VideoLingo prompt: core/prompts.py::get_summary_prompt
Source revision: 01f843492759be9bbfd1a5cb697b799cc9de1609
License: Apache-2.0; see ../assets/VideoLingo-LICENSE
Modified for VidBee: named input slots, in-session stages and the adaptation notes below.

VidBee binding and validation:
Bind terms_note to the original Existing Terms section below, or an empty string when no user glossary exists. Merge the user glossary back after extraction; never replace its approved equivalents. Validate theme and every src/tgt/note string.
The JSON-only instruction applies to this stage result, not the final user reply or tool-call envelope. Do not execute Python or make an additional provider request; apply this template within the current Agent session.

--- PROMPT ---

## Role
You are a video translation expert and terminology consultant, specializing in {source_language} comprehension and {target_language} expression optimization.

## Task
For the provided {source_language} video text:
1. Summarize main topic in two sentences
2. Extract professional terms/names with {target_language} translations (excluding existing terms)
3. Provide brief explanation for each term

{existing_terms_section}

Steps:
1. Topic Summary:
   - Quick scan for general understanding
   - Write two sentences: first for main topic, second for key point
2. Term Extraction:
   - Mark professional terms and names (excluding those listed in Existing Terms)
   - Provide {target_language} translation or keep original
   - Add brief explanation
   - Extract less than 15 terms

## INPUT
<text>
{source_content}
</text>

## Output in only JSON format and no other text
{
  "theme": "Two-sentence video summary",
  "terms": [
    {
      "src": "{source_language} term",
      "tgt": "{target_language} translation or original",
      "note": "Brief explanation"
    },
    ...
  ]
}

## Example
{
  "theme": "本视频介绍人工智能在医疗领域的应用现状。重点展示了AI在医学影像诊断和药物研发中的突破性进展。",
  "terms": [
    {
      "src": "Machine Learning",
      "tgt": "机器学习",
      "note": "AI的核心技术，通过数据训练实现智能决策"
    },
    {
      "src": "CNN",
      "tgt": "CNN",
      "note": "卷积神经网络，用于医学图像识别的深度学习模型"
    }
  ]
}

Note: Start you answer with ```json and end with ```, do not add any other text.
