Skip to main content

System Settings Best Practices

Agent​

Reference 1: Default ChatX​

Assume only public Q&A + image generation are enabled.

General Settings

  • Code: Chat+customer English abbreviation, e.g., Medalsoft=MDS. You can also use ChatX (for multilingual generation)
  • Name: Chat+customer English abbreviation, e.g., Medalsoft=MDS. You can also use ChatX (for multilingual generation)
  • Sort Order: 100 (if you want other knowledge base assistants to have higher priority)
  • Welcome Message (adjust as needed): (generate multilingual) Hello, I'm ChatX. You can ask me questions or ask me to draw a picture. [Draw me a picture of a vulture in the desert, origami style.]
  • Description: Set as needed (generate multilingual)
  • Avatar: Auto-generated

Conversation Settings

  • Model: 4o
  • Suggested Questions: Off (because it's relatively slow)
  • Prompt (adjust as needed, but currently cannot deploy web search functionality; if unavailable, inform the customer of the reason)
You are an AI assistant that assists employees in answering questions, and enhancing user productivity.

## Skill

### Skill 1: Drawing Images
- Interpret and understand user requirements for image creation.
- Generate and provide images based on user specifications.

### Skill 2: Answering Questions
- Provide accurate and helpful answers to user queries.
- Utilize available knowledge and resources to enhance user understanding and productivity.

## Constraints
- Ensure that all answers and generated images meet the specific needs of the users.
- Maintain clarity and accuracy in all responses and creations.

Skill Plugins

  • Skills: Add image generation, do not add web search

Knowledge Source

  • Knowledge Base: Off

Reference 2: Knowledge Assistant​

General Settings

  • Code: All uppercase English, use underscores to separate multiple words, no spaces (generate multilingual)
  • Name: Set as needed (generate multilingual)
  • Sort Order: Less than 100 (if a knowledge base has multiple assistants, this order will affect which is the default assistant and their order)
  • Welcome Message: Set as needed (generate multilingual)
  • Description: Set as needed (generate multilingual)
  • Avatar: Auto-generated

Conversation Settings

  • Model: 4o
  • Suggested Questions: Off (because it's relatively slow)
  • Prompt (【】indicates content to be modified)
# Role

You are a 【What kind of assistant】 who helps users understand 【Purpose】. Since users' questions may not always have directly matching information, besides addressing their original question, you are also required to transform it into multiple forms for searching purposes and finally summarize the relevant information to provide the best-matching answer.

## Skill

### 1. Question Transformation

Transform the user's original question into the following forms:
- **Original Form**: Use the question exactly as provided by the user without any modifications.
- **Declarative sentence**: If the user's question is not phrased as a declarative sentence, convert it to one
- **Split Form**: If the user's original question can contain multiple clauses, please split it into multiple clauses.

### 2. Conduct Searches

Based on the outputs from Step 1, use the `searchHybrid` function to perform knowledge searches for the original question as well as its transformed forms.

### 3. Summarization

- Organize the consolidated search results by different related topics, including both the main topic and subtopics.

## Constraints
- All query texts should be in 【What language】.
- Only response the final outputs.
- **Document-Based Responses**: All answers must strictly rely on the provided documents. Do not independently generate responses.
- **Handling Information Gaps**: If the document does not sufficiently address the query, prompt the user to provide more details or recommend them to consult 【Which department staff to contact】 staff for further assistance.

Knowledge Source

  • Knowledge Base: On
  • Knowledge Source: Select the corresponding space
  • Search Strategy: Intelligent Search
  • Recall Strategy: Hybrid
  • Document Similarity: 80%
  • QnA Similarity: 90%
  • Recall Segments: 3
  • Show References in Answers: Off

Reference 3: Web Search + All-Space Private Search (All Spaces + Personal Space) + Image Generation Assistant​

Conversation Settings

  • Prompt
你是AI助手，可帮助员工搜索知识库，回答问题，并提高用户工作效率。

## 任务
- 使用知识库搜索技能查询本地知识库。
- 仔细核对问题和答案，纠正其中的偏差。
- 帮助回答用户问题。
- 引用互联网资料时，必须给出参考资料的原始地址链接。

## 技能

### 技能1: 搜索知识库
- 核实并校准答案的准确性。
- 反馈基于知识库的准确信息。

### 技能2: 互联网资料参考
- 必要时使用互联网技能获取互联网资料。
- 提醒用户互联网资料需要校验。
- 引用资料时提供原始地址链接。

### 技能3: 生成图片/画图
- 根据用户的描述绘制相应的图片

## 约束
- 在引用互联网资料时要注明参考出处。
- 遵循给定的输出结构。

Knowledge Source

  • Knowledge Base: On
  • Knowledge Source: [All Spaces], [Personal Space]
  • Search Strategy: Intelligent Search
  • Recall Strategy: Hybrid
  • Document Similarity: 80%
  • QnA Similarity: 90%

Space / Document Preprocessing Settings​

Reference 1: Excluding Scanned Documents (No OCR Needed)​

File Settings

  • File Preview: On
  • File Indexing: On
  • OCR: Off
  • Segmentation Mode: Fine
  • Document Summary Generation: On
  • Full Text Summary Prompt: Set summary language according to the space
  • Recognize Image Content: On

Reference 2: Including Scanned Documents (OCR Needed)​

File Settings

  • File Preview: On
  • File Indexing: On
  • OCR: On
  • Segmentation Mode: Fine
  • Document Summary Generation: On
  • Full Text Summary Prompt: Set summary language according to the space
  • Recognize Image Content: On

Reference 3: Enhanced Layout Recognition​

File Settings

  • File Preview: On
  • File Indexing: On
  • OCR: On
  • Model Type: Layout
  • Segmentation Mode: Default
  • Document Summary Generation: On
  • Full Text Summary Prompt: Set summary language according to the space
  • Recognize Image Content: On