codemie-sdk-python 0.1.249__tar.gz → 0.1.258__tar.gz

{codemie_sdk_python-0.1.249 → codemie_sdk_python-0.1.258}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: codemie-sdk-python
-Version: 0.1.249
+Version: 0.1.258
 Summary: CodeMie SDK for Python
 Author: Vadym Vlasenko
 Author-email: vadym_vlasenko@epam.com
@@ -26,6 +26,7 @@ Python SDK for CodeMie services. This SDK provides a comprehensive interface to
     - [Core Methods](#core-methods)
     - [Advanced Features](#advanced-features)
     - [Prompt Variables Support](#prompt-variables-support)
+    - [Assistant Versioning](#assistant-versioning)
   - [Datasource Service](#datasource-service)
     - [Supported Datasource Types](#supported-datasource-types)
     - [Core Methods](#core-methods-1)
@@ -44,30 +45,35 @@ Python SDK for CodeMie services. This SDK provides a comprehensive interface to
     - [Workflow Status Monitoring](#workflow-status-monitoring)
   - [Conversation Service](#conversation-service)
     - [Core Methods](#core-methods-4)
-  - [Webhook Service](#webhook-service)
+  - [File Service](#file-service)
     - [Core Methods](#core-methods-5)
-- [Development](#development)
-  - [Setup](#setup)
-  - [Running Tests](#running-tests)
-  - [Building Package](#building-package)
+  - [User Service](#user-service)
+    - [Core Methods](#core-methods-6)
+  - [Task Service](#task-service)
+    - [Core Methods](#core-methods-7)
+  - [Webhook Service](#webhook-service)
+    - [Core Methods](#core-methods-8)
+  - [Vendor Services](#vendor-services)
+    - [Vendor Assistant Service](#vendor-assistant-service)
+    - [Vendor Workflow Service](#vendor-workflow-service)
+    - [Vendor Knowledge Base Service](#vendor-knowledge-base-service)
+    - [Vendor Guardrail Service](#vendor-guardrail-service)
 - [Error Handling](#error-handling-1)
 - [Authentication](#authentication)
   - [Required Parameters](#required-parameters)
   - [Usage Examples](#usage-examples)
 - [Best Practices](#best-practices-1)
 - [Support](#support)
+- [Development](#development)
+  - [Setup](#setup)
+  - [Code Quality](#code-quality)
+  - [Building Package](#building-package)
 
 ## Installation
 
 ```sh
 pip install codemie-sdk-python
 ```
-OR
-```sh
-poetry install
-```
-
-### If you want to run only tests, go to ## Running tests section
 
 ## Usage
 
@@ -90,30 +96,25 @@ client = CodeMieClient(
 
 ### LLM Service
 
-The LLM service provides access to language models and embedding models:
+The LLM service provides access to language models and embedding models.
 
-- **list()**: Retrieves a list of available LLM models
-  ```python
-  llm_models = client.llm.list(token=client.token)
-  ```
+**Available Methods:**
 
-- **list_embeddings()**: Retrieves a list of available embedding models
-  ```python
-  embedding_models = client.llm.list_embeddings(token=client.token)
-  ```
+1. **list()** - Retrieves a list of available LLM models
+2. **list_embeddings()** - Retrieves a list of available embedding models
 
-Each LLM model contains the following information:
+Each LLM model contains:
 - Model identifier
 - Model capabilities
 - Configuration parameters
 
-Example usage:
+**Example:**
 ```python
 # List available LLM models
-llm_models = client.llm.list(token=client.token)
+llm_models = client.llms.list()
 
 # List available embedding models
-embedding_models = client.llm.list_embeddings(token=client.token)
+embedding_models = client.llms.list_embeddings()
 ```
 
 ### Assistant Service
@@ -124,7 +125,7 @@ The Assistant service allows you to manage and interact with CodeMie assistants:
 
 1. **List Assistants**
 ```python
-assistants = client.assistant.list(
+assistants = client.assistants.list(
     minimal_response=True,  # Return minimal assistant info
     scope="visible_to_user",  # or "created_by_user"
     page=0,
@@ -136,10 +137,10 @@ assistants = client.assistant.list(
 2. **Get Assistant Details**
 ```python
 # By ID
-assistant = client.assistant.get("assistant-id")
+assistant = client.assistants.get("assistant-id")
 
 # By Slug
-assistant = client.assistant.get_by_slug("assistant-slug")
+assistant = client.assistants.get_by_slug("assistant-slug")
 ```
 
 3. **Create Assistant**
@@ -153,7 +154,7 @@ request = AssistantCreateRequest(
     tools=["tool1", "tool2"],
     # Additional parameters as needed
 )
-new_assistant = client.assistant.create(request)
+new_assistant = client.assistants.create(request)
 ```
 
 4. **Update Assistant**
@@ -165,12 +166,12 @@ request = AssistantUpdateRequest(
     description="Updated description",
     # Other fields to update
 )
-updated_assistant = client.assistant.update("assistant-id", request)
+updated_assistant = client.assistants.update("assistant-id", request)
 ```
 
 5. **Delete Assistant**
 ```python
-result = client.assistant.delete("assistant-id")
+result = client.assistants.delete("assistant-id")
 ```
 
 #### Advanced Features
@@ -185,7 +186,7 @@ chat_request = AssistantChatRequest(
     propagate_headers=True,  # Enable propagation of X-* headers to MCP servers
 )
 # Pass X-* headers to forward to MCP servers
-response = client.assistant.chat(
+response = client.assistants.chat(
     "assistant-id",
     chat_request,
     headers={
@@ -196,7 +197,7 @@ response = client.assistant.chat(
 )
 ```
 
-6.a. **Chat with Assistant by slug (with MCP header propagation)**
+7. **Chat with Assistant by slug (with MCP header propagation)**
 ```python
 chat_request = AssistantChatRequest(
     text="Your message here",
@@ -212,7 +213,7 @@ response = client.assistants.chat_by_slug(
 )
 ```
 
-7. **Utilize structured outputs with Assistant**
+8. **Utilize structured outputs with Assistant**
 ```python
 from pydantic import BaseModel
 
@@ -221,8 +222,8 @@ class OutputSchema(BaseModel):
 
 chat_request = AssistantChatRequest(
     text="Your message here",
-    stream=False, 
-    output_schema=OutputSchema
+    stream=False,
+    output_schema=OutputSchema,
     # Additional parameters
 )
 
@@ -246,30 +247,31 @@ output_schema = {
 
 chat_request = AssistantChatRequest(
     text="Your message here",
-    stream=False, 
-    output_schema=output_schema 
+    stream=False,
+    output_schema=output_schema,
     # Additional parameters
 )
 
 response = client.assistants.chat("id", chat_request)
-# response.generated is a dict corresponded with JSON schema
+# response.generated is a dict corresponding to the JSON schema
 ```
 
-8. **Work with Prebuilt Assistants**
+9. **Work with Prebuilt Assistants**
 ```python
 # List prebuilt assistants
-prebuilt = client.assistant.get_prebuilt()
+prebuilt = client.assistants.get_prebuilt()
 
 # Get specific prebuilt assistant
-prebuilt_assistant = client.assistant.get_prebuilt_by_slug("assistant-slug")
+prebuilt_assistant = client.assistants.get_prebuilt_by_slug("assistant-slug")
 ```
 
-9. **Get Available Tools**
+10. **Get Available Tools**
 ```python
-tools = client.assistant.get_tools()
+tools = client.assistants.get_tools()
 ```
 
-### Prompt Variables Support
+#### Prompt Variables Support
+
 The SDK supports assistant-level prompt variables that the backend already exposes via the `prompt_variables` field.
 
 Create and update an assistant with prompt variables:
@@ -304,6 +306,52 @@ update_req = AssistantUpdateRequest(
     ],
 )
 client.assistants.update("assistant-id", update_req)
+```
+
+#### Assistant Versioning
+
+The SDK provides full assistant versioning capabilities.
+
+1. **List Versions**
+```python
+# Get all versions of an assistant
+versions = client.assistants.list_versions("assistant-id", page=0, per_page=20)
+for version in versions:
+    print(f"Version {version.version_number}")
+```
+
+2. **Get Specific Version**
+```python
+# Get details of a specific version
+version = client.assistants.get_version("assistant-id", version_number=2)
+print(version.system_prompt)
+```
+
+3. **Compare Versions**
+```python
+from codemie_sdk.models.assistant import AssistantVersionDiff
+
+# Compare two versions to see what changed
+diff = client.assistants.compare_versions("assistant-id", version1=1, version2=3)
+print(diff.summary)
+```
+
+4. **Rollback to Version**
+```python
+# Rollback assistant to a previous version
+response = client.assistants.rollback_to_version("assistant-id", version_number=2)
+print(f"Rolled back to version {response.version_number}")
+```
+
+5. **Chat with Specific Version**
+```python
+from codemie_sdk.models.assistant import AssistantChatRequest
+
+# Chat with a specific version of the assistant
+request = AssistantChatRequest(text="Hi", stream=False)
+response = client.assistants.chat_with_version("assistant-id", version_number=2, request)
+print(response.generated)
+```
 
 ### Datasource Service
 
@@ -316,6 +364,7 @@ The Datasource service enables managing various types of data sources in CodeMie
 - `JIRA`: Jira knowledge base
 - `FILE`: File-based knowledge base
 - `GOOGLE`: Google documents
+- `AZURE_DEVOPS_WIKI`: Azure DevOps Wiki knowledge base (requires Azure DevOps integration)
 
 #### Core Methods
 
@@ -325,7 +374,8 @@ from codemie_sdk.models.datasource import (
     CodeDataSourceRequest,
     ConfluenceDataSourceRequest,
     JiraDataSourceRequest,
-    GoogleDataSourceRequest
+    GoogleDataSourceRequest,
+    AzureDevOpsWikiDataSourceRequest
 )
 
 # Create Code Datasource
@@ -341,7 +391,7 @@ code_request = CodeDataSourceRequest(
     summarization_model="gpt-4",  # optional
     docs_generation=False  # optional
 )
-result = client.datasource.create(code_request)
+result = client.datasources.create(code_request)
 
 # Create Confluence Datasource
 confluence_request = ConfluenceDataSourceRequest(
@@ -354,7 +404,7 @@ confluence_request = ConfluenceDataSourceRequest(
     include_attachments=True,
     include_comments=True
 )
-result = client.datasource.create(confluence_request)
+result = client.datasources.create(confluence_request)
 
 # Create Jira Datasource
 jira_request = JiraDataSourceRequest(
@@ -363,7 +413,7 @@ jira_request = JiraDataSourceRequest(
     description="Jira project",
     jql="project = 'MYPROJECT'"
 )
-result = client.datasource.create(jira_request)
+result = client.datasources.create(jira_request)
 
 # Create Google Doc Datasource
 google_request = GoogleDataSourceRequest(
@@ -372,12 +422,39 @@ google_request = GoogleDataSourceRequest(
     description="Google document",
     google_doc="document_url"
 )
-result = client.datasource.create(google_request)
+result = client.datasources.create(google_request)
+
+# Create Azure DevOps Wiki Datasource
+# Note: Requires Azure DevOps integration to be configured
+ado_wiki_request = AzureDevOpsWikiDataSourceRequest(
+    name="ado_wiki",
+    project_name="my_project",
+    description="Azure DevOps Wiki",
+    setting_id="azure-devops-integration-id",  # Integration ID with ADO credentials
+    wiki_query="*",  # Path filter (see wiki_query format below)
+    wiki_name="MyProject.wiki"  # Optional: specific wiki name (leave empty for all wikis)
+)
+result = client.datasources.create(ado_wiki_request)
+
+# Important: wiki_query Path Format
+# The page path should NOT include "/Overview/Wiki" and must start from the page level.
+#
+# Example: If your Azure DevOps breadcrumbs show:
+#   "ProjectName/WikiName/Overview/Wiki/Page1/Page2"
+#
+# Then use: "/Page1/*" as the path
+#
+# Build the path using breadcrumb values, NOT the page URL.
+#
+# Common patterns:
+#   - "*" - Index all pages in the wiki
+#   - "/Engineering/*" - Index all pages under /Engineering folder
+#   - "/Engineering/Architecture" - Index only the Architecture page
 ```
 
 2. **Update Datasource**
 ```python
-from codemie_sdk.models.datasource import UpdateCodeDataSourceRequest
+from codemie_sdk.models.datasource import UpdateCodeDataSourceRequest, UpdateAzureDevOpsWikiDataSourceRequest
 
 # Update Code Datasource
 update_request = UpdateCodeDataSourceRequest(
@@ -389,18 +466,36 @@ update_request = UpdateCodeDataSourceRequest(
     skip_reindex=False,
     resume_indexing=False
 )
-result = client.datasource.update("datasource_id", update_request)
+result = client.datasources.update("datasource_id", update_request)
+
+# Update Azure DevOps Wiki Datasource
+ado_update_request = UpdateAzureDevOpsWikiDataSourceRequest(
+    name="ado_wiki",
+    project_name="my_project",
+    description="Updated description",
+    wiki_query="/Engineering/*",  # Update path filter (see wiki_query format above)
+    wiki_name="MyProject.wiki",
+    full_reindex=True  # Trigger full reindex
+)
+result = client.datasources.update("datasource_id", ado_update_request)
 ```
 
+**Reindex Options for Azure DevOps Wiki:**
+Azure DevOps Wiki datasources support the following reindex options:
+- `full_reindex=True` - Completely reindex all pages (clears existing data and reindexes)
+- `skip_reindex=True` - Update metadata without reindexing content
+
+Note: Azure DevOps Wiki does not support `incremental_reindex` or `resume_indexing` options.
+
 3. **List Datasources**
 ```python
 # List all datasources with filtering and pagination
-datasources = client.datasource.list(
+datasources = client.datasources.list(
     page=0,
     per_page=10,
     sort_key="update_date",  # or "date"
     sort_order="desc",  # or "asc"
-    datasource_types=["CODE", "CONFLUENCE"],  # optional filter by type
+    datasource_types=["CODE", "CONFLUENCE", "AZURE_DEVOPS_WIKI"],  # optional filter by type
     projects=["project1", "project2"],  # optional filter by projects
     owner="John Doe",  # optional filter by owner
     status="COMPLETED"  # optional filter by status
@@ -410,13 +505,20 @@ datasources = client.datasource.list(
 4. **Get Datasource Details**
 ```python
 # Get single datasource by ID
-datasource = client.datasource.get("datasource_id")
+datasource = client.datasources.get("datasource_id")
+
+# Access Azure DevOps Wiki specific fields
+if datasource.type == "knowledge_base_azure_devops_wiki":
+    wiki_info = datasource.azure_devops_wiki
+    if wiki_info:
+        print(f"Wiki Query: {wiki_info.wiki_query}")
+        print(f"Wiki Name: {wiki_info.wiki_name}")
 ```
 
 5. **Delete Datasource**
 ```python
 # Delete datasource by ID
-result = client.datasource.delete("datasource_id")
+result = client.datasources.delete("datasource_id")
 ```
 
 #### Datasource Status
@@ -464,7 +566,7 @@ The Integration service manages both user and project-level integrations in Code
 from codemie_sdk.models.integration import IntegrationType
 
 # List user integrations with pagination
-user_integrations = client.integration.list(
+user_integrations = client.integrations.list(
     setting_type=IntegrationType.USER,
     page=0,
     per_page=10,
@@ -472,7 +574,7 @@ user_integrations = client.integration.list(
 )
 
 # List project integrations
-project_integrations = client.integration.list(
+project_integrations = client.integrations.list(
     setting_type=IntegrationType.PROJECT,
     per_page=100
 )
@@ -481,13 +583,13 @@ project_integrations = client.integration.list(
 2. **Get Integration**
 ```python
 # Get integration by ID
-integration = client.integration.get(
+integration = client.integrations.get(
     integration_id="integration_id",
     setting_type=IntegrationType.USER
 )
 
 # Get integration by alias
-integration = client.integration.get_by_alias(
+integration = client.integrations.get_by_alias(
     alias="integration_alias",
     setting_type=IntegrationType.PROJECT
 )
@@ -503,7 +605,7 @@ new_integration = Integration(
     alias="my_integration",
     # Add other required fields based on integration type
 )
-result = client.integration.create(new_integration)
+result = client.integrations.create(new_integration)
 ```
 
 4. **Update Integration**
@@ -514,13 +616,13 @@ updated_integration = Integration(
     alias="updated_alias",
     # Add other fields to update
 )
-result = client.integration.update("integration_id", updated_integration)
+result = client.integrations.update("integration_id", updated_integration)
 ```
 
 5. **Delete Integration**
 ```python
 # Delete integration
-result = client.integration.delete(
+result = client.integrations.delete(
     setting_id="integration_id",
     setting_type=IntegrationType.USER
 )
@@ -564,7 +666,7 @@ workflow_request = WorkflowCreateRequest(
     shared=False,       # Optional, defaults to False
     icon_url="https://example.com/icon.png"  # Optional
 )
-result = client.workflow.create_workflow(workflow_request)
+result = client.workflows.create_workflow(workflow_request)
 ```
 
 2. **Update Workflow**
@@ -579,13 +681,13 @@ update_request = WorkflowUpdateRequest(
     mode="PARALLEL",
     shared=True
 )
-result = client.workflow.update("workflow-id", update_request)
+result = client.workflows.update("workflow-id", update_request)
 ```
 
 3. **List Workflows**
 ```python
 # List workflows with pagination and filtering
-workflows = client.workflow.list(
+workflows = client.workflows.list(
     page=0,
     per_page=10,
     projects=["project1", "project2"]  # Optional project filter
@@ -595,15 +697,15 @@ workflows = client.workflow.list(
 4. **Get Workflow Details**
 ```python
 # Get workflow by ID
-workflow = client.workflow.get("workflow-id")
+workflow = client.workflows.get("workflow-id")
 
 # Get prebuilt workflows
-prebuilt_workflows = client.workflow.get_prebuilt()
+prebuilt_workflows = client.workflows.get_prebuilt()
 ```
 
 5. **Delete Workflow**
 ```python
-result = client.workflow.delete("workflow-id")
+result = client.workflows.delete("workflow-id")
 ```
 
 #### Workflow Execution
@@ -613,7 +715,7 @@ The SDK provides comprehensive workflow execution management through the Workflo
 1. **Run Workflow (with MCP header propagation)**
 ```python
 # Enable propagation in payload and pass X-* headers to forward to MCP servers
-execution = client.workflow.run(
+execution = client.workflows.run(
     "workflow-id",
     user_input="optional input",
     propagate_headers=True,
@@ -624,7 +726,7 @@ execution = client.workflow.run(
 )
 
 # Get execution service for advanced operations
-execution_service = client.workflow.executions("workflow-id")
+execution_service = client.workflows.executions("workflow-id")
 ```
 
 2. **Manage Executions**
@@ -750,7 +852,7 @@ Implement proper error handling for workflow operations:
 
 ```python
 try:
-    workflow = client.workflow.get("workflow-id")
+    workflow = client.workflows.get("workflow-id")
 except ApiError as e:
     if e.status_code == 404:
         print("Workflow not found")
@@ -814,18 +916,374 @@ client.conversations.delete("conversation-id")
 ```
 
 
+### File Service
+
+The File service enables file upload and download operations in CodeMie.
+
+#### Core Methods
+
+1. **Bulk Upload Files**
+```python
+from pathlib import Path
+
+# Upload multiple files
+files = [
+    Path("/path/to/file1.pdf"),
+    Path("/path/to/file2.txt"),
+    Path("/path/to/file3.docx")
+]
+
+response = client.files.bulk_upload(files)
+
+# Access uploaded file information
+for file_info in response.files:
+    print(f"Uploaded: {file_info.name}, ID: {file_info.id}")
+```
+
+2. **Get File**
+```python
+# Download file by ID
+file_content = client.files.get_file("file-id")
+
+# Save to disk
+with open("downloaded_file.pdf", "wb") as f:
+    f.write(file_content)
+```
+
+### User Service
+
+The User service provides access to user profile and preferences.
+
+#### Core Methods
+
+1. **Get Current User Profile**
+```python
+# Get current user information
+user = client.users.about_me()
+print(f"User: {user.name}, Email: {user.email}")
+```
+
+2. **Get User Data and Preferences**
+```python
+# Get user data and preferences
+user_data = client.users.get_data()
+```
+
+### Task Service
+
+The Task service enables monitoring of background tasks.
+
+#### Core Methods
+
+1. **Get Background Task**
+```python
+# Get background task status by ID
+task = client.tasks.get("task-id")
+print(f"Task Status: {task.status}")
+print(f"Progress: {task.progress}")
+```
+
 ### Webhook Service
 
-The Webhook service provides access to trigger available webhook in CodeMie.
+The Webhook service provides access to trigger available webhooks in CodeMie.
 
 #### Core Methods
 
-1. **Get All Conversations**
+1. **Trigger Webhook**
 ```python
-# Trigger assistant/workflow/datasource by it's ID
+# Trigger assistant/workflow/datasource by its ID
 # Data - body of the post method
-response = client.webhook.trigger("resource_id", "data")
+response = client.webhook.trigger("resource_id", {"key": "value"})
+```
+
+### Vendor Services
+
+The Vendor Services enable integration with cloud providers to access and manage their native AI assistants, workflows, knowledge bases, and guardrails. Currently, only AWS is supported.
+
+#### Vendor Assistant Service
+
+Manage cloud vendor assistants (AWS Bedrock Agents).
+
+**Core Methods:**
+
+1. **Get Assistant Settings**
+```python
+from codemie_sdk.models.vendor_assistant import VendorType
+
+# Get AWS assistant settings with pagination
+settings = client.vendor_assistants.get_assistant_settings(
+    vendor=VendorType.AWS,
+    page=0,
+    per_page=10
+)
+
+# Or use string
+settings = client.vendor_assistants.get_assistant_settings("aws", page=0, per_page=10)
+```
+
+2. **Get Assistants**
+```python
+# Get assistants for a specific vendor setting
+assistants = client.vendor_assistants.get_assistants(
+    vendor=VendorType.AWS,
+    setting_id="cac90788-39b7-4ffe-8b57-e8b047fa1f6c",
+    per_page=8,
+    next_token=None  # For pagination
+)
+
+# Access assistant data
+for assistant in assistants.data:
+    print(f"Assistant: {assistant.name}, ID: {assistant.id}")
+```
+
+3. **Get Assistant Details**
+```python
+# Get specific assistant
+assistant = client.vendor_assistants.get_assistant(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    assistant_id="assistant-id"
+)
+
+# Get assistant versions
+versions = client.vendor_assistants.get_assistant_versions(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    assistant_id="assistant-id"
+)
 ```
+
+4. **Get Assistant Aliases**
+```python
+# Get aliases for an assistant
+aliases = client.vendor_assistants.get_assistant_aliases(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    assistant_id="assistant-id"
+)
+```
+
+5. **Install/Uninstall Assistants**
+```python
+from codemie_sdk.models.vendor_assistant import VendorAssistantInstallRequest
+
+# Install assistant
+install_request = VendorAssistantInstallRequest(
+    assistant_id="assistant-id",
+    version="1.0",
+    project="project-name"
+)
+
+response = client.vendor_assistants.install_assistant(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    request=install_request
+)
+
+# Uninstall assistant
+response = client.vendor_assistants.uninstall_assistant(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    assistant_id="assistant-id"
+)
+```
+
+#### Vendor Workflow Service
+
+Manage cloud vendor workflows (AWS Step Functions).
+
+**Core Methods:**
+
+1. **Get Workflow Settings**
+```python
+# Get workflow settings for a vendor
+settings = client.vendor_workflows.get_workflow_settings(
+    vendor=VendorType.AWS,
+    page=0,
+    per_page=10
+)
+```
+
+2. **Get Workflows**
+```python
+# Get workflows for a specific setting
+workflows = client.vendor_workflows.get_workflows(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    per_page=10,
+    next_token=None
+)
+```
+
+3. **Get Workflow Details**
+```python
+# Get specific workflow
+workflow = client.vendor_workflows.get_workflow(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    workflow_id="workflow-id"
+)
+```
+
+4. **Install/Uninstall Workflows**
+```python
+from codemie_sdk.models.vendor_workflow import VendorWorkflowInstallRequest
+
+# Install workflow
+install_request = VendorWorkflowInstallRequest(
+    workflow_id="workflow-id",
+    project="project-name"
+)
+
+response = client.vendor_workflows.install_workflow(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    request=install_request
+)
+
+# Uninstall workflow
+response = client.vendor_workflows.uninstall_workflow(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    workflow_id="workflow-id"
+)
+```
+
+#### Vendor Knowledge Base Service
+
+Manage cloud vendor knowledge bases (AWS Bedrock Knowledge Bases).
+
+**Core Methods:**
+
+1. **Get Knowledge Base Settings**
+```python
+# Get knowledge base settings for a vendor
+settings = client.vendor_knowledgebases.get_knowledgebase_settings(
+    vendor=VendorType.AWS,
+    page=0,
+    per_page=10
+)
+```
+
+2. **Get Knowledge Bases**
+```python
+# Get knowledge bases for a specific setting
+kbs = client.vendor_knowledgebases.get_knowledgebases(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    per_page=10,
+    next_token=None
+)
+```
+
+3. **Get Knowledge Base Details**
+```python
+# Get specific knowledge base with details
+kb_detail = client.vendor_knowledgebases.get_knowledgebase_detail(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    kb_id="kb-id"
+)
+```
+
+4. **Install/Uninstall Knowledge Bases**
+```python
+from codemie_sdk.models.vendor_knowledgebase import VendorKnowledgeBaseInstallRequest
+
+# Install knowledge base
+install_request = VendorKnowledgeBaseInstallRequest(
+    kb_id="kb-id",
+    project="project-name"
+)
+
+response = client.vendor_knowledgebases.install_knowledgebase(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    request=install_request
+)
+
+# Uninstall knowledge base
+response = client.vendor_knowledgebases.uninstall_knowledgebase(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    kb_id="kb-id"
+)
+```
+
+#### Vendor Guardrail Service
+
+Manage cloud vendor guardrails (AWS Bedrock Guardrails).
+
+**Core Methods:**
+
+1. **Get Guardrail Settings**
+```python
+# Get guardrail settings for a vendor
+settings = client.vendor_guardrails.get_guardrail_settings(
+    vendor=VendorType.AWS,
+    page=0,
+    per_page=10
+)
+
+# Check for invalid settings
+for setting in settings.data:
+    if setting.invalid:
+        print(f"Error: {setting.error}")
+```
+
+2. **Get Guardrails**
+```python
+# Get guardrails for a specific setting
+guardrails = client.vendor_guardrails.get_guardrails(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    per_page=10,
+    next_token=None
+)
+```
+
+3. **Get Guardrail Details and Versions**
+```python
+# Get specific guardrail
+guardrail = client.vendor_guardrails.get_guardrail(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    guardrail_id="guardrail-id"
+)
+
+# Get guardrail versions
+versions = client.vendor_guardrails.get_guardrail_versions(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    guardrail_id="guardrail-id"
+)
+```
+
+4. **Install/Uninstall Guardrails**
+```python
+from codemie_sdk.models.vendor_guardrail import VendorGuardrailInstallRequest
+
+# Install guardrail
+install_request = VendorGuardrailInstallRequest(
+    guardrail_id="guardrail-id",
+    version="1.0",
+    project="project-name"
+)
+
+response = client.vendor_guardrails.install_guardrail(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    request=install_request
+)
+
+# Uninstall guardrail
+response = client.vendor_guardrails.uninstall_guardrail(
+    vendor=VendorType.AWS,
+    setting_id="setting-id",
+    guardrail_id="guardrail-id"
+)
+```
+
 ## Error Handling
 
 The SDK implements comprehensive error handling. All API calls may raise exceptions for:
@@ -907,153 +1365,40 @@ client = CodeMieClient(
 )
 ```
 
-### Assistant Versioning via SDK
-
-The Python SDK exposes full assistant versioning capabilities delivered in EPMCDME-8285.
-
-- List versions
-```python
-versions = client.assistants.list_versions("assistant-id", page=0, per_page=20)
-print([v.version_number for v in versions])
-```
-
-- Get specific version
-```python
-version = client.assistants.get_version("assistant-id", 2)
-print(version.system_prompt)
-```
-
-- Compare two versions
-```python
-from codemie_sdk.models.assistant import AssistantVersionDiff
-
-diff: AssistantVersionDiff = client.assistants.compare_versions("assistant-id", 1, 3)
-print(diff.summary)
-```
-
-- Rollback to a version
-```python
-resp = client.assistants.rollback_to_version("assistant-id", 2)
-print(resp)
-```
-
-- Chat with a specific version
-```python
-from codemie_sdk.models.assistant import AssistantChatRequest
-
-req = AssistantChatRequest(text="Hi", stream=False)
-resp = client.assistants.chat_with_version("assistant-id", 2, req)
-print(resp.generated)
-```
-
-Quick CLI example
-```bash
-python codemie-sdk/examples/assistant_versions.py <assistant_id> [version_number]
-```
-
 ## Support
-For providing credentials please contact AI/Run CodeMie Team: Vadym_Vlasenko@epam.com or Nikita_Levyankov@epam.com
-
-## Running tests
-
-For running tests on custom environment you should create .env file in the ./tests directory,
-ask QA team: anton_yeromin@epam.com to provide all needed testing credentials. Under this directory there are stubs
-for .env files for running tests on local and preview environments.
-
-Configuration example:
-
-``` properties
-
-AUTH_SERVER_URL=https://keycloak.eks-core.aws.main.edp.projects.epam.com/auth
-AUTH_CLIENT_ID=codemie-preview
-AUTH_CLIENT_SECRET=<auth_clienbt_secret>
-AUTH_REALM_NAME=codemie-prod
-CODEMIE_API_DOMAIN=http://localhost:8080
-VERIFY_SSL=False
-
-NATS_URL=nats://localhost:4222
-
-ENV=local
-CLEANUP_DATA=True
-
-AUTH_USERNAME=<username>
-AUTH_PASSWORD=<password>
-TEST_USER_FULL_NAME=<user_full_name>
-
-PROJECT_NAME=codemie
-GIT_ENV=gitlab
-
-DEFAULT_TIMEOUT=60
-
-GITLAB_URL=https://gitbud.epam.com
-GITLAB_TOKEN=<gitlab_token>
-GITLAB_PROJECT=https://gitbud.epam.com/epm-cdme/autotests/codemie-test-project
-GITLAB_PROJECT_ID=17889
-
-GITHUB_URL=https://github.com
-GITHUB_TOKEN=<github_token>
-GITHUB_PROJECT=https://github.com/wild47/final_task
-
-JIRA_URL=https://jiraeu.epam.com
-JIRA_TOKEN=<jira_token>
-JQL="project = 'EPMCDME' and issuetype = 'Epic' and status = 'Closed'"
 
-CONFLUENCE_URL=https://kb.epam.com
-CONFLUENCE_TOKEN=<confluence_token>
-CQL="space = EPMCDME and type = page and title = 'AQA Backlog Estimation'"
-
-AWS_ACCESS_KEY=<aws_access_token>
-AWS_SECRET_KEY=<aws_secret_key>
-
-RP_API_KEY=<report_portal_key_optional>
-```
+For providing credentials please contact AI/Run CodeMie Team: Vadym_Vlasenko@epam.com or Nikita_Levyankov@epam.com
 
-Run all tests (-n - number of parallel workers. Fill free to change it to find the best that suits your environment)
+## Development
 
-```shell
-pytest -n 10 --reruns 2
-```
+### Setup
 
-Run e2e/regression tests
+```bash
+# Install dependencies
+poetry install
 
-```shell
-pytest -n 10 -m "e2e or regression" --reruns 2
+# Or using make
+make install
 ```
 
-Run UI tests
-
-First you have to install playwright browsers:
+### Code Quality
 
-```shell
-playwright install
-```
-and then
+```bash
+# Run linter (check and fix)
+make ruff
 
-```shell
-pytest -n 4 -m ui --reruns 2
+# Or manually
+poetry run ruff check --fix
+poetry run ruff format
 ```
 
-All Playwright documentation can be found by the following link: https://playwright.dev/python/docs/intro
-
-Run tests for e2e tests for specific integration/tool.
-Available marks:
- - jira_kb
- - confluence_kb
- - code_kb
- - gitlab
- - github
- - git
-
-```shell
-pytest -n 10 -m "jira_kb or github" --reruns 2
-```
+### Building Package
 
-In case you want to send test results in **ReportPortal** you should specify RP_API_KEY in .env and run tests like this:
+```bash
+# Build package
+poetry build
+# Or make build
 
-```shell
-pytest -n 10 -m "e2e or regression" --reruns 2 --reportportal
+# Publish to PyPI
+make publish
 ```
-
-ReportPortal link is available by the following URL: https://report-portal.core.kuberocketci.io/ui/#epm-cdme/launches/all
-
-If you do not have access to the project ask Anton Yeromin (anton_yeromin@epam.com) to add you.