@clickzetta/cz-cli-darwin-arm64 0.3.94 → 0.3.96

package/bin/skills/lakehouse-doc-en/references/datacatalog.md

@@ -0,0 +1,127 @@
+# Data Catalog
+
+## Overview
+
+The Data Catalog provides powerful data retrieval and visualization capabilities, designed to help users find, understand, and utilize data more easily. It supports two modes: Data Search Mode and Data Management Mode. In Data Search Mode, users can directly search for data, while Data Management Mode allows users to locate and manage data tables through a directory structure. With the data catalog, you can manage and utilize data resources more efficiently.
+![](.topwrite/assets/image_1740369561047.png)
+
+* Asset Details: Displays the total data assets of the current tenant.
+
+* Search Box: Click to enter the data search results page.
+
+* Data Management: Click to enter the data management page.
+
+* Upload Data: A lightweight entry for uploading local files.
+
+* Recently Viewed / Newly Created: Shows the top 5 most recently viewed or created data tables under the current tenant. Click to directly access the table details page.
+
+^
+
+## Data Search
+
+Enter keywords in the search box on the data catalog homepage to access the search results page. The search function supports searching by name and description for object types such as **Table, View, and Materialized View**.
+
+The search results page offers multiple filtering options, including **object type, workspace/schema, creation time, and owner**, as well as sorting options by **name, creation time, and update time**.
+
+For search result filtering, users can:
+
+* Filter by **object type, workspace/schema, creation time, and owner**.
+* Sort results by **name, creation time, and update time**.
+
+Click on a table name in the search results page to navigate to the corresponding **Table Details Page**.
+
+^
+
+## Data Management
+
+The **Data Management** page displays all data assets that the current user has permission to manage in the service instance, organized in a directory structure. Click “**Data Management**” on the homepage to enter the **Data Management** page, where you will see a list of workspaces that the user has access to within the current service.
+
+^
+
+### Workspace Level
+
+At the **Workspace Level**, you can view all **Schemas** within the workspace. Click the left-side directory tree to expand and browse different levels. The **top section** displays basic workspace information such as **source, creation time, last modified time, and owner**. The **information section** presents details of each **Schema**, including **name, creation time, last update time, and owner**.
+
+Each workspace contains a **default** \`\`.
+Schemas within a workspace can be **internally created** or **externally created**.
+
+^
+
+Users can **visually create** schema information within a workspace. Click the **question mark** next to the title to access the **help documentation** for schema creation.
+
+###
+
+### Schema Level
+
+Clicking on a specific **Schema** navigates to its **Schema Details Page**.
+At the **Schema Level**, you can view all objects managed within the schema, categorized by object type. The system currently supports the following object types:
+
+* **Table**
+* **View**
+* **Materialized View**
+
+Users can create objects directly within a schema using either **script-based creation** or **visual creation**. The system provides **built-in templates** for different object types to help users better understand **Lakehouse syntax**.
+
+## \*\*\*\*
+
+## Table Details Page
+
+The **Table Details Page** displays comprehensive information about tables stored in the **Lakehouse**, including:
+
+* Table details
+* Field information
+* Data preview
+* Data lineage
+* Job history
+* Upload history
+
+This page is divided into two sections:
+
+1. **Top Section** – Displays the **table name, owner, and quick actions**.
+2. **Information Section** – Contains six tabs: **Details, Fields, Preview, Lineage, Jobs, and Uploads**.
+
+### Top Section
+
+The **top section** provides:
+
+* The **full table path** (workspace/schema/table name).
+* Basic information such as **number of rows, storage size, creation time, last update time, and owner**.
+* An **Upload** function, allowing users to upload local files to the **Lakehouse platform**.
+
+### Details Tab
+
+* Displays the **DDL statement** of the current table.
+* Supports **one-click copy** of the DDL statement.
+* Provides a **one-click** shortcut to the **permission management page** for granting access.
+
+### Fields Tab
+
+* Displays **column names, data types, and descriptions**.
+* If primary keys and standardization tags exist, they will also be displayed.
+
+### Preview Tab
+
+* Allows users to **preview up to 100 rows** of data from the current table.
+* **Data access permissions apply**—only users with **SELECT permissions** on the table can view the preview.
+* To generate a data preview, the user must **manually select a compute cluster** for query execution.
+
+### Lineage Tab
+
+* Displays **upstream and downstream dependencies** of the current table.
+* The lineage relationships are derived from **code analysis of the jobs that produced the table**, representing a "**definition-level**" relationship.
+* Clicking on an **upstream** or **downstream** table node provides **more detailed information**.
+
+### Jobs Tab
+
+* Displays **SQL jobs** that generated the table.
+* Clicking on a **Job ID** allows users to view **job details**.
+
+### Upload Tab
+
+* Lists **all historical uploads** to the table via the **Upload** function.
+
+^
+
+## Upload Data
+
+Please refer to [this document](upload_data.md).

package/bin/skills/lakehouse-doc-en/references/datagpt-release.md

@@ -0,0 +1 @@
+# Analytics Agent Release Notes History

package/bin/skills/lakehouse-doc-en/references/datagpt_bestpractice.md

@@ -0,0 +1 @@
+# Analytics Agent Best Practices

package/bin/skills/lakehouse-doc-en/references/datagpt_data_source.md

@@ -0,0 +1,57 @@
+# Data Source Management
+
+DataGPT will by default add the Alibaba Cloud Lakehouse instance in the same region as a built-in data source, without the need for manual addition. If you want to add a Lakehouse data source from another region, please refer to the following operations.
+
+## Function Overview
+
+This function is used to add and configure LakeHouse data source connections, supporting users to connect LakeHouse databases to the system for data analysis.
+
+## Operation Entry
+
+* Location: Product homepage, left navigation bar: Management -> Data Source
+
+## Configuration Item Description
+
+### Basic Information
+
+| Field Name                        | Required | Description                                                 |
+| --------------------------------- | -------- | ----------------------------------------------------------- |
+| Data Source Name                  | Yes      | The unique name used to identify the data source            |
+| Connection String                 | Yes      | The connection address of the LakeHouse database            |
+| Username                          | Yes      | The user account for accessing the database, example: admin |
+| Password                          | Yes      | The password for accessing the database                     |
+| Analytical Computing Cluster Name | No       | Specify the computing cluster used for data analysis        |
+
+## Operation Instructions
+
+1. Enter the data source name
+2. Fill in the database connection string
+
+![](.topwrite/assets/20250219-114848.jpeg =691)
+
+![](.topwrite/assets/20250219-114853.jpeg =677)
+
+1. Enter the username and password
+2. Fill in the analytical computing cluster name
+3. Click the "Connection Test" button to verify if the configuration is correct
+4. After passing the test, click the "Save" button to complete the addition
+
+## Precautions
+
+1. The data source name must be unique in the system
+2. It is recommended to perform a connection test before saving
+3. Please ensure that the username provided has sufficient database access permissions
+4. It is recommended to use a strong password to ensure security
+
+## Error Handling
+
+|                        |                                       |                                                     |
+| ---------------------- | ------------------------------------- | --------------------------------------------------- |
+| Error Type             | Possible Cause                        | Solution                                            |
+| Connection Test Failed | Connection string format error        | Check if the connection string format is correct    |
+|                        | Username or password error            | Confirm the correctness of the account and password |
+|                        | Network issue                         | Check if the network connection is normal           |
+| Save Failed            | Duplicate data source name            | Use an unused name                                  |
+|                        | Required information not fully filled | Check if all required fields are filled             |
+
+^

package/bin/skills/lakehouse-doc-en/references/datagpt_get_accurate_answers.md

@@ -0,0 +1,40 @@
+# How to Make DataGPT's Answers More Accurate
+
+As a data-based Q\&A system, accuracy is particularly important. The system provides the following means to ensure the accuracy of answers.
+
+## 1. Data Governance
+
+* **Data Profile**: The system provides a data profile function that allows you to understand the data status of the underlying dataset tables: through **Left Navigation Bar -> Data -> Data Tables**, on the **Statistical Analysis** tab of the table details page, you can view the data status to help you with data governance; by establishing a data profile, it also helps to find the appropriate target data through natural language.
+
+> Note: DataGPT only provides the **statistical analysis** function for customers to view data distribution and statistical analysis. Data quality is guaranteed by the upstream data platform.
+
+* **Table, Column Descriptions, and Column Alias Configuration**: Adding accurate descriptions and alias information to table columns helps the system accurately match questions with data. In **Left Navigation Bar -> Data -> Data Tables**, you can configure table-level descriptions, column aliases (Alias), and column description information (Description) respectively. The clearer and more accurate the aliases and descriptions of tables and columns are, the less ambiguity there is in names and descriptions, and the higher the accuracy of answers.
+
+* **Index Switch**: For columns that are frequently referenced by questions, you can choose to index the specific values of those columns. Common dimension columns such as region, product category, and channel can be considered for indexing. (If the underlying data is updated, you can refresh the column value index in Action.)
+
+  * For example, the question: `In the year of 2017, the total sales trend both undefined and undefined state by mouth, present Separately？` The actual values stored in the `customer_state` field of the table is `MG` and `RJ`. Without adding index, using `customer_state` `in ['undefined','undefined']` as a filter will not return any value. If an index is added, the system will match `undefined and undefined state `with the original value `MG` and `RJ` for similarity and provide a suggestion: ![](.topwrite/assets/20250219-120022.jpeg =725)
+
+> Note: Indexing will incur additional creation and maintenance costs. DataGPT defaults to no more than 10,000 index values on a single column. If you need to create a larger number of index values on the target column, you need to communicate with Singdata to lift the restriction.
+
+* **Column Type and Intended Use**: Please fill in the column type (ColumnType) and intended use (Intended For) based on the actual values of the column. **This option will affect whether the column is selected as a data source for questions**.
+
+## 2. Divide Analysis Domains
+
+Splitting business domains helps the system focus more on specific data.
+
+1. Pre-divide analysis domains to reduce the range of data tables and knowledge involved in each Domain.
+2. Asking questions for a specific Domain is more focused, and the Domain will be bound to the user, enabling table-level data isolation.
+
+## 3. Create Metrics and Answer Builders
+
+Metrics are the results of aggregate functions or calculations of aggregate functions, and answer builders are SQL template definitions for predefined objects. Answering questions based on metrics and answer builders will significantly improve accuracy. If there are strict requirements for Q\&A accuracy, it is recommended to predefine them. Metrics support aliases to match more expressions.
+
+:-: ![](.topwrite/assets/20250219-115256.jpeg)
+
+## 4. Use Input Prompts
+
+Column Value Intelligent Matching: After enabling the column value index function, the system will provide real-time data value prompts as you input, ensuring the accuracy and relevance of query results.
+
+![](.topwrite/assets/20250219-120653.jpeg)
+
+^

package/bin/skills/lakehouse-doc-en/references/datagpt_intro.md

@@ -0,0 +1,75 @@
+# Singdata Conversational AI Analysts: DataGPT
+
+Lakehouse DataGPT is a new generation conversational data analysis tool built on the cloud-native Lakehouse architecture. It combines the natural language understanding capabilities of large language models (LLM) with the processing power of the Lakehouse enterprise-grade data engine, transforming data analysis into an intuitive conversational experience. With DataGPT, even business personnel without a technical background can easily explore data value and drive data-driven intelligent decision-making.
+
+![](.topwrite/assets/20250219-110334.jpeg)
+
+## Technical Architecture:
+
+Multi-source, multi-type data enters the Lakehouse system through warehousing and lake entry methods:
+
+* **Metadata** is uniformly managed and accessed according to the data warehouse's permission system.
+* **Data** is transformed and information is extracted through our integrated engine Single Engine and AI engine.
+
+The extracted results are stored in the system in the form of tables, vectors, and inverted indexes, forming a RAG preparation layer. These three parts of the data are then subjected to automated data feature analysis, knowledge graph construction, and automated index extraction through the semantic engine layer. The significance of these last two new layers is: the RAG ready layer provides the basic data ready for AI preparation. If we apply the previously mentioned DIKW model, this data foundation is information, and the role of the semantic engine layer is to annotate, organize, and summarize this information to the knowledge level, laying the foundation for generative AI applications.
+
+![](<.topwrite/assets/screenshot2025-01-15 17.11.19.png>)
+
+## Product Features:
+
+* Seamless integration with the **Lakehouse data platform**, capable of automatically building a semantic layer based on Lakehouse tables, directly transforming into LLM application-ready data. Compared to traditional knowledge base systems, it defaults to using Lakehouse as the underlying data lake warehouse, vector, and scalar storage engine, with stronger concurrent processing capabilities and quickly scalable computing resources.
+* Combines conversational interaction with traditional BI exploration to enhance data analysis efficiency and Emphasizes the interpretability of the analysis process, providing business personnel with clear result validation evidence.   ![](.topwrite/assets/20250219-112543.jpeg =789)
+* Adopts a Multi-Agent architecture, capable of intelligently decomposing and parallel processing complex customized tasks, significantly improving Q\&A efficiency and accuracy.
+* Supports intelligent follow-up questions and multi-turn conversations, allowing users to gradually optimize and clarify requirements, effectively eliminating data understanding ambiguities.
+* Utilizes multi-model collaboration to continuously optimize response efficiency and accuracy during the Q\&A process: users can choose different models (such as **Azure-gpt-4o** and **Deepseek-R1**) to handle query or analysis tasks. The system provides open-source models for private deployment to summarize questions, ensuring data does not leave the service.   ![](.topwrite/assets/20250219-112622.jpeg =790)
+
+## Concept System:
+
+Its core concept system consists of two main parts: data assets and analysis domains:
+
+1. Data Assets: Serving as the infrastructure for enterprise-level analysis, it includes all core data elements available for intelligent analysis:
+
+   * Data Tables: Structured basic data sources
+   * Metric System: Standardized measurement metrics built based on data tables
+   * Business Terms: Unified naming conventions and explanatory definitions
+   * Analysis Documents: A collection of knowledge files supporting Q\&A
+   * Column Value Index: Indexes established for fields in the dataset tables
+
+2. Analysis Domain (Domain): Serving as the logical boundary for business analysis, it undertakes the dual responsibilities of data classification and access control. Data assets can be flexibly referenced to different analysis domains, achieving efficient reuse of enterprise data:
+
+   * Business Grouping: Aggregates and manages data objects (tables, metrics, documents, etc.) with the same attributes
+   * Definition Control: Ensures consistency and uniqueness of data definitions within the domain
+   * Permission Isolation: Achieves fine-grained control of data access through the association between users and analysis domains
+
+   :-: ![](.topwrite/assets/whiteboard_exported_image_1739936522979.png =711)
+
+^
+
+## User Roles and Responsibilities:
+
+The DataGPT system is designed to meet the needs of two core user groups in data analysis scenarios: data developers and business analysts. These two types of users play unique and complementary roles in the process of data value mining:
+
+1. **Data Developers**: Lead the full lifecycle management of data, including data access, quality control, model building, and semantic layer design (covering metric systems and answer builders), and continuously optimize the Q\&A experience. They use system functions to prepare data for business analysts.
+2. **Business Analysts**: As the core users of the system, they deeply explore data through natural language interaction, quickly obtaining business insights and decision support. Through the feedback process, they communicate with data developers to further refine and explore data for deeper understanding and insights.
+
+## Free Version Limitations:
+
+Thank you for using Singdata DataGPT. You are currently using the free version. To ensure you fully understand the product status, we hereby explain:
+
+1. The features in the current version are early product features, and we reserve the right to optimize, adjust, or change the features.
+
+2. Based on product development plans, some features may be upgraded to paid services or have their service scope adjusted. We will notify affected users in advance before such changes occur.
+
+3. During the free usage period, the product features have the following limitations:
+   • 4 Dedicated Analysis Domain
+   • Maximum 5 files upload capacity (50MB max size)
+   • Concurrent file upload limit: 8 files
+   • File size restriction: 50MB per file
+   • Data table capacity: 480 rows
+   • Daily response quota: 30 queries
+
+If you have any suggestions about the product, feel free to provide feedback using the contact information below.
+
+* **Email**: <service@singdata.com>
+
+^

package/bin/skills/lakehouse-doc-en/references/datagpt_introduction.md

@@ -0,0 +1,129 @@
+# Conversational AI Data Analysis Tool: Analytics Agent
+
+Analytics Agent is a next-generation agentic analysis assistant built on cloud-native Lakehouse architecture and other data platforms (formerly known as DataGPT). It deeply integrates AI cognitive capabilities with enterprise-grade data, going beyond simple query functionality. The agent can dynamically construct AI dashboards through natural language, providing imaginative visualization flexibility that surpasses traditional rigid BI tools. It also proactively embeds contextual AI insights into key chart metrics, instantly revealing anomalies and trends, and uncovering hidden data insights within static reports.
+
+^
+
+![](/.topwrite/assets/datagpt_1.png)
+
+^
+
+## When to Use Analytics Agent
+
+| Scenario | Suitable? |
+| ---------------------------------------------------- | ------------------------------------ |
+| Business users querying data and viewing trends via natural language | ✅ Core use case |
+| Quickly generating AI dashboards without writing SQL | ✅ |
+| Automatic anomaly detection and alerting | ✅ |
+| Precise SQL logic control, complex ETL | ❌ Use Studio SQL tasks |
+| Vector search / RAG Q&A | ❌ Use vector search + AI functions |
+
+## Quick Start
+
+**① Activate the service** (1 min)
+
+Find the Analytics Agent product card on the management center homepage and click "Free Activation". New users are recommended to check "Also activate a Lakehouse instance as the default data source" — the system will automatically configure sample data.
+
+**② Try with sample data** (5 min)
+
+Go to the product homepage, find the analysis domain marked "Sample", click "Start Analysis", and ask questions in natural language:
+- "What is the average second-hand housing price by district?"
+- "Which district has the highest listing volume?"
+- "Generate a housing price trend dashboard for me"
+
+**③ Connect your own data** (as needed)
+
+Add a data source (supports uploading Excel/CSV files or connecting Lakehouse data tables) → Create an analysis domain → Configure the semantic layer (business terms, metric definitions, table relationships, answer builders, knowledge documents, data annotations to help the Agent understand your business) → Start conversational analysis
+
+## Conceptual Framework:
+
+**Core Concepts**:
+The core conceptual framework consists of two main components: Data Assets and Analysis Domains.
+
+**Data Assets**
+As the infrastructure for enterprise analytics, it encompasses all core elements available for intelligent analysis, enhanced through the Analytics Agent Semantic Layer:
+
+* **Data Tables**: Structured basic data sources from Lakehouse.
+
+* **Semantic Layer Elements**:
+
+  * **Metric System**: Standardized measurement indicators built on data tables.
+  * **Business Terms**: Unified naming conventions and explanatory definitions designed to provide context for the agent.
+
+* **Dashboards**: Visual analytics panels built using AI based on the semantic layer and data tables.
+
+* **Documents**: A collection of knowledge documents supporting Agentic RAG-based Q&A.
+
+* **Indexes**: Indexes built on data table fields to accelerate retrieval.
+
+:-: ![](/.topwrite/assets/DataGPT_2.png)
+
+^
+
+## User Roles and Responsibilities:
+
+The Analytics Agent system is designed to serve two core user groups in data analysis scenarios: data developers and business analysts. These two types of users play unique and complementary roles in the process of extracting data value:
+
+1. **Data Developers**: Lead the full data lifecycle management, including data ingestion, quality control, model building, and semantic layer design (covering metric systems and answer builders), while continuously optimizing the Q&A experience. They leverage system capabilities to prepare data for use by business analysts.
+2. **Business Analysts**: As the core users of the system, they explore data deeply through natural language interaction, quickly obtaining business insights and decision support. Through the feedback process, they communicate with data developers to further refine and explore data, gaining deeper understanding and insights.
+
+## Technical Architecture:
+
+Multi-source and multi-type data enters the Lakehouse system through warehousing and data lake ingestion (when Lakehouse is chosen as the data engine):
+
+* Metadata is managed and access-controlled uniformly according to the data warehouse's permission system.
+* Data undergoes transformation processing and information extraction through our integrated Single Engine and AI engine.
+* Extraction results are stored in the form of tables, vectors, and inverted indexes, building an Agentic RAG Preparation Layer for the agent. These are then further processed by the Analytics Agent Semantic Layer, which performs automated feature analysis, knowledge graph construction, and index extraction.
+* Based on the DIKW model, the Agentic RAG layer provides "Information," while the Analytics Agent Semantic Layer elevates it to "Knowledge" by annotating, organizing, and summarizing context. This architecture enables the agent to autonomously plan and reason, laying a solid foundation for generative AI applications.
+* Agentic RAG: A Semantic Paradigm Shift
+  Analytics Agent transcends the linear "retrieve-then-generate" pipeline. By implementing Agentic RAG, we transform the LLM from a passive text generator into a proactive Reasoning Agent within the Analysis Domain.
+  * **LLM-Driven Understanding**: Rather than relying solely on vector distance (cosine similarity), Analytics Agent leverages the LLM's internal cognition to interpret user intent. The model determines "what is needed" rather than simply matching keywords.
+
+  * **Proactive Orchestration**: The agent acts as the central brain within the analysis domain. It autonomously decides which objects to interact with:
+
+    * Whether to query **Data Tables** via SQL
+    * Whether to read specific **Files**
+    * Whether to check **Metric** definitions
+
+  * **Iterative Refinement**: If the initial retrieval information is insufficient, the agent self-corrects. It performs multi-step reasoning to obtain additional context, ensuring the final answer is comprehensive and accurate.
+    By internalizing retrieval logic into the LLM itself, Analytics Agent addresses the limitations of traditional RAG:
+
+  * **Semantic Fidelity**: We leverage the model's multi-dimensional understanding of business logic and nuances, breaking through the "ceiling" of standard vector search.
+
+  * **Complex Problem Solving**: The agent can handle multi-hop queries, synthesizing information from different data types (e.g., correlating a sales decline in a **dashboard** with a market report in a **file**).
+
+  * **Dynamic Adaptation**: As new assets are added to the analysis domain, the agent can adjust its reasoning strategies in real time, without relying on rigid, hard-coded index rules.
+
+## Free Version Limitations:
+
+Thank you for using Singdata Analytics Agent. You are currently using the free version. To ensure you fully understand the product status, please note the following:
+
+1. Features in the current version are early-stage product features, and we reserve the right to optimize, adjust, or modify these features.
+
+2. Based on product development plans, some features may be upgraded to paid services or have their service scope adjusted. We will notify affected users in advance before such changes occur.
+
+3. During the free usage period, the product features have the following limitations:
+
+        ![](.topwrite/assets/20250114-221654.jpeg =258)
+
+If you have any suggestions for the product, please feel free to provide feedback through the following channels:
+
+* **Phone**: 400-6767-862
+
+* **Email**: <service@singdata.com>
+
+* **Enterprise WeChat**: ![](.topwrite/assets/image_1736856313196.png =116)
+
+^
+
+## Related Documentation
+
+| Document | Description |
+| ---------------------------------------------------- | -------------------------------------------- |
+| [Quick Start](datagpt_quickstart.md) | Get started with Analytics Agent in 5 minutes |
+| [User Guide](datagpt_tutorial.md) | Data source configuration, semantic layer setup, dashboard creation |
+| [Best Practices](datagpt_bestpractice.md) | Methods to improve Q&A accuracy |
+| [Q&A Accuracy Improvement](answer-accuracy-improve.md) | Semantic layer optimization, metric definition standards |
+| [Lakehouse DataGPT Tour](lakehousedatagpt-tour.md) | Feature demo videos and screenshots |
+
+^

package/bin/skills/lakehouse-doc-en/references/datagpt_quickstart.md

@@ -0,0 +1,99 @@
+# DataGPT Quick Start
+
+## Activate DataGPT Service
+
+* Find the DataGPT product card on the "Home" page of the management center and click the "Activate for Free" button. 
+* In the pop-up window, the **cloud service provider** Alibaba Cloud and **region** ap-southeast-1 will be specified by default. The system provides the option "**Activate Lakehouse instance** in **Alibaba Cloud** - **ap-southeast-1** **as the default data source**":![](.topwrite/assets/20250218-202455.jpeg)
+* * **Check (recommended for new users**): The system will automatically activate the Lakehouse in Alibaba Cloud - **ap-southeast-1** as the default data source, no manual configuration is required.
+  * **Uncheck**: The system will not automatically activate the Lakehouse instance in East China 2 (Shanghai). You can manually add it on the data source management page after the service is activated. Please note that in this case, **DataGPT will not include preset sample data**.
+* Click "Activate" and after a short wait, you can enter the usage interface
+
+       ![](.topwrite/assets/20250218-200517.jpeg =783)
+
+^
+
+After the service is activated, you can start the DataGPT data analysis experience in various ways. To help you get started quickly, we provide the following analysis paths:
+
+## Method 1: Use Sample Analysis Domain
+
+Ask questions using the sample dataset: We have prepared a well-configured sample dataset for you, which includes a complete table configuration and indicator system. You can start asking questions directly to quickly experience the intelligent analysis capabilities. At the same time, this sample can also serve as a template to help you create an analysis domain suitable for your business scenarios.
+
+Enter the product homepage, find the analysis domain marked "Sample" on the main page, click "Start Analysis" to enter the analysis homepage, and you can start asking questions.
+
+![](.topwrite/assets/20250218-200800.jpeg)
+
+## Method 2: Analyze Based on Your Own Data
+
+The system supports importing various data formats, including CSV, Text, Excel, PDF, etc. You can create an independent analysis domain and start intelligent analysis and Q\&A after importing the data.
+
+In this case, we will use the real business data of the famous Brazilian e-commerce platform Olist to demonstrate the system's data analysis capabilities. We will import the following core data files:
+
+**Core Business Data**:
+
+`olist_orders_dataset.csv.gz (Order Main Table)`
+
+`olist_order_items_dataset.csv.gz (Order Item Details)`
+
+`olist_order_payments_dataset.csv.gz (Payment Information)`
+
+`olist_products_dataset.csv.gz (Product Information)`
+
+**User and Seller Data**:
+
+`olist_customers_dataset.csv.gz (Customer Information)`
+
+`olist_sellers_dataset.csv.gz (Seller Information)`
+
+These data files are compressed in gzip format (.gz) to improve transmission efficiency. The system will automatically decompress and recognize them. The data is linked through key fields such as order number (order\_id) and product number (product\_id) to form a complete business analysis data chain.
+
+###
+
+### Step 1: Create a New Analysis Domain
+
+![](.topwrite/assets/20250218-200854.jpeg)
+
+^
+
+### Step 2: Basic Configuration
+
+* **Analysis Domain Name**: Users need to fill in the analysis domain name, such as "Brazil Olist E-commerce Data Analysis"
+* **Data Source**: Select LAKEHOUSE as the underlying data platform (default)
+
+> **Data Source Restriction**: The tables, indicators, and base tables of the answer builder in the analysis domain must come from the same data source. Keep other options as default. Click **Confirm** to create the analysis domain.
+
+Keep other options as default. Click **Confirm** to create the analysis domain.
+
+^
+
+### Step 3: Add Data
+
+* After creating a new analysis domain, a prompt to add data will pop up. Click **Add Data -> Table**, then click **Start Adding**
+* Select "**Upload File**" and add the above files to the system. Click **Next** to start parsing
+
+:-: ![](.topwrite/assets/20250218-201126.jpeg =759)
+
+* Click **Next** to upload data:![](.topwrite/assets/20250218-201200.jpeg =781)       
+
+^
+
+> ⚠️ **Note**: In the file parsing interface, there is a mandatory verification requirement: all files displayed with gray dots must click the file name and confirm to display green before clicking the "Next" button to proceed to the next steps.
+>
+> ![](.topwrite/assets/20250218-201423.jpeg =703)
+
+* Automatic Data Semantic Layer Construction:
+  * Data Auto-Profiling: Automatically analyze the basic statistical characteristics of the dataset, including data distribution, missing values, outliers, and other key indicators
+  * Intelligent Supplement of Column Descriptions and Aliases: Note: For aliases, the system has generated alias suggestions, which will take effect after selection
+* Column type auto-recognition: Continuous, Categorical, Date\_And\_Time, Partition, and Other
+  * Column usage: FILTER, DATETIME\_FILTER, DIM, MEASURE
+  * Relationship auto-recognition: If more than one table is uploaded, the relationships will be automatically determined
+  * Automatic metric recommendation: Automatically generate business-meaningful metrics
+    ![](.topwrite/assets/20250218-201550.jpeg =775)
+
+**Once the data is ready, you can start asking questions in natural language**.
+
+^
+
+:-: ![](.topwrite/assets/20250218-202239.jpeg =752)
+
+^
+^

package/bin/skills/lakehouse-doc-en/references/datagpt_tutorial.md

@@ -0,0 +1 @@
+# Analytics Agent User Guide

package/bin/skills/lakehouse-doc-en/references/datalake-acceleration.md

@@ -0,0 +1,5 @@
+# Data Lake Acceleration
+
+Without moving your data, connect directly to an existing Hive Metastore and object storage via External Schema, and replace Spark/Hive ETL and Presto/Trino ad hoc queries with Singdata Serverless compute.
+
+- [In-Place Data Lake Acceleration Implementation Guide](lakehouse-acceleration-guide.md)

package/bin/skills/lakehouse-doc-en/references/datalake-storage-connection.md

@@ -0,0 +1,12 @@
+# Storage Connection
+
+A Storage Connection is a type of Connection object in Singdata Lakehouse. It belongs to the workspace level and is used to store authentication credentials and access control information required when the Lakehouse accesses data in cloud object storage (such as Alibaba Cloud OSS, Tencent Cloud COS, Amazon S3), other data platforms (such as Hive), and real-time streaming data (such as Kafka). It is a prerequisite for Lakehouse Volume objects, External Tables, External Catalogs, Autoloader, and other objects to access external data.
+
+> Note: If you have not enabled an object storage service and need to upload data to Singdata Lakehouse via files, you can upload data to [Internal Volume](internal_volume.md). This approach does not require the user to enable a cloud object storage service.
+
+### Usage Restrictions:
+
+* Cross-cloud object storage connections are currently not supported. For example: if the activated Singdata Lakehouse instance is in the Alibaba Cloud Shanghai site, this instance does not support connecting to non-Alibaba Cloud object storage.
+* One object storage Storage Connection can be used to create multiple Volume objects.
+
+^

package/bin/skills/lakehouse-doc-en/references/datalake_FAQ.md

@@ -0,0 +1,48 @@
+# Data Lake FAQ
+
+#### **Question 1**: **After uploading a file to the Volume path using the PUT command, the file cannot be found during SQL processing**
+
+**Answer**: If the file directory table was enabled when creating the Volume object (`DIRECTORY = (enable = TRUE)`), you need to manually synchronize this change to the Lakehouse metadata system after adding new files to the Volume path. You can use the command `alter volume xxxx refresh;` (the executor needs to have alter permission on the volume object: `GRANT ALTER ON VOLUME xxxx TO USER datalake_user;`)
+
+^
+
+#### **Question 2**: **Does the data lake Volume support CSV files in compressed format**
+
+**Answer**: The current version does not support CSV files in compressed format, but it will be supported in future versions.
+
+^
+
+#### **Question 3: Error when querying CSV files**: **CZLH-00000:CZLH-71001: CZ**\_**SQL\_TIMEZONE should exist in context**;
+
+**Answer**: You need to specify the default time zone in the query: add the option `'timeZone' = 'Asia/Shanghai'` in the options of the select statement querying the volume, for example:
+```
+select * from volume hz_csv_volume (
+  order_id STRING,
+  order_item_id INT,
+  product_id STRING,
+  seller_id STRING,
+  shipping_limit_date TIMESTAMP,
+  price DECIMAL(10,2),
+  freight_value DECIMAL(10,2)
+)using csv 
+ options(
+    'header'='true',
+    'sep'=',',
+    'timeZone' = 'Asia/Shanghai'
+ ) files('brazil-ecommerce/olist_order_items_dataset.csv');
+```
+#### **Question 4**: **Error when executing remote function**: **CZLH-42000:\[1,8] Semantic analysis exception - function not found**
+
+**Answer**: Possible reasons:
+
+1. The function is a schema-level object. Please ensure that the correct schema information is included when executing the function. For example, the function `fc_orc_schema` belongs to the public schema, so the schema information must be included when referencing it: `public.fc_orc_schema()`
+2. Currently, when executing a remote function, you need to include `set cz.sql.remote.udf.enabled=true;` before the SQL statement and execute them together.
+```
+set cz.sql.remote.udf.enabled = true;
+SELECT public.fc_orc_schema('orc','<url>') as schema_orc;
+```
+####
+
+#### **Question 5: Error when executing remote function**: **CZLH-XX000: failed** **to hook preExecute**: **urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'OpenSSL 1.1.0l 10 Sep 2019**'.
+
+**Answer**: When handling file URL links in python code, there is an incompatibility between the urllib3 library version and the OpenSSL version. You can install version 1.26.9 of urllib3 instead: `pip3 install --upgrade urllib3==1.26.9 -t .`

package/bin/skills/lakehouse-doc-en/references/datalake_overview.md

@@ -0,0 +1,17 @@
+# Data Lake
+
+## Overview
+
+Singdata Lakehouse, as an integrated data platform, can seamlessly connect to cloud object storage (currently supported cloud object storage products include: Alibaba Cloud OSS, Tencent Cloud COS, Google GCS, AWS S3), and utilize its integrated data processing engine combined with industry-leading AI capabilities to efficiently process semi-structured and unstructured data in the data lake. In this process, we adopt a unified permission management method to ensure data security and compliance. Specific capabilities include:
+
+1. **Ability to perceive and acquire external data**: As the amount of data continues to grow, the proportion of semi-structured and unstructured data in the data is increasing, and their importance is becoming more prominent.
+2. **Ability to conveniently utilize cutting-edge AI technology**: The multimodal capabilities of deep learning models and large language models (LLM) greatly reduce the threshold for practitioners to analyze semi-structured and unstructured data. Allowing the data platform to conveniently utilize these capabilities expands the scope of data analysis from two-dimensional table data to almost all data (ALL Data), which is an important enhancement in the dimension of analytical capabilities.
+3. **Ability to manage and govern data and files uniformly**: Applying the mature, complete, and universal permission system in the data warehouse to data and files (such as AI model files), for example: controlling specific users to use specified model files and processing authorized data. At the same time, it can achieve a global view of data from an organizational perspective.
+
+The following is a detailed introduction to specific product features:
+
+1. [Data Lake Volume Object](datalake_volume.md): By integrating the data platform with unstructured data, it solves the problem of the data platform accessing unstructured data and the fragmentation of AI/BI data. For example, users can easily import unstructured data such as images and text into the data platform through Volume objects for further analysis and processing.
+2. [Remote Function](remotefunctionbestpractice.md): Provides users with a low-threshold method to call AI models and large language models (LLM) to analyze data. For example, users can easily call pre-trained deep learning models through Remote Function to perform tasks such as image classification and recognition.
+3. [Unified Lakehouse Metadata System](datalake_privilege.md): Integrates structured and unstructured data into a unified Catalog-Schema view, solving the problem of unified lakehouse metadata management and permission management, simplifying data organization and access. For example, administrators can assign corresponding data access permissions to employees of different departments through the metadata system to ensure data security and compliance.
+
+^