok {
+		return
+	}
+	for _, pipeline := range pipelines.List() {
+		select {
+		case pipeline.channel <- msg:
+		default:
+			// 如果管道已满，跳过
+		}
+	}
+}
+
+type PullCallback func(msg PullMessage) error
+
+func PullModel(model string, id string, fn PullCallback) (*Pipeline, error) {
+	if client == nil {
+		return nil, fmt.Errorf("client not initialized")
+	}
+	mp, has := taskExecutor.GetModelPipeline(model)
+	if !has {
+		mp = newModelPipeline(taskExecutor.ctx, 100)
+		mp.pullFn = fn
+		taskExecutor.SetModelPipeline(model, mp)
+	}
+	p, err := mp.AddPipeline(id)
+	if err != nil {
+		return nil, err
+	}
+	if !has {
+		var status string
+		bars := make(map[string]*progress.Bar)
+		fn := func(resp api.ProgressResponse) error {
+			if resp.Digest != "" {
+				bar, ok := bars[resp.Digest]
+				if !ok {
+					bar = progress.NewBar(fmt.Sprintf("pulling %s...", resp.Digest[7:19]), resp.Total, resp.Completed)
+					bars[resp.Digest] = bar
+				}
+				bar.Set(resp.Completed)
+
+				taskExecutor.msgQueue <- messageTask{
+					message: PullMessage{
+						Model:     model,
+						Digest:    resp.Digest,
+						Total:     resp.Total,
+						Completed: resp.Completed,
+						Msg:       bar.String(),
+						Status:    resp.Status,
+					},
+				}
+			} else if status != resp.Status {
+				taskExecutor.msgQueue <- messageTask{
+					message: PullMessage{
+						Model:     model,
+						Digest:    resp.Digest,
+						Total:     resp.Total,
+						Completed: resp.Completed,
+						Msg:       status,
+						Status:    resp.Status,
+					},
+				}
+			}
+
+			return nil
+		}
+		go func() {
+			err = client.Pull(mp.ctx, &api.PullRequest{Model: model}, fn)
+			if err != nil {
+				taskExecutor.msgQueue <- messageTask{
+					message: PullMessage{
+						Model:     model,
+						Status:    "error",
+						Digest:    "",
+						Total:     0,
+						Completed: 0,
+						Msg:       err.Error(),
+					},
+				}
+			}
+		}()
+
+	}
+
+	return p, nil
+}
+
+func StopPull(model string) {
+	if client == nil {
+		return
+	}
+	taskExecutor.CloseModelPipeline(model)
+}
+
+func CancelPipeline(model string, id string) {
+	taskExecutor.ClosePipeline(model, id)
+}
+
+func RemoveModel(model string) error {
+	if client == nil {
+		return fmt.Errorf("client not initialized")
+	}
+	taskExecutor.CloseModelPipeline(model)
+	err := client.Delete(context.Background(), &api.DeleteRequest{Model: model})
+	if err != nil {
+		if err.Error() == fmt.Sprintf("model '%s' not found", model) {
+			return nil
+		}
+	}
+	return err
+}
+
+func ModelsInstalled() ([]Model, error) {
+	if client == nil {
+		return nil, fmt.Errorf("client not initialized")
+	}
+	result, err := client.List(context.Background())
+	if err != nil {
+		return nil, err
+	}
+	models := make([]Model, 0, len(result.Models))
+	for _, m := range result.Models {
+		models = append(models, Model{
+			Name:       m.Name,
+			Model:      m.Model,
+			ModifiedAt: m.ModifiedAt,
+			Size:       m.Size,
+			Digest:     m.Digest,
+			Details: ModelDetails{
+				ParentModel:       m.Details.ParentModel,
+				Format:            m.Details.Format,
+				Family:            m.Details.Family,
+				Families:          m.Details.Families,
+				ParameterSize:     m.Details.ParameterSize,
+				QuantizationLevel: m.Details.QuantizationLevel,
+			},
+		})
+	}
+	return models, nil
+}

ai-provider/local/executor_test.go

@@ -0,0 +1,80 @@
+package ai_provider_local
+
+import (
+	"fmt"
+	"io"
+	"net/http"
+	"testing"
+
+	"github.com/gin-contrib/gzip"
+
+	"github.com/eolinker/eosc/log"
+
+	"github.com/google/uuid"
+
+	"github.com/gin-gonic/gin"
+)
+
+func TestPullModel(t *testing.T) {
+	// 创建 Gin 引擎
+	r := gin.Default()
+	r.Use(gzip.Gzip(gzip.DefaultCompression))
+	// 设置路由，监听 "/stream" 路径
+	r.GET("/stream", streamHandler)
+	r.GET("/stop", stopPull)
+	r.GET("/models", models)
+
+	// 启动 HTTP 服务器
+	r.Run(":11180")
+}
+
+func streamHandler(c *gin.Context) {
+	// 创建一个通道，用于监测客户端关闭连接的信号
+	model := c.Query("model")
+	p, err := PullModel(model, uuid.NewString(), nil)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	done := make(chan struct{})
+	// 启动一个 goroutine 监听客户端关闭连接
+	go func() {
+		select {
+		case <-c.Writer.CloseNotify():
+			log.Info("client closed connection,close pipeline")
+			taskExecutor.ClosePipeline(model, p.id)
+		case <-done:
+		}
+	}()
+
+	c.Stream(func(w io.Writer) bool {
+		select {
+		case msg, ok := <-p.channel:
+			if !ok {
+				return false
+			}
+			_, err := w.Write([]byte(fmt.Sprintf("%s\n", msg.Msg)))
+			if err != nil {
+				log.Error("write message error: %v", err)
+				return false
+			}
+			return true
+		}
+	})
+	done <- struct{}{}
+}
+
+func stopPull(c *gin.Context) {
+	model := c.Query("model")
+	StopPull(model)
+	c.JSON(http.StatusOK, gin.H{"message": "stop pull model"})
+}
+
+func models(c *gin.Context) {
+	ms, err := ModelsInstalled()
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{"models": ms})
+}

ai-provider/local/local.go

@@ -0,0 +1,31 @@
+package ai_provider_local
+
+import (
+	"net/http"
+	"net/url"
+
+	"github.com/ollama/ollama/api"
+)
+
+var (
+	client        *api.Client
+	ProviderLocal = "LocalModel"
+)
+
+func ResetLocalAddress(address string) error {
+	u, err := url.Parse(address)
+	if err != nil {
+		return err
+	}
+	client = api.NewClient(u, http.DefaultClient)
+	return nil
+}
+
+var (
+	LocalConfig = "{\n  \"temperature\": \"\",\n  \"top_p\": \"\",\n  \"max_tokens\": \"\"\n}"
+	LocalSvg    = `<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="50" height="50" viewBox="0 0 50 50">
+    <image id="椭圆_1_拷贝" data-name="椭圆 1 拷贝" x="5" y="4" width="42" height="38" xlink:href="data:img/png;base64,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"/>
+</svg>
+
+`
+)

ai-provider/local/model.go

@@ -0,0 +1,70 @@
+package ai_provider_local
+
+import (
+	"embed"
+	"encoding/json"
+	"strings"
+
+	"github.com/eolinker/eosc/log"
+)
+
+var (
+	//go:embed models.json
+	modelsFs        embed.FS
+	modelCanInstall []ModelDetail
+	modelVersion    string
+	modelTags       = make(map[string][]ModelDetail)
+)
+
+type ModelConfig struct {
+	Models  []ModelDetail `json:"models"`
+	Version string        `json:"version"`
+}
+
+type ModelDetail struct {
+	Id          string `json:"id"`
+	Name        string `json:"name"`
+	Description string `json:"description"`
+	Size        string `json:"size"`
+	Digest      string `json:"digest"`
+	Provider    string `json:"provider"`
+	IsPopular   bool   `json:"is_popular"`
+	Latest      bool   `json:"latest"`
+}
+
+func init() {
+	data, err := modelsFs.ReadFile("models.json")
+	if err != nil {
+		log.Info("read models.json error: ", err)
+		return
+	}
+	var cfg ModelConfig
+	err = json.Unmarshal(data, &cfg)
+	if err != nil {
+		log.Info("unmarshal models.json error: ", err)
+		return
+	}
+	modelVersion = cfg.Version
+	modelCanInstall = make([]ModelDetail, 0, len(cfg.Models))
+	for _, model := range cfg.Models {
+		if _, ok := modelTags[model.Id]; !ok {
+			modelTags[model.Id] = make([]ModelDetail, 0)
+		}
+		names := strings.Split(model.Id, ":")
+
+		modelTags[names[0]] = append(modelTags[names[0]], model)
+		if !model.Latest {
+			continue
+		}
+		modelCanInstall = append(modelCanInstall, model)
+	}
+
+}
+
+func ModelsCanInstall() ([]ModelDetail, string) {
+	return modelCanInstall, modelVersion
+}
+
+func ModelsCanInstallById(id string) []ModelDetail {
+	return modelTags[id]
+}

ai-provider/local/model_test.go

@@ -0,0 +1,7 @@
+package ai_provider_local
+
+import "testing"
+
+func TestModels(t *testing.T) {
+	t.Log(ModelsCanInstall())
+}

ai-provider/model-runtime/entity/ai-model.go

@@ -0,0 +1,21 @@
+package entity
+
+type AIModel struct {
+	Model           string            `json:"model" yaml:"model"`
+	Label           map[string]string `json:"label" yaml:"label"`
+	ModelType       string            `json:"model_type" yaml:"model_type"`
+	Features        []string          `json:"features" yaml:"features"`
+	ModelProperties map[string]string `json:"model_properties" yaml:"model_properties"`
+	ParameterRules  []ParameterRule   `json:"parameter_rules" yaml:"parameter_rules"`
+}
+
+type ParameterRule struct {
+	Name      string            `json:"name" yaml:"name"`
+	Default   interface{}       `json:"default" yaml:"default"`
+	Label     map[string]string `json:"label" yaml:"label"`
+	Type      string            `json:"type" yaml:"type"`
+	Min       float64           `json:"min" yaml:"min"`
+	Max       float64           `json:"max" yaml:"max"`
+	Precision int               `json:"precision" yaml:"precision"`
+	Required  bool              `json:"required" yaml:"required"`
+}

ai-provider/model-runtime/entity/provider.go

@@ -0,0 +1,50 @@
+package entity
+
+var (
+	ModelTypeLLM           = "llm"
+	ModelTypeTextEmbedding = "text-embedding"
+	ModelTypeSpeech2Text   = "speech2text"
+	ModelTypeTTS           = "tts"
+	ModelTypeModeration    = "moderation"
+
+	LanguageEnglish = "en_US"
+	LanguageChinese = "zh_Hans"
+)
+
+type Provider struct {
+	Provider                 string                   `json:"provider" yaml:"provider"`
+	Label                    map[string]string        `json:"label" yaml:"label"`
+	Description              map[string]string        `json:"description" yaml:"description"`
+	IconSmall                map[string]string        `json:"icon_small" yaml:"icon_small"`
+	IconLarge                map[string]string        `json:"icon_large" yaml:"icon_large"`
+	Background               string                   `json:"background" yaml:"background"`
+	Help                     Help                     `json:"help" yaml:"help"`
+	SupportedModelTypes      []string                 `json:"supported_model_types" yaml:"supported_model_types"`
+	ProviderCredentialSchema ProviderCredentialSchema `json:"provider_credential_schema" yaml:"provider_credential_schema"`
+	Default                  map[string]string        `json:"default" yaml:"default"`
+	Address                  string                   `json:"address" yaml:"address"`
+	Recommend                bool                     `json:"recommend" yaml:"recommend"`
+	Sort                     int                      `json:"sort" yaml:"sort"`
+	ModelConfig              ModelConfig              `json:"model_config" yaml:"model_config"`
+}
+type ModelConfig struct {
+	AccessConfigurationStatus bool   `json:"access_configuration_status" yaml:"access_configuration_status"`
+	AccessConfigurationDemo   string `json:"access_configuration_demo" yaml:"access_configuration_demo"`
+}
+
+type ProviderCredentialSchema struct {
+	CredentialFormSchemas []CredentialFormSchema `json:"credential_form_schemas" yaml:"credential_form_schemas"`
+}
+
+type CredentialFormSchema struct {
+	Variable    string            `json:"variable" yaml:"variable"`
+	Label       map[string]string `json:"label" yaml:"label"`
+	Type        string            `json:"type" yaml:"type"`
+	Required    bool              `json:"required" yaml:"required"`
+	Placeholder map[string]string `json:"placeholder" yaml:"placeholder"`
+}
+
+type Help struct {
+	Title map[string]string `json:"title" yaml:"title"`
+	URL   map[string]string `json:"url" yaml:"url"`
+}

ai-provider/model-runtime/load_test.go

@@ -0,0 +1,11 @@
+package model_runtime
+
+import "testing"
+
+func TestLoad(t *testing.T) {
+	Load()
+	for _, p := range Providers() {
+		t.Logf("Provider: %s", p.ID())
+		t.Log(p.DefaultModel("llm"))
+	}
+}

ai-provider/model-runtime/loader.go

@@ -0,0 +1,159 @@
+package model_runtime
+
+import (
+	"embed"
+	"encoding/json"
+	"fmt"
+	"strings"
+
+	"github.com/eolinker/eosc"
+)
+
+func init() {
+	Load()
+}
+
+type IConfig interface {
+	Check(cfg string) error
+	GenConfig(target string, origin string) (string, error)
+	DefaultConfig() string
+}
+
+func NewConfig(cfg string, validator IParamValidator) *Config {
+	return &Config{cfg: cfg, validator: validator}
+}
+
+type Config struct {
+	cfg       string
+	validator IParamValidator
+}
+
+func (c *Config) Check(cfg string) error {
+	data := make(map[string]interface{})
+	err := json.Unmarshal([]byte(cfg), &data)
+	if err != nil {
+		return err
+	}
+	if c.validator != nil {
+		return c.validator.Valid(data)
+	}
+	return nil
+}
+
+func (c *Config) GenConfig(target string, origin string) (string, error) {
+	if target == "" {
+		target = "{}"
+	}
+	if origin == "" {
+		origin = "{}"
+	}
+	var targetData map[string]interface{}
+
+	err := json.Unmarshal([]byte(target), &targetData)
+	if err != nil {
+		return "", err
+	}
+	var originData map[string]interface{}
+	err = json.Unmarshal([]byte(origin), &originData)
+	if err != nil {
+		return "", err
+	}
+	if c.validator == nil {
+		c.validator = ParamValidator(nil)
+	}
+
+	return c.validator.GenConfig(targetData, originData)
+}
+
+func (c *Config) DefaultConfig() string {
+	return c.cfg
+}
+
+const (
+	DirAssets = "assets"
+)
+
+var (
+	//go:embed model-providers/*
+	providerDir embed.FS
+)
+
+func Load() error {
+	files, err := providerDir.ReadDir("model-providers")
+	if err != nil {
+		return err
+	}
+	for _, file := range files {
+		if !file.IsDir() {
+			continue
+		}
+		name := fmt.Sprintf("model-providers/%s", file.Name())
+		if file.Name() == "customize" {
+			continue
+		}
+		err = LoadProvider(name)
+		if err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+func LoadProvider(name string) error {
+	files, err := providerDir.ReadDir(name)
+	if err != nil {
+		return err
+	}
+	var providerFile string
+	models := make(map[string]eosc.Untyped[string, string])
+	for _, file := range files {
+		if file.IsDir() {
+			result, err := ReadFile(providerDir, fmt.Sprintf("%s/%s", name, file.Name()))
+			if err != nil {
+				return err
+			}
+			models[file.Name()] = result
+			continue
+		}
+		if strings.HasSuffix(file.Name(), ".yaml") {
+			data, err := providerDir.ReadFile(fmt.Sprintf("%s/%s", name, file.Name()))
+			if err != nil {
+				return err
+			}
+			providerFile = string(data)
+		}
+	}
+	provider, err := NewProvider(providerFile, models)
+	if err != nil {
+		return err
+	}
+	//gateway.RegisterDynamicResourceDriver(provider.ID(), gateway.Worker{
+	//	Profession: gateway.ProfessionAIProvider,
+	//	Driver:     provider.ID(),
+	//})
+	Register(provider.ID(), provider)
+	return nil
+}
+
+func ReadFile(dir embed.FS, name string) (eosc.Untyped[string, string], error) {
+
+	files, err := dir.ReadDir(name)
+	if err != nil {
+		return nil, err
+	}
+	result := eosc.BuildUntyped[string, string]()
+	for _, file := range files {
+		if file.IsDir() {
+			continue
+		}
+		if !strings.HasSuffix(file.Name(), ".yaml") && !strings.HasSuffix(file.Name(), ".svg") {
+			continue
+		}
+		data, err := dir.ReadFile(fmt.Sprintf("%s/%s", name, file.Name()))
+		if err != nil {
+			return nil, fmt.Errorf("open file %s error: %w", file.Name(), err)
+		}
+		result.Set(file.Name(), string(data))
+	}
+	return result, nil
+}

ai-provider/model-runtime/manager.go

@@ -0,0 +1,56 @@
+package model_runtime
+
+import (
+	"github.com/eolinker/eosc"
+)
+
+var (
+	defaultManager = NewManager()
+)
+
+type Manager struct {
+	providers eosc.Untyped[string, IProvider]
+}
+
+func NewManager() *Manager {
+	return &Manager{providers: eosc.BuildUntyped[string, IProvider]()}
+}
+
+func (m *Manager) Set(name string, driver IProvider) {
+	m.providers.Set(name, driver)
+}
+
+func (m *Manager) Get(name string) (IProvider, bool) {
+	return m.providers.Get(name)
+}
+
+func (m *Manager) Del(name string) {
+	m.providers.Del(name)
+}
+
+func (m *Manager) List() []IProvider {
+	//list := m.providers.List()
+	//sort.Slice(list, func(i, j int) bool {
+	//	if list[i].Sort() == list[j].Sort() {
+	//		return list[i].ID() < list[j].ID()
+	//	}
+	//	return list[i].Sort() < list[j].Sort()
+	//})
+	return m.providers.List()
+}
+
+func Register(name string, driver IProvider) {
+	defaultManager.Set(name, driver)
+}
+
+func Remove(name string) {
+	defaultManager.Del(name)
+}
+
+func GetProvider(name string) (IProvider, bool) {
+	return defaultManager.Get(name)
+}
+
+func Providers() []IProvider {
+	return defaultManager.List()
+}

ai-provider/model-runtime/model-providers/authropic/anthropic.yaml

@@ -0,0 +1,42 @@
+provider: anthropic
+label:
+  en_US: Anthropic
+description:
+  en_US: Anthropic’s powerful models, such as Claude 3.
+  zh_Hans: Anthropic 的强大模型，例如 Claude 3。
+icon_small:
+  en_US: icon_s_en.svg
+icon_large:
+  en_US: icon_l_en.svg
+background: "#F0F0EB"
+help:
+  title:
+    en_US: Get your API Key from Anthropic
+    zh_Hans: 从 Anthropic 获取 API Key
+  url:
+    en_US: https://console.anthropic.com/account/keys
+supported_model_types:
+  - llm
+configurate_methods:
+  - predefined-model
+provider_credential_schema:
+  credential_form_schemas:
+    - variable: anthropic_api_key
+      label:
+        en_US: API Key
+      type: secret-input
+      required: true
+      placeholder:
+        zh_Hans: 在此输入您的 API Key
+        en_US: Enter your API Key
+    - variable: anthropic_api_url
+      label:
+        en_US: https://api.anthropic.com/v1/
+      type: text-input
+      required: false
+      placeholder:
+        zh_Hans: 在此输入您的 API URL
+        en_US: Enter your API URL
+address: https://api.anthropic.com/v1/
+recommend: true
+sort: 2

ai-provider/model-runtime/model-providers/authropic/assets/icon_l_en.svg

@@ -0,0 +1,78 @@
+<svg width="90" height="20" viewBox="0 0 90 20" fill="none" xmlns="http://www.w3.org/2000/svg">
+<g clip-path="url(#clip0_8587_60274)">
+<mask id="mask0_8587_60274" style="mask-type:luminance" maskUnits="userSpaceOnUse" x="0" y="4" width="90" height="11">
+<path d="M89.375 4.99805H0V14.998H89.375V4.99805Z" fill="white"/>
+</mask>
+<g mask="url(#mask0_8587_60274)">
+<mask id="mask1_8587_60274" style="mask-type:luminance" maskUnits="userSpaceOnUse" x="0" y="4" width="90" height="11">
+<path d="M0 4.99609H89.375V14.9961H0V4.99609Z" fill="white"/>
+</mask>
+<g mask="url(#mask1_8587_60274)">
+<mask id="mask2_8587_60274" style="mask-type:luminance" maskUnits="userSpaceOnUse" x="0" y="4" width="90" height="11">
+<path d="M0 4.99414H89.375V14.9941H0V4.99414Z" fill="white"/>
+</mask>
+<g mask="url(#mask2_8587_60274)">
+<mask id="mask3_8587_60274" style="mask-type:luminance" maskUnits="userSpaceOnUse" x="0" y="4" width="90" height="11">
+<path d="M0 4.99219H89.375V14.9922H0V4.99219Z" fill="white"/>
+</mask>
+<g mask="url(#mask3_8587_60274)">
+<path d="M18.1273 11.9244L13.7773 5.15625H11.4297V14.825H13.4321V8.05688L17.7821 14.825H20.1297V5.15625H18.1273V11.9244Z" fill="black" fill-opacity="0.92"/>
+</g>
+<mask id="mask4_8587_60274" style="mask-type:luminance" maskUnits="userSpaceOnUse" x="0" y="4" width="90" height="11">
+<path d="M0 4.99219H89.375V14.9922H0V4.99219Z" fill="white"/>
+</mask>
+<g mask="url(#mask4_8587_60274)">
+<path d="M21.7969 7.02094H25.0423V14.825H27.1139V7.02094H30.3594V5.15625H21.7969V7.02094Z" fill="black" fill-opacity="0.92"/>
+</g>
+<mask id="mask5_8587_60274" style="mask-type:luminance" maskUnits="userSpaceOnUse" x="0" y="4" width="90" height="11">
+<path d="M0 4.99219H89.375V14.9922H0V4.99219Z" fill="white"/>
+</mask>
+<g mask="url(#mask5_8587_60274)">
+<path d="M38.6442 9.00994H34.0871V5.15625H32.0156V14.825H34.0871V10.8746H38.6442V14.825H40.7156V5.15625H38.6442V9.00994Z" fill="black" fill-opacity="0.92"/>
+</g>
+<mask id="mask6_8587_60274" style="mask-type:luminance" maskUnits="userSpaceOnUse" x="0" y="4" width="90" height="11">
+<path d="M0 4.99219H89.375V14.9922H0V4.99219Z" fill="white"/>
+</mask>
+<g mask="url(#mask6_8587_60274)">
+<path d="M45.3376 7.02094H47.893C48.9152 7.02094 49.4539 7.39387 49.4539 8.09831C49.4539 8.80275 48.9152 9.17569 47.893 9.17569H45.3376V7.02094ZM51.5259 8.09831C51.5259 6.27506 50.186 5.15625 47.9897 5.15625H43.2656V14.825H45.3376V11.0404H47.6443L49.7164 14.825H52.0094L49.715 10.7521C50.8666 10.3094 51.5259 9.37721 51.5259 8.09831Z" fill="black" fill-opacity="0.92"/>
+</g>
+<mask id="mask7_8587_60274" style="mask-type:luminance" maskUnits="userSpaceOnUse" x="0" y="4" width="90" height="11">
+<path d="M0 4.99219H89.375V14.9922H0V4.99219Z" fill="white"/>
+</mask>
+<g mask="url(#mask7_8587_60274)">
+<path d="M57.8732 13.0565C56.2438 13.0565 55.2496 11.8963 55.2496 10.004C55.2496 8.08416 56.2438 6.92394 57.8732 6.92394C59.4887 6.92394 60.4691 8.08416 60.4691 10.004C60.4691 11.8963 59.4887 13.0565 57.8732 13.0565ZM57.8732 4.99023C55.0839 4.99023 53.1094 7.06206 53.1094 10.004C53.1094 12.9184 55.0839 14.9902 57.8732 14.9902C60.6486 14.9902 62.6094 12.9184 62.6094 10.004C62.6094 7.06206 60.6486 4.99023 57.8732 4.99023Z" fill="black" fill-opacity="0.92"/>
+</g>
+<mask id="mask8_8587_60274" style="mask-type:luminance" maskUnits="userSpaceOnUse" x="0" y="4" width="90" height="11">
+<path d="M0 4.99219H89.375V14.9922H0V4.99219Z" fill="white"/>
+</mask>
+<g mask="url(#mask8_8587_60274)">
+<path d="M69.1794 9.45194H66.6233V7.02094H69.1794C70.2019 7.02094 70.7407 7.43532 70.7407 8.23644C70.7407 9.03756 70.2019 9.45194 69.1794 9.45194ZM69.2762 5.15625H64.5508V14.825H66.6233V11.3166H69.2762C71.473 11.3166 72.8133 10.1564 72.8133 8.23644C72.8133 6.3165 71.473 5.15625 69.2762 5.15625Z" fill="black" fill-opacity="0.92"/>
+</g>
+<mask id="mask9_8587_60274" style="mask-type:luminance" maskUnits="userSpaceOnUse" x="0" y="4" width="90" height="11">
+<path d="M0 4.99219H89.375V14.9922H0V4.99219Z" fill="white"/>
+</mask>
+<g mask="url(#mask9_8587_60274)">
+<path d="M86.8413 11.5786C86.4823 12.5179 85.7642 13.0565 84.7837 13.0565C83.1542 13.0565 82.16 11.8963 82.16 10.004C82.16 8.08416 83.1542 6.92394 84.7837 6.92394C85.7642 6.92394 86.4823 7.46261 86.8413 8.40183H89.0369C88.4984 6.33002 86.8827 4.99023 84.7837 4.99023C81.9942 4.99023 80.0195 7.06206 80.0195 10.004C80.0195 12.9184 81.9942 14.9902 84.7837 14.9902C86.8965 14.9902 88.5122 13.6366 89.0508 11.5786H86.8413Z" fill="black" fill-opacity="0.92"/>
+</g>
+<mask id="mask10_8587_60274" style="mask-type:luminance" maskUnits="userSpaceOnUse" x="0" y="4" width="90" height="11">
+<path d="M0 4.99219H89.375V14.9922H0V4.99219Z" fill="white"/>
+</mask>
+<g mask="url(#mask10_8587_60274)">
+<path d="M73.6484 5.15625L77.5033 14.825H79.6172L75.7624 5.15625H73.6484Z" fill="black" fill-opacity="0.92"/>
+</g>
+<mask id="mask11_8587_60274" style="mask-type:luminance" maskUnits="userSpaceOnUse" x="0" y="4" width="90" height="11">
+<path d="M0 4.99219H89.375V14.9922H0V4.99219Z" fill="white"/>
+</mask>
+<g mask="url(#mask11_8587_60274)">
+<path d="M3.64038 10.9989L4.95938 7.60106L6.27838 10.9989H3.64038ZM3.85422 5.15625L0 14.825H2.15505L2.9433 12.7946H6.97558L7.76371 14.825H9.91875L6.06453 5.15625H3.85422Z" fill="black" fill-opacity="0.92"/>
+</g>
+</g>
+</g>
+</g>
+</g>
+<defs>
+<clipPath id="clip0_8587_60274">
+<rect width="89.375" height="10" fill="white" transform="translate(0 5)"/>
+</clipPath>
+</defs>
+</svg>

ai-provider/model-runtime/model-providers/authropic/assets/icon_s_en.svg

@@ -0,0 +1,4 @@
+<svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg">
+<rect width="24" height="24" rx="6" fill="#CA9F7B"/>
+<path d="M15.3843 6.43481H12.9687L17.3739 17.5652H19.7896L15.3843 6.43481ZM8.40522 6.43481L4 17.5652H6.4633L7.36417 15.2279H11.9729L12.8737 17.5652H15.337L10.9318 6.43481H8.40522ZM8.16104 13.1607L9.66852 9.24907L11.176 13.1607H8.16104Z" fill="#191918"/>
+</svg>

ai-provider/model-runtime/model-providers/authropic/llm/_position.yaml

@@ -0,0 +1,8 @@
+- claude-3-5-sonnet-20240620
+- claude-3-haiku-20240307
+- claude-3-opus-20240229
+- claude-3-sonnet-20240229
+- claude-2.1
+- claude-instant-1.2
+- claude-2
+- claude-instant-1

ai-provider/model-runtime/model-providers/authropic/llm/claude-2.1.yaml

@@ -0,0 +1,36 @@
+model: claude-2.1
+label:
+  en_US: claude-2.1
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 200000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 4096
+    min: 1
+    max: 4096
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '8.00'
+  output: '24.00'
+  unit: '0.000001'
+  currency: USD

ai-provider/model-runtime/model-providers/authropic/llm/claude-2.yaml

@@ -0,0 +1,37 @@
+model: claude-2
+label:
+  en_US: claude-2
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 100000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 4096
+    min: 1
+    max: 4096
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '8.00'
+  output: '24.00'
+  unit: '0.000001'
+  currency: USD
+deprecated: true

ai-provider/model-runtime/model-providers/authropic/llm/claude-3-5-haiku-20241022.yaml

@@ -0,0 +1,38 @@
+model: claude-3-5-haiku-20241022
+label:
+  en_US: claude-3-5-haiku-20241022
+model_type: llm
+features:
+  - agent-thought
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 8192
+    min: 1
+    max: 8192
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '1.00'
+  output: '5.00'
+  unit: '0.000001'
+  currency: USD

ai-provider/model-runtime/model-providers/authropic/llm/claude-3-5-sonnet-20240620.yaml

@@ -0,0 +1,39 @@
+model: claude-3-5-sonnet-20240620
+label:
+  en_US: claude-3-5-sonnet-20240620
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 8192
+    min: 1
+    max: 8192
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '3.00'
+  output: '15.00'
+  unit: '0.000001'
+  currency: USD

ai-provider/model-runtime/model-providers/authropic/llm/claude-3-5-sonnet-20241022.yaml

@@ -0,0 +1,40 @@
+model: claude-3-5-sonnet-20241022
+label:
+  en_US: claude-3-5-sonnet-20241022
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+  - document
+model_properties:
+  mode: chat
+  context_size: 200000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 8192
+    min: 1
+    max: 8192
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '3.00'
+  output: '15.00'
+  unit: '0.000001'
+  currency: USD

ai-provider/model-runtime/model-providers/authropic/llm/claude-3-haiku-20240307.yaml

@@ -0,0 +1,39 @@
+model: claude-3-haiku-20240307
+label:
+  en_US: claude-3-haiku-20240307
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 4096
+    min: 1
+    max: 4096
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.25'
+  output: '1.25'
+  unit: '0.000001'
+  currency: USD

ai-provider/model-runtime/model-providers/authropic/llm/claude-3-opus-20240229.yaml

@@ -0,0 +1,39 @@
+model: claude-3-opus-20240229
+label:
+  en_US: claude-3-opus-20240229
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 4096
+    min: 1
+    max: 4096
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '15.00'
+  output: '75.00'
+  unit: '0.000001'
+  currency: USD

ai-provider/model-runtime/model-providers/authropic/llm/claude-3-sonnet-20240229.yaml

@@ -0,0 +1,39 @@
+model: claude-3-sonnet-20240229
+label:
+  en_US: claude-3-sonnet-20240229
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 4096
+    min: 1
+    max: 4096
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '3.00'
+  output: '15.00'
+  unit: '0.000001'
+  currency: USD

ai-provider/model-runtime/model-providers/authropic/llm/claude-instant-1.2.yaml

@@ -0,0 +1,36 @@
+model: claude-instant-1.2
+label:
+  en_US: claude-instant-1.2
+model_type: llm
+features: [ ]
+model_properties:
+  mode: chat
+  context_size: 100000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 4096
+    min: 1
+    max: 4096
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '1.63'
+  output: '5.51'
+  unit: '0.000001'
+  currency: USD
+deprecated: true

ai-provider/model-runtime/model-providers/authropic/llm/claude-instant-1.yaml

@@ -0,0 +1,36 @@
+model: claude-instant-1
+label:
+  en_US: claude-instant-1
+model_type: llm
+features: [ ]
+model_properties:
+  mode: chat
+  context_size: 100000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 4096
+    min: 1
+    max: 4096
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '1.63'
+  output: '5.51'
+  unit: '0.000001'
+  currency: USD
+deprecated: true

ai-provider/model-runtime/model-providers/baichuan/assets/icon_l_en.svg

@@ -0,0 +1,19 @@
+<svg width="130" height="24" viewBox="0 0 130 24" fill="none" xmlns="http://www.w3.org/2000/svg">
+<path fill-rule="evenodd" clip-rule="evenodd" d="M9.58154 1.7793H6.52779L4.34655 6.20409V17.7335L1.91602 22.2206H7.21333L9.58154 17.7335V1.7793ZM11.5761 1.7793H16.8111V22.2206H11.5761V1.7793ZM23.9166 1.7793H18.6816V6.01712H23.9166V1.7793ZM23.9166 7.38818H18.6816V22.2206H23.9166V7.38818Z" fill="url(#paint0_radial_11622_96091)"/>
+<path d="M129.722 6.83203V18H127.482V6.83203H129.722Z" fill="#FF6A34"/>
+<path d="M123.196 15.872H118.748L118.012 18H115.66L119.676 6.81604H122.284L126.3 18H123.932L123.196 15.872ZM122.588 14.08L120.972 9.40804L119.356 14.08H122.588Z" fill="#FF6A34"/>
+<path d="M110.962 18H108.722L103.65 10.336V18H101.41V6.81598H103.65L108.722 14.496V6.81598H110.962V18Z" fill="#FF6A34"/>
+<path d="M97.1258 15.872H92.6778L91.9418 18H89.5898L93.6058 6.81604H96.2138L100.23 18H97.8618L97.1258 15.872ZM96.5178 14.08L94.9018 9.40804L93.2858 14.08H96.5178Z" fill="#FF6A34"/>
+<path d="M81.6482 6.83203V13.744C81.6482 14.5014 81.8455 15.0827 82.2402 15.488C82.6349 15.8827 83.1895 16.08 83.9042 16.08C84.6295 16.08 85.1895 15.8827 85.5842 15.488C85.9789 15.0827 86.1762 14.5014 86.1762 13.744V6.83203H88.4322V13.728C88.4322 14.6774 88.2242 15.4827 87.8082 16.144C87.4029 16.7947 86.8535 17.2854 86.1602 17.616C85.4775 17.9467 84.7149 18.112 83.8722 18.112C83.0402 18.112 82.2829 17.9467 81.6002 17.616C80.9282 17.2854 80.3949 16.7947 80.0002 16.144C79.6055 15.4827 79.4082 14.6774 79.4082 13.728V6.83203H81.6482Z" fill="#FF6A34"/>
+<path d="M77.557 6.83203V18H75.317V13.248H70.533V18H68.293V6.83203H70.533V11.424H75.317V6.83203H77.557Z" fill="#FF6A34"/>
+<path d="M55.7871 12.4C55.7871 11.3013 56.0324 10.32 56.5231 9.45599C57.0244 8.58132 57.7018 7.90399 58.5551 7.42399C59.4191 6.93332 60.3844 6.68799 61.4511 6.68799C62.6991 6.68799 63.7924 7.00799 64.7311 7.64799C65.6698 8.28799 66.3258 9.17332 66.6991 10.304H64.1231C63.8671 9.77065 63.5044 9.37065 63.0351 9.10399C62.5764 8.83732 62.0431 8.70399 61.4351 8.70399C60.7844 8.70399 60.2031 8.85865 59.6911 9.16799C59.1898 9.46665 58.7951 9.89332 58.5071 10.448C58.2298 11.0027 58.0911 11.6533 58.0911 12.4C58.0911 13.136 58.2298 13.7867 58.5071 14.352C58.7951 14.9067 59.1898 15.3387 59.6911 15.648C60.2031 15.9467 60.7844 16.096 61.4351 16.096C62.0431 16.096 62.5764 15.9627 63.0351 15.696C63.5044 15.4187 63.8671 15.0133 64.1231 14.48H66.6991C66.3258 15.6213 65.6698 16.512 64.7311 17.152C63.8031 17.7813 62.7098 18.096 61.4511 18.096C60.3844 18.096 59.4191 17.856 58.5551 17.376C57.7018 16.8853 57.0244 16.208 56.5231 15.344C56.0324 14.48 55.7871 13.4987 55.7871 12.4Z" fill="#FF6A34"/>
+<path d="M54.4373 6.83203V18H52.1973V6.83203H54.4373Z" fill="#FF6A34"/>
+<path d="M47.913 15.872H43.465L42.729 18H40.377L44.393 6.81598H47.001L51.017 18H48.649L47.913 15.872ZM47.305 14.08L45.689 9.40798L44.073 14.08H47.305Z" fill="#FF6A34"/>
+<path d="M37.4395 12.272C38.0688 12.3893 38.5862 12.704 38.9915 13.216C39.3968 13.728 39.5995 14.3146 39.5995 14.976C39.5995 15.5733 39.4502 16.1013 39.1515 16.56C38.8635 17.008 38.4422 17.36 37.8875 17.616C37.3328 17.872 36.6768 18 35.9195 18H31.1035V6.83197H35.7115C36.4688 6.83197 37.1195 6.95464 37.6635 7.19997C38.2182 7.4453 38.6342 7.78664 38.9115 8.22397C39.1995 8.6613 39.3435 9.1573 39.3435 9.71197C39.3435 10.3626 39.1675 10.9066 38.8155 11.344C38.4742 11.7813 38.0155 12.0906 37.4395 12.272ZM33.3435 11.44H35.3915C35.9248 11.44 36.3355 11.3226 36.6235 11.088C36.9115 10.8426 37.0555 10.496 37.0555 10.048C37.0555 9.59997 36.9115 9.2533 36.6235 9.00797C36.3355 8.76264 35.9248 8.63997 35.3915 8.63997H33.3435V11.44ZM35.5995 16.176C36.1435 16.176 36.5648 16.048 36.8635 15.792C37.1728 15.536 37.3275 15.1733 37.3275 14.704C37.3275 14.224 37.1675 13.8506 36.8475 13.584C36.5275 13.3066 36.0955 13.168 35.5515 13.168H33.3435V16.176H35.5995Z" fill="#FF6A34"/>
+<defs>
+<radialGradient id="paint0_radial_11622_96091" cx="0" cy="0" r="1" gradientUnits="userSpaceOnUse" gradientTransform="translate(6.5 5.5) rotate(45) scale(20.5061 22.0704)">
+<stop stop-color="#FEBD3F"/>
+<stop offset="0.77608" stop-color="#FF6933"/>
+</radialGradient>
+</defs>
+</svg>

ai-provider/model-runtime/model-providers/baichuan/assets/icon_s_en.svg

@@ -0,0 +1,11 @@
+<svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg">
+<g id="Baichuan">
+<path id="Union" fill-rule="evenodd" clip-rule="evenodd" d="M8.58154 1.7793H5.52779L3.34655 6.20409V17.7335L0.916016 22.2206H6.21333L8.58154 17.7335V1.7793ZM10.5761 1.7793H15.8111V22.2206H10.5761V1.7793ZM22.9166 1.7793H17.6816V6.01712H22.9166V1.7793ZM22.9166 7.38818H17.6816V22.2206H22.9166V7.38818Z" fill="url(#paint0_radial_11622_96084)"/>
+</g>
+<defs>
+<radialGradient id="paint0_radial_11622_96084" cx="0" cy="0" r="1" gradientUnits="userSpaceOnUse" gradientTransform="translate(5.5 5.5) rotate(45) scale(20.5061 22.0704)">
+<stop stop-color="#FEBD3F"/>
+<stop offset="0.77608" stop-color="#FF6933"/>
+</radialGradient>
+</defs>
+</svg>

ai-provider/model-runtime/model-providers/baichuan/baichuan.yaml

@@ -0,0 +1,38 @@
+provider: baichuan
+label:
+  en_US: Baichuan
+icon_small:
+  en_US: icon_s_en.svg
+icon_large:
+  en_US: icon_l_en.svg
+background: "#FFF6F2"
+help:
+  title:
+    en_US: Get your API Key from BAICHUAN AI
+    zh_Hans: 从百川智能获取您的 API Key
+  url:
+    en_US: https://www.baichuan-ai.com
+supported_model_types:
+  - llm
+  - text-embedding
+configurate_methods:
+  - predefined-model
+provider_credential_schema:
+  credential_form_schemas:
+    - variable: api_key
+      label:
+        en_US: API Key
+      type: secret-input
+      required: true
+      placeholder:
+        zh_Hans: 在此输入您的 API Key
+        en_US: Enter your API Key
+    - variable: base_url
+      label:
+        en_US: https://api.baichuan-ai.com/v1
+      type: text-input
+      required: false
+      placeholder:
+        zh_Hans: 在此输入您的 Base URL
+        en_US: Enter your Base URL
+address: https://api.baichuan-ai.com/v1

ai-provider/model-runtime/model-providers/baichuan/llm/baichuan2-53b.yaml

@@ -0,0 +1,46 @@
+model: baichuan2-53b
+label:
+  en_US: Baichuan2-53B
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 32000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 1000
+    min: 1
+    max: 4000
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    default: 1
+    min: 1
+    max: 2
+  - name: with_search_enhance
+    label:
+      zh_Hans: 搜索增强
+      en_US: Search Enhance
+    type: boolean
+    help:
+      zh_Hans: 允许模型自行进行外部搜索，以增强生成结果。
+      en_US: Allow the model to perform external search to enhance the generation results.
+    required: false
+deprecated: true

ai-provider/model-runtime/model-providers/baichuan/llm/baichuan2-turbo-192k.yaml

@@ -0,0 +1,46 @@
+model: baichuan2-turbo-192k
+label:
+  en_US: Baichuan2-Turbo-192K
+model_type: llm
+features:
+  - agent-thought
+model_properties:
+  mode: chat
+  context_size: 192000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 8000
+    min: 1
+    max: 192000
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty
+    default: 1
+    min: 1
+    max: 2
+  - name: with_search_enhance
+    label:
+      zh_Hans: 搜索增强
+      en_US: Search Enhance
+    type: boolean
+    help:
+      zh_Hans: 允许模型自行进行外部搜索，以增强生成结果。
+      en_US: Allow the model to perform external search to enhance the generation results.
+    required: false
+deprecated: true

ai-provider/model-runtime/model-providers/baichuan/llm/baichuan2-turbo.yaml

@@ -0,0 +1,41 @@
+model: baichuan2-turbo
+label:
+  en_US: Baichuan2-Turbo
+model_type: llm
+features:
+  - agent-thought
+  - multi-tool-call
+model_properties:
+  mode: chat
+  context_size: 32000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.3
+  - name: top_p
+    use_template: top_p
+    default: 0.85
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    min: 0
+    max: 20
+    default: 5
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    default: 2048
+  - name: with_search_enhance
+    label:
+      zh_Hans: 搜索增强
+      en_US: Search Enhance
+    type: boolean
+    help:
+      zh_Hans: 允许模型自行进行外部搜索，以增强生成结果。
+      en_US: Allow the model to perform external search to enhance the generation results.
+    required: false

ai-provider/model-runtime/model-providers/baichuan/llm/baichuan3-turbo-128k.yaml

@@ -0,0 +1,53 @@
+model: baichuan3-turbo-128k
+label:
+  en_US: Baichuan3-Turbo-128k
+model_type: llm
+features:
+  - agent-thought
+  - multi-tool-call
+model_properties:
+  mode: chat
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.3
+  - name: top_p
+    use_template: top_p
+    default: 0.85
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    min: 0
+    max: 20
+    default: 5
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    default: 2048
+  - name: res_format
+    label:
+      zh_Hans: 回复格式
+      en_US: Response Format
+    type: string
+    help:
+      zh_Hans: 指定模型必须输出的格式
+      en_US: specifying the format that the model must output
+    required: false
+    options:
+      - text
+      - json_object
+  - name: with_search_enhance
+    label:
+      zh_Hans: 搜索增强
+      en_US: Search Enhance
+    type: boolean
+    help:
+      zh_Hans: 允许模型自行进行外部搜索，以增强生成结果。
+      en_US: Allow the model to perform external search to enhance the generation results.
+    required: false

ai-provider/model-runtime/model-providers/baichuan/llm/baichuan3-turbo.yaml

@@ -0,0 +1,53 @@
+model: baichuan3-turbo
+label:
+  en_US: Baichuan3-Turbo
+model_type: llm
+features:
+  - agent-thought
+  - multi-tool-call
+model_properties:
+  mode: chat
+  context_size: 32000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.3
+  - name: top_p
+    use_template: top_p
+    default: 0.85
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    min: 0
+    max: 20
+    default: 5
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    default: 2048
+  - name: res_format
+    label:
+      zh_Hans: 回复格式
+      en_US: Response Format
+    type: string
+    help:
+      zh_Hans: 指定模型必须输出的格式
+      en_US: specifying the format that the model must output
+    required: false
+    options:
+      - text
+      - json_object
+  - name: with_search_enhance
+    label:
+      zh_Hans: 搜索增强
+      en_US: Search Enhance
+    type: boolean
+    help:
+      zh_Hans: 允许模型自行进行外部搜索，以增强生成结果。
+      en_US: Allow the model to perform external search to enhance the generation results.
+    required: false

ai-provider/model-runtime/model-providers/baichuan/llm/baichuan4.yaml

@@ -0,0 +1,53 @@
+model: baichuan4
+label:
+  en_US: Baichuan4
+model_type: llm
+features:
+  - agent-thought
+  - multi-tool-call
+model_properties:
+  mode: chat
+  context_size: 32000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.3
+  - name: top_p
+    use_template: top_p
+    default: 0.85
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    min: 0
+    max: 20
+    default: 5
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    default: 2048
+  - name: res_format
+    label:
+      zh_Hans: 回复格式
+      en_US: Response Format
+    type: string
+    help:
+      zh_Hans: 指定模型必须输出的格式
+      en_US: specifying the format that the model must output
+    required: false
+    options:
+      - text
+      - json_object
+  - name: with_search_enhance
+    label:
+      zh_Hans: 搜索增强
+      en_US: Search Enhance
+    type: boolean
+    help:
+      zh_Hans: 允许模型自行进行外部搜索，以增强生成结果。
+      en_US: Allow the model to perform external search to enhance the generation results.
+    required: false

ai-provider/model-runtime/model-providers/bailian/assets/icon_s_en.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1" id="Layer_1" x="0px" y="0px" width="48px" height="48px" viewBox="0 0 48 48" enable-background="new 0 0 48 48" xml:space="preserve">  <image id="image0" width="48" height="48" x="0" y="0" xlink:href="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAADAAAAAwCAYAAABXAvmHAAAAIGNIUk0AAHomAACAhAAA+gAAAIDo AAB1MAAA6mAAADqYAAAXcJy6UTwAAAAGYktHRAD/AP8A/6C9p5MAAAAJcEhZcwAAFiUAABYlAUlS JPAAAApPSURBVGje7VlrkFTFFf7O6Tu77AuWhygoKYXEREO0EFCjZbkUUUxSiiUOEB8RNPIookZB UBAZRR6iKIIJAaJYGDWyQVkrxgpWAoqgUUlIWRJiIr5IIChhhd1hd+b2+fLjzszOLrO7gBBNlV3V NXf6cfr7zut29wW+LJ9vkSMhZML42nlQ3gwgEBGIAKJRhcgWhrHvLlxY+uHRIKCfVcC4cfv6euN4 C/EaDTQjzJCrNJ6qLn33DTew+AtHIB6n86lwhnmshso1JHfQAJJgBB40wIxx52q//YUjUFlSewnA C9JeZixeXLkNHg9HwLPgJXomSj3k7qNB4LBjYOTID3qWFJWvdZTlv3i8y1wAGDWKHYqDPW9DpHd+ HKgKIIA6XF8UNDx3oLQyoPzA1nJ8sjeROKnhqBAYfcWuO6hyrdU1Dlyx+oTd2faxP9ozlOAzIqL5 JEQE6rBfFfUQQFSg2T4XBb6qQBRwCkDhIXg6FpbfmkhIqjUcweGAv2bEh308/XWg3pIPHgBSvmGj Q/H7quwNFcAymlKChhKDlIgCMII5/RFQgABEAKNACAgwISxK/h7Ac61hOawY8LSZZqkt+1MfP3+A ScPiYTT0NgPMM5OJmrKSeYAeIAHLBDmZjRs0C34QDp53JBKsPGIERg575yyP8GIRvbu6um8z044a 9V4ladNzwDJgLB8c2QSYgDGPRLYvv4ID07r3qiNCYMyYN2NEOANmT/T5xiNvtOy3xuIppPUEm2sW bEEiryIzDmxhFWOuXUSn3X77jmMKYSoYxJdf+vpg84yLOINqhqmAcF1V9IKY+NOeeOb07flzrh7x YV+obBAEHUUUqg4impeJosAt/NwU1OqaB7i6aJxA7rtnevnkdglcdtlrJ1jK1gkUEN0uEEAcoBkS YtWrnu3/05bzrhz53jhQh2WBO3EAHDQQSkYEROCEkEAoopFYaUq16gB1jDJWBJ6qSij7iKKjQfvN vqNsR6sESMol339pPqA/UUXN9h2lwzdtGpA+1Dg5kmXMGMa69tz3O1VN7q0sG7boRmnM728WAxdf 9Id+tHAE6cV8eOHx3fZc+HmCB4DOx+4dAcjZZrFJLcE3I9C//5sxQ3qc0XqSIYxW6oG74lUryw9t ySNXJiV2dhfKrTQsnZMo+luhMTkC3bp9cr63cLRZGt6nYZaG0fffV1Rx/edFAOnyKwwocz54EBC2 SQC+4U4yDIwhIgtEv4BNGjJkZZf/NfZp05K94P10T7t/1qySD1obl9tKeAt7i0QxTQgEAkIhkJ7C smkAJrYmJB7fWNK8pddBgayu7rW/tb56MnRkUs11BymQdixg5m8zS3uzjPtk3chCeEtde+GgZ/u3 tliYcqvDxiBpqeIk06VJ8bVJtbpkgP3JmITJYsdkSaDJ0qKiZHlxabKipCzZsazsxbbILZhdtgOC mYCNv2nKvpNbG5cjUBKGz9PCl8w8SA+jBxmC9CCtkg4Tq6rWdigkhB4JM6snPQgDma3MPRuZ+U+A TJqkJ6OdUtEh9aSR78RirVs/R+D5V67cQwsfMKYbzNKZOPAwi2KB5i8tcnsuLSQkVlK2ScR+GZ3E IuDIEMn/ze4dDLJq+fLur7ZHIJHoXkfR+UJeNnVq7RltEgCAtevff8G81Rg9vIWgZS3gQfoSMz+x qmp5ZUsh1dV9U9RgFsFdyLNAE/iM9qONzzaENru1rNKy1O1+5wWCr3jR2YkEi9okACTMc/9c0n+S zURmISK3CkHYAIfyEYUWqqk58yMI55MWuRGaXKaJDGmwpY891W1rIRkTJtQOHz9+d7MMsHTpgDTp plJw1n5fP7wdAsDGjRM2E34FzYNmkRsxhJmB9IDYnVVVK48r6ErFFT8DsA3Mj4MmC4B+syYblhSa e911H3Wh8SFVNy0eb67p+XMqtojJ46TdOnVq3bFtEgCAIJA5pP83GQJREOe5kvV0IjcXmldd3bfO U++0SP2IzlhNAS3APY+tPqm24JpaMYnEcQCv6tHjPwNa9qcldZ+oxFjEHycSzOEuSGDdurGfUDg7 Cxr52QUGwI8ZUrXyq4XmdupcvFrAtdH4fDfnKw32ek2hOddfs++bIrwuGiZlRndXyzEPzOr6kdAv JHFtMmz8WpsEAECkfjmNf4n83zKpNafNylDxAMkDtuOPP356fRDE7gaRigxhIPgpzSZVVw/3LcfH 4yyBS08j0T1zAgOI70y4cfcB/t7BdXoMwFYXpKblLNcagQ0bpuw75+yFjxL2EKkAFSJNVlC6IRcO /vUFANa0nPvxnk83dO5Y/qiQYyEQgNW/WnXyHwutU1Gx6zwgNpTM5KWM0Zy4e2+65dOhqoCqigSQ ZHqvqNMeEBnYrgX691/SyTP9w1wWYdYlokpYESEzzztv5QFHvXXrBoUmbhEEO0SwM6SbX2iNUaPe q1QLJgMojcye53DEiSCvAHAFYT8AbSQgIwCeIsDT7RJw7tOxNOufBZxVTZTPkW07s6S4aFSh+TU1 Z2whsNjAe1et+nrBtKm+c5yUwVmto603Q7ZPZHs6jM1tk8DAgfOOMx9OZt7rn9lT9wEL8baLqp49 sZCcuqR7sCHVbWmhvhtu2N2RsBnt4W7RaaTdP29m8bZsQ8EYoE9PhqCrSHTRlCvZl2feS5REF8Tc bQDGt1xuzZrT61vDlazFRJDHH8rloAg2NYbBSsnbmRYmIDKkSaxAJLO9pnwAwVwVV0dRKAQg4MHG qqq1bt26QeHBALn66n+d4s3fKOIyK7SFOvfQaMKHF8xufqgvSEAhNRA5NZqdkxAKbMH69aN/ftAq Kwh+Z5l43gpB5QEgo9+PReQ1iKSjKz0hxSCQV9/f2vGJlvIKEkj7DvNiQThcxPWJvrgoROQNNDRF /+EWSzUOcq7o8oKdBERlwaJFHecc7GavYBBv3nxzbeCC2SJKgYOIJkkuXr9p7I6DEdpaicff7SSq UwBUZF0zq30RAIptqm7ZwYJvlUDUw6dE5M/R7Zq+vHNXeuVn0z0Qg7tcKOdkIDd1ZEkYpy9aVPHx ochsM36qzl12dkh72WnRKtFgK1ShUAABFAoNihBoAGiAQKN2qEsFJk8+89tzmx3ER4/++zGp+thf 1QVdVQKoBhDVzG0cAGD9kmWdzxc5eO0D7XwfOKbnmjd27rwoQWCwiHRz0ZcJiEbH/eh0ZXCZS1ko EUC/wsB1TiQStyUSCcvKaqzXiSraFRkZkQvl9JgOFDMOFXy7FjicMmzoxnOIohr42JBnfnP6nwBg 5LC3+6krXa8alKk4qMaiy9/MZa4KlvXo1XlcIiF2qOsdcQLxOB3TmxeK6PF1b/1zRHm/ujCGAU+J ajznOhJAnWZvoLdLgO8tXdrlrcNZ74gTAIARl77Vh4IXxQU3wgUpR1ejGnRoIuBy1+ZOMWfJI12m Hu5an/lDd6Hy9OpvvQtxC0XcXWqYB2gHQDO5MpM+AUD4j/3p5PzPstZRIQAAdLYClF0iwWkiAhX1 AvUiEopISgR7aJyyYkXzj4Rflv+38l9KlbIj6CqimgAAACV0RVh0ZGF0ZTpjcmVhdGUAMjAyNC0x MC0xMFQxMDoxOTo0NSswMDowMMQaMdYAAAAldEVYdGRhdGU6bW9kaWZ5ADIwMjQtMTAtMTBUMTA6 MTk6NDUrMDA6MDC1R4lqAAAAKHRFWHRkYXRlOnRpbWVzdGFtcAAyMDI0LTEwLTEwVDEwOjE5OjQ1 KzAwOjAw4lKotQAAAABJRU5ErkJggg=="/>

ai-provider/model-runtime/model-providers/bailian/bailian.yaml

@@ -0,0 +1,40 @@
+provider: bailian
+label:
+  zh_Hans: 阿里云百炼
+  en_US: BaiLian
+icon_small:
+  en_US: icon_s_en.svg
+icon_large:
+  zh_Hans: icon_l_zh.svg
+  en_US: icon_l_en.svg
+background: "#EFF1FE"
+help:
+  title:
+    en_US: Get your API key from AliCloud
+    zh_Hans: 从阿里云百炼获取 API Key
+  url:
+    en_US: https://bailian.console.aliyun.com/?apiKey=1#/api-key
+supported_model_types:
+  - llm
+configurate_methods:
+  - predefined-model
+  - customizable-model
+provider_credential_schema:
+  credential_form_schemas:
+    - variable: api_key
+      label:
+        en_US: API Key
+      type: secret-input
+      required: true
+      placeholder:
+        zh_Hans: 在此输入您的 API Key
+        en_US: Enter your API Key
+    - variable: base_url
+      label:
+        en_US: https://dashscope.aliyuncs.com/compatible-mode/v1
+      type: text-input
+      required: false
+      placeholder:
+        zh_Hans: 在此输入您的 Base URL
+        en_US: Enter your Base URL
+address: https://dashscope.aliyuncs.com/compatible-mode/v1

ai-provider/model-runtime/model-providers/bedrock/assets/icon_l_en.svg

@@ -0,0 +1,14 @@
+<svg width="140" height="24" viewBox="0 0 140 24" fill="none" xmlns="http://www.w3.org/2000/svg">
+<path d="M131.701 17.9999V6.8999H133.876V13.6049L136.531 10.3349H139.141L135.976 13.9949L139.381 17.9999H136.711L133.876 14.5049V17.9999H131.701Z" fill="#252F3E"/>
+<path d="M129.847 17.6699C129.577 17.8299 129.252 17.9499 128.872 18.0299C128.492 18.1199 128.097 18.1649 127.687 18.1649C126.467 18.1649 125.532 17.8249 124.882 17.1449C124.242 16.4649 123.922 15.4849 123.922 14.2049C123.922 12.9349 124.262 11.9449 124.942 11.2349C125.622 10.5249 126.567 10.1699 127.777 10.1699C128.507 10.1699 129.182 10.3299 129.802 10.6499V12.1049C129.212 11.9349 128.672 11.8499 128.182 11.8499C127.482 11.8499 126.967 12.0299 126.637 12.3899C126.307 12.7399 126.142 13.2999 126.142 14.0699V14.2799C126.142 15.0399 126.302 15.5999 126.622 15.9599C126.952 16.3099 127.457 16.4849 128.137 16.4849C128.627 16.4849 129.197 16.3949 129.847 16.2149V17.6699Z" fill="#252F3E"/>
+<path d="M118.51 18.2249C117.32 18.2249 116.39 17.8699 115.72 17.1599C115.05 16.4399 114.715 15.4399 114.715 14.1599C114.715 12.8899 115.05 11.8999 115.72 11.1899C116.39 10.4699 117.32 10.1099 118.51 10.1099C119.7 10.1099 120.63 10.4699 121.3 11.1899C121.97 11.8999 122.305 12.8899 122.305 14.1599C122.305 15.4399 121.97 16.4399 121.3 17.1599C120.63 17.8699 119.7 18.2249 118.51 18.2249ZM118.51 16.5449C119.56 16.5449 120.085 15.7499 120.085 14.1599C120.085 12.5799 119.56 11.7899 118.51 11.7899C117.46 11.7899 116.935 12.5799 116.935 14.1599C116.935 15.7499 117.46 16.5449 118.51 16.5449Z" fill="#252F3E"/>
+<path d="M108.727 17.9998V10.3348H110.527L110.797 11.4748C111.197 11.0348 111.572 10.7248 111.922 10.5448C112.282 10.3548 112.662 10.2598 113.062 10.2598C113.252 10.2598 113.452 10.2748 113.662 10.3048V12.3298C113.382 12.2698 113.072 12.2398 112.732 12.2398C112.082 12.2398 111.477 12.3548 110.917 12.5848V17.9998H108.727Z" fill="#252F3E"/>
+<path d="M104.417 17.9999L104.237 17.3249C103.617 17.8849 102.882 18.1649 102.032 18.1649C101.402 18.1649 100.847 18.0099 100.367 17.6999C99.8866 17.3799 99.5116 16.9199 99.2416 16.3199C98.9816 15.7199 98.8516 15.0149 98.8516 14.2049C98.8516 12.9649 99.1466 11.9749 99.7366 11.2349C100.327 10.4849 101.107 10.1099 102.077 10.1099C102.867 10.1099 103.552 10.3349 104.132 10.7849V6.8999H106.322V17.9999H104.417ZM102.752 16.5149C103.232 16.5149 103.692 16.3749 104.132 16.0949V12.1349C103.702 11.8849 103.207 11.7599 102.647 11.7599C102.117 11.7599 101.722 11.9599 101.462 12.3599C101.202 12.7499 101.072 13.3449 101.072 14.1449C101.072 14.9449 101.207 15.5399 101.477 15.9299C101.757 16.3199 102.182 16.5149 102.752 16.5149Z" fill="#252F3E"/>
+<path d="M92.4625 14.6999C92.5025 15.3599 92.7025 15.8399 93.0625 16.1399C93.4225 16.4299 93.9875 16.5749 94.7575 16.5749C95.4275 16.5749 96.2075 16.4499 97.0975 16.1999V17.6549C96.7475 17.8349 96.3275 17.9749 95.8375 18.0749C95.3575 18.1749 94.8575 18.2249 94.3375 18.2249C93.0675 18.2249 92.0975 17.8799 91.4275 17.1899C90.7675 16.4999 90.4375 15.4899 90.4375 14.1599C90.4375 12.8799 90.7675 11.8849 91.4275 11.1749C92.0875 10.4649 93.0025 10.1099 94.1725 10.1099C95.1625 10.1099 95.9225 10.3849 96.4525 10.9349C96.9925 11.4749 97.2625 12.2499 97.2625 13.2599C97.2625 13.4799 97.2475 13.7299 97.2175 14.0099C97.1875 14.2899 97.1525 14.5199 97.1125 14.6999H92.4625ZM94.0975 11.6249C93.6075 11.6249 93.2175 11.7749 92.9275 12.0749C92.6475 12.3649 92.4875 12.7899 92.4475 13.3499H95.3875V13.0949C95.3875 12.1149 94.9575 11.6249 94.0975 11.6249Z" fill="#252F3E"/>
+<path d="M81.1992 18V7.60498H84.9342C85.9342 7.60498 86.7392 7.85998 87.3492 8.36998C87.9692 8.87998 88.2792 9.54498 88.2792 10.365C88.2792 10.875 88.1592 11.315 87.9192 11.685C87.6892 12.045 87.3442 12.325 86.8842 12.525C87.5242 12.715 88.0092 13.03 88.3392 13.47C88.6792 13.9 88.8492 14.43 88.8492 15.06C88.8492 15.96 88.5142 16.675 87.8442 17.205C87.1742 17.735 86.2742 18 85.1442 18H81.1992ZM83.3292 13.47V16.395H85.0992C86.1192 16.395 86.6292 15.915 86.6292 14.955C86.6292 13.965 86.0842 13.47 84.9942 13.47H83.3292ZM83.3292 9.20998V11.94H84.6342C85.6042 11.94 86.0892 11.49 86.0892 10.59C86.0892 9.66998 85.6442 9.20998 84.7542 9.20998H83.3292Z" fill="#252F3E"/>
+<path fill-rule="evenodd" clip-rule="evenodd" d="M62.0002 20.4425L58.6644 21.5548L57.3636 20.6872L58.7799 20.2142L58.3454 18.9107L55.9143 19.7206L55.1251 19.1953V15.4374C55.1251 15.1775 54.9779 14.9396 54.7456 14.8227L52.375 13.6375V10.3621L54.4376 9.33087L56.5001 10.3621V12.6873C56.5001 12.9486 56.6472 13.1864 56.8796 13.3033L59.6297 14.6783L60.2457 13.4477L57.8751 12.2624V10.3621L60.2457 9.17824C60.4781 9.06136 60.6252 8.82349 60.6252 8.56223V6.49969H59.2502V8.13735L57.1876 9.16862L55.1251 8.13735V4.80566L56.5001 3.88852V6.49969H57.8751V2.97275L58.6644 2.44612L62.0002 3.55851V20.4425ZM69.5628 18.8749C69.941 18.8749 70.2504 19.1829 70.2504 19.5624C70.2504 19.9419 69.941 20.2499 69.5628 20.2499C69.1847 20.2499 68.8753 19.9419 68.8753 19.5624C68.8753 19.1829 69.1847 18.8749 69.5628 18.8749ZM68.1878 3.74964C68.566 3.74964 68.8753 4.05765 68.8753 4.43715C68.8753 4.81666 68.566 5.12467 68.1878 5.12467C67.8097 5.12467 67.5003 4.81666 67.5003 4.43715C67.5003 4.05765 67.8097 3.74964 68.1878 3.74964ZM70.9379 11.9998C71.316 11.9998 71.6254 12.3078 71.6254 12.6873C71.6254 13.0668 71.316 13.3748 70.9379 13.3748C70.5597 13.3748 70.2504 13.0668 70.2504 12.6873C70.2504 12.3078 70.5597 11.9998 70.9379 11.9998ZM69.0018 13.3748C69.2865 14.1737 70.0427 14.7498 70.9379 14.7498C72.075 14.7498 73.0004 13.8258 73.0004 12.6873C73.0004 11.5502 72.075 10.6248 70.9379 10.6248C70.0427 10.6248 69.2865 11.2023 69.0018 11.9998H63.3752V9.24974H68.1878C68.5673 9.24974 68.8753 8.94311 68.8753 8.56223V6.37319C69.6742 6.08856 70.2504 5.3323 70.2504 4.43715C70.2504 3.30001 69.325 2.37462 68.1878 2.37462C67.0507 2.37462 66.1253 3.30001 66.1253 4.43715C66.1253 5.3323 66.7014 6.08856 67.5003 6.37319V7.87472H63.3752V3.06213C63.3752 2.7665 63.1855 2.50387 62.905 2.41037L58.7799 1.03534C58.5778 0.967964 58.3578 0.998214 58.1818 1.11509L54.0567 3.86514C53.8656 3.99302 53.7501 4.20752 53.7501 4.43715V8.13735L51.3795 9.32262C51.1471 9.4395 51 9.67738 51 9.93726V14.0623C51 14.3236 51.1471 14.5615 51.3795 14.6783L53.7501 15.8622V19.5624C53.7501 19.7921 53.8656 20.0079 54.0567 20.1344L58.1818 22.8845C58.2959 22.9615 58.4279 23 58.5626 23C58.6355 23 58.7084 22.989 58.7799 22.9642L62.905 21.5892C63.1855 21.4971 63.3752 21.2345 63.3752 20.9375V17.4999H66.5282L67.7011 18.6742L67.7189 18.6563C67.5842 18.9313 67.5003 19.2366 67.5003 19.5624C67.5003 20.6996 68.4257 21.625 69.5628 21.625C70.7 21.625 71.6254 20.6996 71.6254 19.5624C71.6254 18.4253 70.7 17.4999 69.5628 17.4999C69.2356 17.4999 68.9303 17.5838 68.6567 17.7199L68.6746 17.702L67.2996 16.327C67.1703 16.1977 66.9957 16.1249 66.8128 16.1249H63.3752V13.3748H69.0018Z" fill="#252F3E"/>
+<line x1="43.25" y1="4" x2="43.25" y2="20" stroke="black" stroke-opacity="0.08" stroke-width="0.5"/>
+<path d="M9.89554 9.62679C9.89554 10.0589 9.94226 10.4093 10.024 10.6663C10.1175 10.9232 10.2342 11.2035 10.3978 11.5072C10.4562 11.6006 10.4795 11.6941 10.4795 11.7758C10.4795 11.8926 10.4094 12.0094 10.2576 12.1262L9.52179 12.6168C9.41667 12.6869 9.31156 12.7219 9.21812 12.7219C9.10132 12.7219 8.98453 12.6635 8.86773 12.5584C8.70422 12.3832 8.56406 12.1963 8.44726 12.0094C8.33047 11.8109 8.21367 11.589 8.0852 11.3203C7.17419 12.3949 6.02958 12.9321 4.65139 12.9321C3.6703 12.9321 2.88777 12.6518 2.31546 12.0912C1.74316 11.5306 1.45117 10.7831 1.45117 9.84871C1.45117 8.85594 1.80156 8.05004 2.51402 7.4427C3.22647 6.83536 4.17252 6.53169 5.37552 6.53169C5.77263 6.53169 6.18142 6.56673 6.61356 6.62513C7.04571 6.68353 7.48954 6.77697 7.95672 6.88208V6.02947C7.95672 5.14182 7.76985 4.5228 7.40778 4.16073C7.03403 3.79866 6.40333 3.62347 5.504 3.62347C5.09521 3.62347 4.67475 3.67019 4.2426 3.7753C3.81046 3.88042 3.38999 4.00889 2.9812 4.17241C2.79433 4.25417 2.65417 4.30089 2.57242 4.32424C2.49066 4.3476 2.43226 4.35928 2.38554 4.35928C2.22203 4.35928 2.14027 4.24249 2.14027 3.99722V3.42491C2.14027 3.23804 2.16363 3.09788 2.22203 3.01613C2.28042 2.93437 2.38554 2.85261 2.54906 2.77085C2.95784 2.56062 3.44839 2.38543 4.02069 2.24527C4.59299 2.09344 5.20033 2.02336 5.84271 2.02336C7.23258 2.02336 8.24871 2.33871 8.90277 2.96941C9.54515 3.60011 9.87218 4.55784 9.87218 5.8426V9.62679H9.89554ZM5.15361 11.4021C5.53904 11.4021 5.93615 11.332 6.35661 11.1919C6.77708 11.0517 7.15083 10.7948 7.46618 10.4444C7.65305 10.2225 7.79321 9.97718 7.86328 9.69687C7.93336 9.41656 7.98008 9.07785 7.98008 8.68074V8.1902C7.64137 8.10844 7.2793 8.03836 6.90555 7.99165C6.53181 7.94493 6.16974 7.92157 5.80767 7.92157C5.02514 7.92157 4.45283 8.0734 4.06741 8.38875C3.68198 8.7041 3.49511 9.14793 3.49511 9.73191C3.49511 10.2809 3.63526 10.6896 3.92725 10.9699C4.20756 11.2619 4.61635 11.4021 5.15361 11.4021ZM14.5323 12.6635C14.3221 12.6635 14.182 12.6285 14.0885 12.5467C13.9951 12.4766 13.9133 12.3131 13.8432 12.0912L11.0985 3.06285C11.0285 2.82925 10.9934 2.67742 10.9934 2.59566C10.9934 2.40879 11.0869 2.30367 11.2737 2.30367H12.4183C12.6402 2.30367 12.7921 2.33871 12.8738 2.42047C12.9673 2.49054 13.0374 2.65406 13.1074 2.87597L15.0696 10.6079L16.8916 2.87597C16.95 2.64238 17.0201 2.49054 17.1135 2.42047C17.207 2.35039 17.3705 2.30367 17.5807 2.30367H18.5151C18.737 2.30367 18.8888 2.33871 18.9823 2.42047C19.0757 2.49054 19.1575 2.65406 19.2042 2.87597L21.0496 10.7013L23.0701 2.87597C23.1402 2.64238 23.222 2.49054 23.3037 2.42047C23.3972 2.35039 23.549 2.30367 23.7592 2.30367H24.8454C25.0323 2.30367 25.1374 2.39711 25.1374 2.59566C25.1374 2.65406 25.1258 2.71246 25.1141 2.78253C25.1024 2.85261 25.079 2.94605 25.0323 3.07453L22.2175 12.1029C22.1475 12.3365 22.0657 12.4883 21.9723 12.5584C21.8788 12.6285 21.727 12.6752 21.5284 12.6752H20.524C20.3021 12.6752 20.1502 12.6401 20.0568 12.5584C19.9634 12.4766 19.8816 12.3248 19.8349 12.0912L18.0246 4.55784L16.2259 12.0795C16.1675 12.3131 16.0974 12.4649 16.004 12.5467C15.9105 12.6285 15.747 12.6635 15.5368 12.6635H14.5323ZM29.5407 12.9788C28.9333 12.9788 28.326 12.9088 27.742 12.7686C27.158 12.6285 26.7025 12.4766 26.3988 12.3014C26.212 12.1963 26.0835 12.0795 26.0368 11.9744C25.9901 11.8693 25.9667 11.7525 25.9667 11.6474V11.0517C25.9667 10.8064 26.0601 10.6896 26.2353 10.6896C26.3054 10.6896 26.3755 10.7013 26.4456 10.7247C26.5156 10.748 26.6208 10.7948 26.7375 10.8415C27.1347 11.0167 27.5668 11.1568 28.0223 11.2503C28.4895 11.3437 28.945 11.3904 29.4122 11.3904C30.148 11.3904 30.7203 11.2619 31.1174 11.005C31.5145 10.748 31.7247 10.3743 31.7247 9.89542C31.7247 9.56839 31.6196 9.29976 31.4094 9.07785C31.1992 8.85594 30.8021 8.65738 30.2298 8.47051L28.5362 7.94493C27.6836 7.6763 27.0529 7.27919 26.6675 6.75361C26.282 6.2397 26.0835 5.6674 26.0835 5.06006C26.0835 4.56952 26.1886 4.13737 26.3988 3.76362C26.6091 3.38987 26.8894 3.06285 27.2398 2.80589C27.5902 2.53726 27.9873 2.33871 28.4545 2.19855C28.9216 2.0584 29.4122 2 29.9261 2C30.183 2 30.4517 2.01168 30.7086 2.04672C30.9773 2.08176 31.2225 2.12848 31.4678 2.17519C31.7014 2.23359 31.9233 2.29199 32.1335 2.36207C32.3438 2.43215 32.5073 2.50222 32.6241 2.5723C32.7876 2.66574 32.9044 2.75918 32.9745 2.86429C33.0445 2.95773 33.0796 3.0862 33.0796 3.24972V3.79866C33.0796 4.04393 32.9861 4.17241 32.811 4.17241C32.7175 4.17241 32.5657 4.12569 32.3671 4.03225C31.7014 3.72858 30.9539 3.57675 30.1246 3.57675C29.4589 3.57675 28.9333 3.68187 28.5712 3.90378C28.2092 4.12569 28.0223 4.4644 28.0223 4.94326C28.0223 5.27029 28.1391 5.5506 28.3727 5.77252C28.6063 5.99443 29.0384 6.21634 29.6575 6.4149L31.316 6.94048C32.1569 7.20911 32.7642 7.58286 33.1263 8.06172C33.4884 8.54059 33.6636 9.08953 33.6636 9.69687C33.6636 10.1991 33.5584 10.6546 33.3599 11.0517C33.1497 11.4488 32.8693 11.7992 32.5073 12.0795C32.1452 12.3715 31.7131 12.5817 31.2108 12.7336C30.6853 12.8971 30.1363 12.9788 29.5407 12.9788Z" fill="#252F3E"/>
+<path fill-rule="evenodd" clip-rule="evenodd" d="M31.749 18.6553C27.9064 21.4934 22.3235 23.0001 17.5232 23.0001C10.7957 23.0001 4.73399 20.5123 0.155575 16.3778C-0.206494 16.0507 0.120536 15.6069 0.552682 15.8639C5.50484 18.737 11.6133 20.4773 17.932 20.4773C22.195 20.4773 26.8786 19.5896 31.1883 17.7676C31.8307 17.4756 32.3797 18.1881 31.749 18.6553Z" fill="#FF9900"/>
+<path fill-rule="evenodd" clip-rule="evenodd" d="M33.3507 16.833C32.8601 16.2023 30.1037 16.5293 28.854 16.6811C28.4803 16.7278 28.4219 16.4008 28.7606 16.1555C30.9564 14.6138 34.5654 15.0577 34.9858 15.5716C35.4063 16.0971 34.869 19.7062 32.8134 21.4347C32.4981 21.7034 32.1944 21.5632 32.3345 21.2128C32.8017 20.0565 33.8412 17.452 33.3507 16.833Z" fill="#FF9900"/>
+</svg>

ai-provider/model-runtime/model-providers/bedrock/assets/icon_s_en.svg

@@ -0,0 +1,15 @@
+<svg width="16" height="16" viewBox="0 0 16 16" fill="none" xmlns="http://www.w3.org/2000/svg">
+<g clip-path="url(#clip0_16762_59518)">
+<path d="M12.6667 0H3.33333C1.49238 0 0 1.49238 0 3.33333V12.6667C0 14.5076 1.49238 16 3.33333 16H12.6667C14.5076 16 16 14.5076 16 12.6667V3.33333C16 1.49238 14.5076 0 12.6667 0Z" fill="url(#paint0_linear_16762_59518)"/>
+<path fill-rule="evenodd" clip-rule="evenodd" d="M7.99984 12.093L6.3825 12.6323L5.75184 12.2116L6.4385 11.9823L6.22784 11.3503L5.04917 11.743L4.6665 11.4883V9.66631C4.6665 9.54031 4.59517 9.42497 4.4825 9.3683L3.33317 8.79364V7.20564L4.33317 6.70564L5.33317 7.20564V8.33297C5.33317 8.45964 5.4045 8.57497 5.51717 8.63164L6.8505 9.29831L7.14917 8.70164L5.99984 8.12697V7.20564L7.14917 6.63164C7.26184 6.57497 7.33317 6.45964 7.33317 6.33297V5.33297H6.6665V6.12697L5.6665 6.62697L4.6665 6.12697V4.51164L5.33317 4.06697V5.33297H5.99984V3.62297L6.3825 3.36764L7.99984 3.90697V12.093ZM11.6665 11.333C11.8498 11.333 11.9998 11.4823 11.9998 11.6663C11.9998 11.8503 11.8498 11.9996 11.6665 11.9996C11.4832 11.9996 11.3332 11.8503 11.3332 11.6663C11.3332 11.4823 11.4832 11.333 11.6665 11.333ZM10.9998 3.99964C11.1832 3.99964 11.3332 4.14897 11.3332 4.33297C11.3332 4.51697 11.1832 4.6663 10.9998 4.6663C10.8165 4.6663 10.6665 4.51697 10.6665 4.33297C10.6665 4.14897 10.8165 3.99964 10.9998 3.99964ZM12.3332 7.99964C12.5165 7.99964 12.6665 8.14897 12.6665 8.33297C12.6665 8.51697 12.5165 8.66631 12.3332 8.66631C12.1498 8.66631 11.9998 8.51697 11.9998 8.33297C11.9998 8.14897 12.1498 7.99964 12.3332 7.99964ZM11.3945 8.66631C11.5325 9.05364 11.8992 9.33297 12.3332 9.33297C12.8845 9.33297 13.3332 8.88497 13.3332 8.33297C13.3332 7.78164 12.8845 7.33297 12.3332 7.33297C11.8992 7.33297 11.5325 7.61297 11.3945 7.99964H8.6665V6.66631H10.9998C11.1838 6.66631 11.3332 6.51764 11.3332 6.33297V5.27164C11.7205 5.13364 11.9998 4.76697 11.9998 4.33297C11.9998 3.78164 11.5512 3.33297 10.9998 3.33297C10.4485 3.33297 9.99984 3.78164 9.99984 4.33297C9.99984 4.76697 10.2792 5.13364 10.6665 5.27164V5.99964H8.6665V3.6663C8.6665 3.52297 8.5745 3.39564 8.4385 3.3503L6.4385 2.68364C6.3405 2.65097 6.23384 2.66564 6.1485 2.7223L4.1485 4.05564C4.05584 4.11764 3.99984 4.22164 3.99984 4.33297V6.12697L2.8505 6.70164C2.73784 6.75831 2.6665 6.87364 2.6665 6.99964V8.99964C2.6665 9.12631 2.73784 9.24164 2.8505 9.29831L3.99984 9.87231V11.6663C3.99984 11.7776 4.05584 11.8823 4.1485 11.9436L6.1485 13.277C6.20384 13.3143 6.26784 13.333 6.33317 13.333C6.3685 13.333 6.40384 13.3276 6.4385 13.3156L8.4385 12.649C8.5745 12.6043 8.6665 12.477 8.6665 12.333V10.6663H10.1952L10.7638 11.2356L10.7725 11.227C10.7072 11.3603 10.6665 11.5083 10.6665 11.6663C10.6665 12.2176 11.1152 12.6663 11.6665 12.6663C12.2178 12.6663 12.6665 12.2176 12.6665 11.6663C12.6665 11.115 12.2178 10.6663 11.6665 10.6663C11.5078 10.6663 11.3598 10.707 11.2272 10.773L11.2358 10.7643L10.5692 10.0976C10.5065 10.035 10.4218 9.99964 10.3332 9.99964H8.6665V8.66631H11.3945Z" fill="white"/>
+</g>
+<defs>
+<linearGradient id="paint0_linear_16762_59518" x1="0" y1="1600" x2="1600" y2="0" gradientUnits="userSpaceOnUse">
+<stop stop-color="#055F4E"/>
+<stop offset="1" stop-color="#56C0A7"/>
+</linearGradient>
+<clipPath id="clip0_16762_59518">
+<rect width="16" height="16" fill="white"/>
+</clipPath>
+</defs>
+</svg>

ai-provider/model-runtime/model-providers/bedrock/bedrock.yaml

@@ -0,0 +1,95 @@
+provider: bedrock
+label:
+  en_US: AWS Bedrock
+description:
+  en_US: AWS Bedrock's models.
+icon_small:
+  en_US: icon_s_en.svg
+icon_large:
+  en_US: icon_l_en.svg
+background: "#FCFDFF"
+help:
+  title:
+    en_US: Get your Access Key and Secret Access Key from AWS Console
+  url:
+    en_US: https://console.aws.amazon.com/
+supported_model_types:
+  - llm
+  - text-embedding
+configurate_methods:
+  - predefined-model
+provider_credential_schema:
+  credential_form_schemas:
+    - variable: aws_access_key_id
+      required: false
+      label:
+        en_US: Access Key (If not provided, credentials are obtained from the running environment.)
+        zh_Hans: Access Key
+      type: secret-input
+      placeholder:
+        en_US: Enter your Access Key
+        zh_Hans: 在此输入您的 Access Key
+    - variable: aws_secret_access_key
+      required: false
+      label:
+        en_US: Secret Access Key
+        zh_Hans: Secret Access Key
+      type: secret-input
+      placeholder:
+        en_US: Enter your Secret Access Key
+        zh_Hans: 在此输入您的 Secret Access Key
+    - variable: aws_region
+      required: true
+      label:
+        en_US: AWS Region
+        zh_Hans: AWS 地区
+      type: select
+      default: us-east-1
+      options:
+        - value: us-east-1
+          label:
+            en_US: US East (N. Virginia)
+            zh_Hans: 美国东部 (弗吉尼亚北部)
+        - value: us-west-2
+          label:
+            en_US: US West (Oregon)
+            zh_Hans: 美国西部 (俄勒冈州)
+        - value: ap-southeast-1
+          label:
+            en_US: Asia Pacific (Singapore)
+            zh_Hans: 亚太地区 (新加坡)
+        - value: ap-northeast-1
+          label:
+            en_US: Asia Pacific (Tokyo)
+            zh_Hans: 亚太地区 (东京)
+        - value: eu-central-1
+          label:
+            en_US: Europe (Frankfurt)
+            zh_Hans: 欧洲 (法兰克福)
+        - value: eu-west-2
+          label:
+            en_US: Eu west London (London)
+            zh_Hans: 欧洲西部 (伦敦)
+        - value: us-gov-west-1
+          label:
+            en_US: AWS GovCloud (US-West)
+            zh_Hans: AWS GovCloud (US-West)
+        - value: ap-southeast-2
+          label:
+            en_US: Asia Pacific (Sydney)
+            zh_Hans: 亚太地区 (悉尼)
+    - variable: model_for_validation
+      required: false
+      label:
+        en_US: Available Model Name
+        zh_Hans: 可用模型名称
+      type: text-input
+      placeholder:
+        en_US: A model you have access to (e.g. amazon.titan-text-lite-v1) for validation.
+        zh_Hans: 为了进行验证，请输入一个您可用的模型名称 (例如：amazon.titan-text-lite-v1)
+model_config:
+  access_configuration_status: true
+  access_configuration_demo: "{\"region\":\"\",\"model\":\"\"}"
+address: https://bedrock-runtime.amazonaws.com
+sort: 4
+recommend: true

ai-provider/model-runtime/model-providers/bedrock/llm/ai21.j2-mid-v1.yaml

@@ -0,0 +1,47 @@
+model: ai21.j2-mid-v1
+label:
+  en_US: J2 Mid V1
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 8191
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: topP
+    use_template: top_p
+  - name: maxTokens
+    use_template: max_tokens
+    required: true
+    default: 2048
+    min: 1
+    max: 2048
+  - name: count_penalty
+    label:
+      en_US: Count Penalty
+    required: false
+    type: float
+    default: 0
+    min: 0
+    max: 1
+  - name: presence_penalty
+    label:
+      en_US: Presence Penalty
+    required: false
+    type: float
+    default: 0
+    min: 0
+    max: 5
+  - name: frequency_penalty
+    label:
+      en_US: Frequency Penalty
+    required: false
+    type: float
+    default: 0
+    min: 0
+    max: 500
+pricing:
+  input: '0.00'
+  output: '0.00'
+  unit: '0.000001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/ai21.j2-ultra-v1.yaml

@@ -0,0 +1,47 @@
+model: ai21.j2-ultra-v1
+label:
+  en_US: J2 Ultra V1
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 8191
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: topP
+    use_template: top_p
+  - name: maxTokens
+    use_template: max_tokens
+    required: true
+    default: 2048
+    min: 1
+    max: 2048
+  - name: count_penalty
+    label:
+      en_US: Count Penalty
+    required: false
+    type: float
+    default: 0
+    min: 0
+    max: 1
+  - name: presence_penalty
+    label:
+      en_US: Presence Penalty
+    required: false
+    type: float
+    default: 0
+    min: 0
+    max: 5
+  - name: frequency_penalty
+    label:
+      en_US: Frequency Penalty
+    required: false
+    type: float
+    default: 0
+    min: 0
+    max: 500
+pricing:
+  input: '0.00'
+  output: '0.00'
+  unit: '0.000001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/ai21.jamba-1-5-large-v1.0.yaml

@@ -0,0 +1,26 @@
+model: ai21.jamba-1-5-large-v1:0
+label:
+  en_US: Jamba 1.5 Large
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 256000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 1
+    min: 0.0
+    max: 2.0
+  - name: top_p
+    use_template: top_p
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 4096
+    min: 1
+    max: 4096
+pricing:
+  input: '0.002'
+  output: '0.008'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/ai21.jamba-1-5-mini-v1.0.yaml

@@ -0,0 +1,26 @@
+model: ai21.jamba-1-5-mini-v1:0
+label:
+  en_US: Jamba 1.5 Mini
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 256000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 1
+    min: 0.0
+    max: 2.0
+  - name: top_p
+    use_template: top_p
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 4096
+    min: 1
+    max: 4096
+pricing:
+  input: '0.0002'
+  output: '0.0004'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/amazon.nova-lite-v1.yaml

@@ -0,0 +1,53 @@
+model: amazon.nova-lite-v1:0
+label:
+  en_US: Nova Lite V1
+model_type: llm
+features:
+  - agent-thought
+  - tool-call
+  - stream-tool-call
+  - vision
+model_properties:
+  mode: chat
+  context_size: 300000
+parameter_rules:
+  - name: max_new_tokens
+    use_template: max_tokens
+    required: true
+    default: 2048
+    min: 1
+    max: 5000
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+pricing:
+  input: '0.00006'
+  output: '0.00024'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/amazon.nova-micro-v1.yaml

@@ -0,0 +1,52 @@
+model: amazon.nova-micro-v1:0
+label:
+  en_US: Nova Micro V1
+model_type: llm
+features:
+  - agent-thought
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 128000
+parameter_rules:
+  - name: max_new_tokens
+    use_template: max_tokens
+    required: true
+    default: 2048
+    min: 1
+    max: 5000
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+pricing:
+  input: '0.000035'
+  output: '0.00014'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/amazon.nova-pro-v1.yaml

@@ -0,0 +1,53 @@
+model: amazon.nova-pro-v1:0
+label:
+  en_US: Nova Pro V1
+model_type: llm
+features:
+  - agent-thought
+  - tool-call
+  - stream-tool-call
+  - vision
+model_properties:
+  mode: chat
+  context_size: 300000
+parameter_rules:
+  - name: max_new_tokens
+    use_template: max_tokens
+    required: true
+    default: 2048
+    min: 1
+    max: 5000
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+pricing:
+  input: '0.0008'
+  output: '0.0032'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/amazon.titan-text-express-v1.yaml

@@ -0,0 +1,23 @@
+model: amazon.titan-text-express-v1
+label:
+  en_US: Titan Text G1 - Express
+model_type: llm
+model_properties:
+  mode: chat
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: topP
+    use_template: top_p
+  - name: maxTokenCount
+    use_template: max_tokens
+    required: true
+    default: 2048
+    min: 1
+    max: 8000
+pricing:
+  input: '0.0008'
+  output: '0.0016'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/amazon.titan-text-lite-v1.yaml

@@ -0,0 +1,23 @@
+model: amazon.titan-text-lite-v1
+label:
+  en_US: Titan Text G1 - Lite
+model_type: llm
+model_properties:
+  mode: chat
+  context_size: 4096
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: topP
+    use_template: top_p
+  - name: maxTokenCount
+    use_template: max_tokens
+    required: true
+    default: 2048
+    min: 1
+    max: 2048
+pricing:
+  input: '0.0003'
+  output: '0.0004'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/anthropic.claude-3-5-haiku-v1.yaml

@@ -0,0 +1,60 @@
+model: anthropic.claude-3-5-haiku-20241022-v1:0
+label:
+  en_US: Claude 3.5 Haiku
+model_type: llm
+features:
+  - agent-thought
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 8192
+    min: 1
+    max: 8192
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  # docs: https://docs.anthropic.com/claude/docs/system-prompts
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.001'
+  output: '0.005'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/anthropic.claude-3-haiku-v1.yaml

@@ -0,0 +1,61 @@
+model: anthropic.claude-3-haiku-20240307-v1:0
+label:
+  en_US: Claude 3 Haiku
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  # docs: https://docs.anthropic.com/claude/docs/system-prompts
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.00025'
+  output: '0.00125'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/anthropic.claude-3-opus-v1.yaml

@@ -0,0 +1,61 @@
+model: anthropic.claude-3-opus-20240229-v1:0
+label:
+  en_US: Claude 3 Opus
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  # docs: https://docs.anthropic.com/claude/docs/system-prompts
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.015'
+  output: '0.075'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/anthropic.claude-3-sonnet-v1.5.yaml

@@ -0,0 +1,60 @@
+model: anthropic.claude-3-5-sonnet-20240620-v1:0
+label:
+  en_US: Claude 3.5 Sonnet
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.003'
+  output: '0.015'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/anthropic.claude-3-sonnet-v1.yaml

@@ -0,0 +1,60 @@
+model: anthropic.claude-3-sonnet-20240229-v1:0
+label:
+  en_US: Claude 3 Sonnet
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.003'
+  output: '0.015'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/anthropic.claude-3-sonnet-v2.yaml

@@ -0,0 +1,60 @@
+model: anthropic.claude-3-5-sonnet-20241022-v2:0
+label:
+  en_US: Claude 3.5 Sonnet V2
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 8192
+    min: 1
+    max: 8192
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.003'
+  output: '0.015'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/anthropic.claude-instant-v1.yaml

@@ -0,0 +1,52 @@
+model: anthropic.claude-instant-v1
+label:
+  en_US: Claude Instant 1
+model_type: llm
+model_properties:
+  mode: chat
+  context_size: 100000
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+pricing:
+  input: '0.0008'
+  output: '0.0024'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/anthropic.claude-v1.yaml

@@ -0,0 +1,53 @@
+model: anthropic.claude-v1
+label:
+  en_US: Claude 1
+model_type: llm
+model_properties:
+  mode: chat
+  context_size: 100000
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+pricing:
+  input: '0.008'
+  output: '0.024'
+  unit: '0.001'
+  currency: USD
+deprecated: true

ai-provider/model-runtime/model-providers/bedrock/llm/anthropic.claude-v2.1.yaml

@@ -0,0 +1,54 @@
+model: anthropic.claude-v2:1
+label:
+  en_US: Claude 2.1
+model_type: llm
+model_properties:
+  mode: chat
+  context_size: 200000
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.008'
+  output: '0.024'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/anthropic.claude-v2.yaml

@@ -0,0 +1,54 @@
+model: anthropic.claude-v2
+label:
+  en_US: Claude 2
+model_type: llm
+model_properties:
+  mode: chat
+  context_size: 100000
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.008'
+  output: '0.024'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/cohere.command-light-text-v14.yaml

@@ -0,0 +1,35 @@
+model: cohere.command-light-text-v14
+label:
+  en_US: Command Light Text V14
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 4096
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: p
+    use_template: top_p
+  - name: k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+    min: 0
+    max: 500
+    default: 0
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 4096
+    min: 1
+    max: 4096
+pricing:
+  input: '0.0003'
+  output: '0.0006'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/cohere.command-r-plus-v1.0.yaml

@@ -0,0 +1,44 @@
+model: cohere.command-r-plus-v1:0
+label:
+  en_US: Command R+
+model_type: llm
+features:
+  - tool-call
+  #- stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    max: 5.0
+  - name: p
+    use_template: top_p
+    default: 0.75
+    min: 0.01
+    max: 0.99
+  - name: k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+    default: 0
+    min: 0
+    max: 500
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty
+  - name: max_tokens
+    use_template: max_tokens
+    default: 1024
+    max: 4096
+pricing:
+  input: '3'
+  output: '15'
+  unit: '0.000001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/cohere.command-r-v1.0.yaml

@@ -0,0 +1,43 @@
+model: cohere.command-r-v1:0
+label:
+  en_US: Command R
+model_type: llm
+features:
+  - tool-call
+model_properties:
+  mode: chat
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    max: 5.0
+  - name: p
+    use_template: top_p
+    default: 0.75
+    min: 0.01
+    max: 0.99
+  - name: k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+    default: 0
+    min: 0
+    max: 500
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty
+  - name: max_tokens
+    use_template: max_tokens
+    default: 1024
+    max: 4096
+pricing:
+  input: '0.5'
+  output: '1.5'
+  unit: '0.000001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/cohere.command-text-v14.yaml

@@ -0,0 +1,32 @@
+model: cohere.command-text-v14
+label:
+  en_US: Command Text V14
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 4096
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: p
+    use_template: top_p
+  - name: k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 4096
+    min: 1
+    max: 4096
+pricing:
+  input: '0.0015'
+  output: '0.0020'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/eu.anthropic.claude-3-haiku-v1.yaml

@@ -0,0 +1,59 @@
+model: eu.anthropic.claude-3-haiku-20240307-v1:0
+label:
+  en_US: Claude 3 Haiku(EU.Cross Region Inference)
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  # docs: https://docs.anthropic.com/claude/docs/system-prompts
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+pricing:
+  input: '0.00025'
+  output: '0.00125'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/eu.anthropic.claude-3-sonnet-v1.5.yaml

@@ -0,0 +1,58 @@
+model: eu.anthropic.claude-3-5-sonnet-20240620-v1:0
+label:
+  en_US: Claude 3.5 Sonnet(EU.Cross Region Inference)
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+pricing:
+  input: '0.003'
+  output: '0.015'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/eu.anthropic.claude-3-sonnet-v1.yaml

@@ -0,0 +1,58 @@
+model: eu.anthropic.claude-3-sonnet-20240229-v1:0
+label:
+  en_US: Claude 3 Sonnet(EU.Cross Region Inference)
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+pricing:
+  input: '0.003'
+  output: '0.015'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/eu.anthropic.claude-3-sonnet-v2.yaml

@@ -0,0 +1,60 @@
+model: eu.anthropic.claude-3-5-sonnet-20241022-v2:0
+label:
+  en_US: Claude 3.5 Sonnet V2(EU.Cross Region Inference)
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.003'
+  output: '0.015'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/meta.llama2-13b-chat-v1.yaml

@@ -0,0 +1,23 @@
+model: meta.llama2-13b-chat-v1
+label:
+  en_US: Llama 2 Chat 13B
+model_type: llm
+model_properties:
+  mode: chat
+  context_size: 4096
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 2048
+    min: 1
+    max: 2048
+pricing:
+  input: '0.00075'
+  output: '0.00100'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/meta.llama2-70b-chat-v1.yaml

@@ -0,0 +1,23 @@
+model: meta.llama2-70b-chat-v1
+label:
+  en_US: Llama 2 Chat 70B
+model_type: llm
+model_properties:
+  mode: chat
+  context_size: 4096
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 2048
+    min: 1
+    max: 2048
+pricing:
+  input: '0.00195'
+  output: '0.00256'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/meta.llama3-1-405b-instruct-v1.0.yaml

@@ -0,0 +1,25 @@
+model: meta.llama3-1-405b-instruct-v1:0
+label:
+  en_US: Llama 3.1 405B Instruct
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.5
+  - name: top_p
+    use_template: top_p
+    default: 0.9
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.00532'
+  output: '0.016'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/meta.llama3-1-70b-instruct-v1.0.yaml

@@ -0,0 +1,25 @@
+model: meta.llama3-1-70b-instruct-v1:0
+label:
+  en_US: Llama 3.1 Instruct 70B
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.5
+  - name: top_p
+    use_template: top_p
+    default: 0.9
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.00265'
+  output: '0.0035'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/meta.llama3-1-8b-instruct-v1.0.yaml

@@ -0,0 +1,25 @@
+model: meta.llama3-1-8b-instruct-v1:0
+label:
+  en_US: Llama 3.1 Instruct 8B
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.5
+  - name: top_p
+    use_template: top_p
+    default: 0.9
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.0003'
+  output: '0.0006'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/meta.llama3-70b-instruct-v1.yaml

@@ -0,0 +1,23 @@
+model: meta.llama3-70b-instruct-v1:0
+label:
+  en_US: Llama 3 Instruct 70B
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.00265'
+  output: '0.0035'
+  unit: '0.00001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/meta.llama3-8b-instruct-v1.yaml

@@ -0,0 +1,23 @@
+model: meta.llama3-8b-instruct-v1:0
+label:
+  en_US: Llama 3 Instruct 8B
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 8192
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.0004'
+  output: '0.0006'
+  unit: '0.0001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/mistral.mistral-7b-instruct-v0.2.yaml

@@ -0,0 +1,39 @@
+model: mistral.mistral-7b-instruct-v0:2
+label:
+  en_US: Mistral 7B Instruct
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 32000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    required: false
+    default: 0.5
+  - name: top_p
+    use_template: top_p
+    required: false
+    default: 0.9
+  - name: top_k
+    use_template: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+    default: 50
+    max: 200
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 8192
+pricing:
+  input: '0.00015'
+  output: '0.0002'
+  unit: '0.00001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/mistral.mistral-large-2402-v1.0.yaml

@@ -0,0 +1,30 @@
+model: mistral.mistral-large-2402-v1:0
+label:
+  en_US: Mistral Large
+model_type: llm
+features:
+  - tool-call
+  - agent-thought
+model_properties:
+  mode: completion
+  context_size: 32000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    required: false
+    default: 0.7
+  - name: top_p
+    use_template: top_p
+    required: false
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 4096
+pricing:
+  input: '0.008'
+  output: '0.024'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/mistral.mistral-large-2407-v1.0.yaml

@@ -0,0 +1,29 @@
+model: mistral.mistral-large-2407-v1:0
+label:
+  en_US: Mistral Large 2 (24.07)
+model_type: llm
+features:
+  - tool-call
+model_properties:
+  mode: completion
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    required: false
+    default: 0.7
+  - name: top_p
+    use_template: top_p
+    required: false
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 8192
+pricing:
+  input: '0.003'
+  output: '0.009'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/mistral.mistral-small-2402-v1.0.yaml

@@ -0,0 +1,29 @@
+model: mistral.mistral-small-2402-v1:0
+label:
+  en_US: Mistral Small
+model_type: llm
+features:
+  - tool-call
+model_properties:
+  mode: completion
+  context_size: 32000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    required: false
+    default: 0.7
+  - name: top_p
+    use_template: top_p
+    required: false
+    default: 1
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 4096
+pricing:
+  input: '0.001'
+  output: '0.03'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/mistral.mixtral-8x7b-instruct-v0.1.yaml

@@ -0,0 +1,39 @@
+model: mistral.mixtral-8x7b-instruct-v0:1
+label:
+  en_US: Mixtral 8X7B Instruct
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 32000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    required: false
+    default: 0.5
+  - name: top_p
+    use_template: top_p
+    required: false
+    default: 0.9
+  - name: top_k
+    use_template: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+    default: 50
+    max: 200
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 8192
+pricing:
+  input: '0.00045'
+  output: '0.0007'
+  unit: '0.00001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/us.amazon.nova-lite-v1.yaml

@@ -0,0 +1,53 @@
+model: us.amazon.nova-lite-v1:0
+label:
+  en_US: Nova Lite V1 (US.Cross Region Inference)
+model_type: llm
+features:
+  - agent-thought
+  - tool-call
+  - stream-tool-call
+  - vision
+model_properties:
+  mode: chat
+  context_size: 300000
+parameter_rules:
+  - name: max_new_tokens
+    use_template: max_tokens
+    required: true
+    default: 2048
+    min: 1
+    max: 5000
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+pricing:
+  input: '0.00006'
+  output: '0.00024'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/us.amazon.nova-micro-v1.yaml

@@ -0,0 +1,52 @@
+model: us.amazon.nova-micro-v1:0
+label:
+  en_US: Nova Micro V1 (US.Cross Region Inference)
+model_type: llm
+features:
+  - agent-thought
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 128000
+parameter_rules:
+  - name: max_new_tokens
+    use_template: max_tokens
+    required: true
+    default: 2048
+    min: 1
+    max: 5000
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+pricing:
+  input: '0.000035'
+  output: '0.00014'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/us.amazon.nova-pro-v1.yaml

@@ -0,0 +1,53 @@
+model: us.amazon.nova-pro-v1:0
+label:
+  en_US: Nova Pro V1 (US.Cross Region Inference)
+model_type: llm
+features:
+  - agent-thought
+  - tool-call
+  - stream-tool-call
+  - vision
+model_properties:
+  mode: chat
+  context_size: 300000
+parameter_rules:
+  - name: max_new_tokens
+    use_template: max_tokens
+    required: true
+    default: 2048
+    min: 1
+    max: 5000
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+pricing:
+  input: '0.0008'
+  output: '0.0032'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/us.anthropic.claude-3-5-haiku-v1.yaml

@@ -0,0 +1,60 @@
+model: us.anthropic.claude-3-5-haiku-20241022-v1:0
+label:
+  en_US: Claude 3.5 Haiku(US.Cross Region Inference)
+model_type: llm
+features:
+  - agent-thought
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 8192
+    min: 1
+    max: 8192
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  # docs: https://docs.anthropic.com/claude/docs/system-prompts
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.001'
+  output: '0.005'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/us.anthropic.claude-3-haiku-v1.yaml

@@ -0,0 +1,59 @@
+model: us.anthropic.claude-3-haiku-20240307-v1:0
+label:
+  en_US: Claude 3 Haiku(US.Cross Region Inference)
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  # docs: https://docs.anthropic.com/claude/docs/system-prompts
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+pricing:
+  input: '0.00025'
+  output: '0.00125'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/us.anthropic.claude-3-opus-v1.yaml

@@ -0,0 +1,59 @@
+model: us.anthropic.claude-3-opus-20240229-v1:0
+label:
+  en_US: Claude 3 Opus(US.Cross Region Inference)
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  # docs: https://docs.anthropic.com/claude/docs/system-prompts
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+pricing:
+  input: '0.015'
+  output: '0.075'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/us.anthropic.claude-3-sonnet-v1.5.yaml

@@ -0,0 +1,58 @@
+model: us.anthropic.claude-3-5-sonnet-20240620-v1:0
+label:
+  en_US: Claude 3.5 Sonnet(US.Cross Region Inference)
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+pricing:
+  input: '0.003'
+  output: '0.015'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/us.anthropic.claude-3-sonnet-v1.yaml

@@ -0,0 +1,58 @@
+model: us.anthropic.claude-3-sonnet-20240229-v1:0
+label:
+  en_US: Claude 3 Sonnet(US.Cross Region Inference)
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 4096
+    min: 1
+    max: 4096
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+pricing:
+  input: '0.003'
+  output: '0.015'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/us.anthropic.claude-3-sonnet-v2.yaml

@@ -0,0 +1,60 @@
+model: us.anthropic.claude-3-5-sonnet-20241022-v2:0
+label:
+  en_US: Claude 3.5 Sonnet V2(US.Cross Region Inference)
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 200000
+# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
+parameter_rules:
+  - name: max_tokens
+    use_template: max_tokens
+    required: true
+    type: int
+    default: 8192
+    min: 1
+    max: 8192
+    help:
+      zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
+      en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
+  - name: temperature
+    use_template: temperature
+    required: false
+    type: float
+    default: 1
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 生成内容的随机性。
+      en_US: The amount of randomness injected into the response.
+  - name: top_p
+    required: false
+    type: float
+    default: 0.999
+    min: 0.000
+    max: 1.000
+    help:
+      zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
+      en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
+  - name: top_k
+    required: false
+    type: int
+    default: 0
+    min: 0
+    # tip docs from aws has error, max value is 500
+    max: 500
+    help:
+      zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
+      en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
+  - name: response_format
+    use_template: response_format
+pricing:
+  input: '0.003'
+  output: '0.015'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/us.meta.llama3-2-11b-instruct-v1.0.yaml

@@ -0,0 +1,29 @@
+model: us.meta.llama3-2-11b-instruct-v1:0
+label:
+  en_US: US Meta Llama 3.2 11B Instruct
+model_type: llm
+features:
+  - vision
+  - tool-call
+model_properties:
+  mode: completion
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.5
+    min: 0.0
+    max: 1
+  - name: top_p
+    use_template: top_p
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.00035'
+  output: '0.00035'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/us.meta.llama3-2-1b-instruct-v1.0.yaml

@@ -0,0 +1,26 @@
+model: us.meta.llama3-2-1b-instruct-v1:0
+label:
+  en_US: US Meta Llama 3.2 1B Instruct
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.5
+    min: 0.0
+    max: 1
+  - name: top_p
+    use_template: top_p
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.0001'
+  output: '0.0001'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/us.meta.llama3-2-3b-instruct-v1.0.yaml

@@ -0,0 +1,26 @@
+model: us.meta.llama3-2-3b-instruct-v1:0
+label:
+  en_US: US Meta Llama 3.2 3B Instruct
+model_type: llm
+model_properties:
+  mode: completion
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.5
+    min: 0.0
+    max: 1
+  - name: top_p
+    use_template: top_p
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.00015'
+  output: '0.00015'
+  unit: '0.001'
+  currency: USD

ai-provider/model-runtime/model-providers/bedrock/llm/us.meta.llama3-2-90b-instruct-v1.0.yaml

@@ -0,0 +1,31 @@
+model: us.meta.llama3-2-90b-instruct-v1:0
+label:
+  en_US: US Meta Llama 3.2 90B Instruct
+model_type: llm
+features:
+  - tool-call
+model_properties:
+  mode: completion
+  context_size: 128000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.5
+    min: 0.0
+    max: 1
+  - name: top_p
+    use_template: top_p
+    default: 0.9
+    min: 0
+    max: 1
+  - name: max_gen_len
+    use_template: max_tokens
+    required: true
+    default: 512
+    min: 1
+    max: 2048
+pricing:
+  input: '0.002'
+  output: '0.002'
+  unit: '0.001'
+  currency: USD