AI Slides
AI Slides is an intelligent PPT generation application designed for enterprise presentation scenarios. It is suitable for high-frequency tasks such as market research, business reporting, client proposals, internal training, and project wrap-ups. It helps users quickly transform initial ideas into presentation documents that are structurally complete, stylistically consistent, and ready for delivery.
AI Slides page:

Product Overview
AI Slides provides a complete workflow from idea input, knowledge retrieval, and outline generation to PPT generation and online editing, helping users quickly turn ideas into deliverable presentation documents.
- System-side capabilities: Supports LLM model management, text-to-image model management (such as GPT-Image), and template import.
- User-side configuration: Supports parameter settings such as model selection, page count, writing style, templates, web search, and knowledge base, and allows configurations to be persisted and reused to reduce repetitive setup costs.
Typical scenarios:
- Business users can quickly generate a structured presentation draft after entering a topic.
- AI automatically generates an outline with streaming preview, and users can manually edit it or use AI-assisted expansion.
- Slides are automatically generated based on the outline, with support for page-by-page streaming rendering and natural language conversational modifications.
Core value:
- Provides a practical presentation document production capability within the enterprise, forming an alternative to similar paid external products.
- By integrating with the knowledge base, it provides reliable information sources and stores generated results together with referenced materials in the internal system, reducing the risk of knowledge fragmentation and improving reuse and governance capabilities.
Using AI Slides
Enter Topic and Requirements
Open AI Slides, describe the presentation topic, target audience, and key requirements in the input box, and optionally set the page range as needed.
Example input:
Practical implementation and phased results report of enterprise-grade large model applications: covering ROI evaluation and experience accumulation across three core scenarios—intelligent customer service, coding assistant, and document review.
The target audience is the CTO and the Digitalization Committee. Key requirements are to highlight comparative efficiency data for each scenario, showcase typical use cases, explain the decision logic for model selection, and outline the path for large-scale promotion in the next phase.
AI PPT Settings
- Click the “gear” to enter AI PPT settings and configure the knowledge base and MCP resources.
- Knowledge base access (optional): Select the associated knowledge base and configure retrieval strategies and recall parameters.
- MCP resources (optional): Connect external data sources or tools, such as real-time APIs and internal systems.
Tip: Click the “
” icon to view and preview PPT templates before creation.

Generate and Optimize
- Click send, and the system will perform retrieval and content preparation while displaying the process progress in real time;
- After the system generates the initial outline, you can choose to confirm, modify, or continue adding requirements;
- Confirm the outline and select a template, and the system will begin generating the PPT page by page;
- After generation is complete, you can continue optimizing the content and layout through conversational or visual methods;
- Finally, you can choose to present online, download the
.pptxfile, or keep it on the platform for continuous iteration.
Configuration Guide
Page Count Configuration
- Auto: The system intelligently matches the page count based on the amount of content, suitable for quick generation.
- 1-10 pages: Suitable for brief reports, product introductions, and meeting minutes.
- 11-20 pages: Suitable for regular business reports, client proposals, and internal training.
- 30+ pages: Suitable for in-depth industry research, large project wrap-ups, and strategic planning.
Recommendation: If you are not yet sure about the content depth, you can first use “Auto” to generate a draft, and then adjust the page count based on the actual content density.

Knowledge Base Access Configuration (Optional)
- Knowledge base: You can select one or more authorized knowledge bases. It is recommended to prioritize knowledge bases related to the topic;
- Retrieval strategy: Supports three strategies—hybrid, embedding, and text. Hybrid retrieval is recommended as the preferred option;
- Maximum recall count: Supports 0-10. The higher the value, the richer the information, but the longer the processing time;
- Metadata filtering (Preview): Supports none, filter, and weight, used to control the scope and weighting of recalled content;
- Document match similarity: Used to control the document recall threshold. The commonly recommended value is 0.7;
- Q&A pair match similarity: Used to control the Q&A recall threshold. The commonly recommended value is 0.8.
Note: Higher match similarity is not always better. It is recommended to start with the default value and gradually fine-tune it based on actual output results.

MCP Resource Configuration (Optional)
- If you need to connect to external capabilities such as internal CRM, real-time data APIs, or ticketing systems, you can configure the MCP server with credentials;
- If the current task does not depend on external resources, you can skip this directly without affecting the core generation functions.
- Enable MCP only when the presentation content requires real-time data or information from external systems, so as to ensure timeliness while avoiding unnecessary configuration complexity.

AI Slides Management
Administrators can perform global configuration for AI Slides and centrally manage core capabilities such as models, web search, and text-to-image generation.
Path: Management → Agent Management → APP → Find AI Slides → Click Configuration under the Actions column.
Permission note: The above configurations are all global settings. Changes will affect all users of AI Slides, and such adjustments are restricted to administrators only.
Model Groups and Channels
- Model group: You can specify the large language model group used by AI Slides, with support for multi-model configuration.
- Bound channel: Associates configured API channels to carry model invocation requests.
Web Search
- Enabled status: The toggle controls whether AI Slides is allowed to call web search engines to obtain real-time information.
- Available search engines: Supports multiple selections, including Bing Search, Google Search, Metaso Search, Tencent Search, etc.
Text-to-Image
Used to control whether AI image illustration capabilities are enabled during PPT generation.
- Enabled status: The toggle controls whether the text-to-image function is enabled or disabled.
- Image type: Select the model used to generate images.
- API Key: Enter the API key for the corresponding service.
- Base URL: Configure the request endpoint for the image generation service.
- Model type: Select Azur or OpenAI.
