Back to Details

gemini-deep-research

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Gemini Deep Research

Gemini深度研究

Use Gemini's Deep Research Agent to perform complex, long-running context gathering and synthesis tasks.
使用Gemini的Deep Research Agent执行复杂、耗时的信息收集与整合任务。

Prerequisites

前置条件

  • GEMINI_API_KEY
    environment variable (from Google AI Studio)
  • Note: This does NOT work with Antigravity OAuth tokens. Requires a direct Gemini API key.
  • GEMINI_API_KEY
    环境变量（从Google AI Studio获取）
  • 注意：该工具不支持Antigravity OAuth令牌，需要直接使用Gemini API密钥。

How It Works

工作原理

Deep Research is an agent that:
  1. Breaks down complex queries into sub-questions
  2. Searches the web systematically
  3. Synthesizes findings into comprehensive reports
  4. Provides streaming progress updates
Deep Research是一款具备以下能力的Agent：
  1. 将复杂查询拆解为子问题
  2. 系统性地进行网页搜索
  3. 将研究结果整合为全面的报告
  4. 提供流式进度更新

Usage

使用方法

Basic Research

基础研究

bash
scripts/deep_research.py --query "Research the history of Google TPUs"
bash
scripts/deep_research.py --query "Research the history of Google TPUs"

Custom Output Format

自定义输出格式

bash
scripts/deep_research.py --query "Research the competitive landscape of EV batteries" \
  --format "1. Executive Summary\n2. Key Players (include data table)\n3. Supply Chain Risks"
bash
scripts/deep_research.py --query "Research the competitive landscape of EV batteries" \
  --format "1. Executive Summary\n2. Key Players (include data table)\n3. Supply Chain Risks"

With File Search (optional)

结合文件搜索（可选）

bash
scripts/deep_research.py --query "Compare our 2025 fiscal year report against current public web news" \
  --file-search-store "fileSearchStores/my-store-name"
bash
scripts/deep_research.py --query "Compare our 2025 fiscal year report against current public web news" \
  --file-search-store "fileSearchStores/my-store-name"

Stream Progress

流式进度更新

bash
scripts/deep_research.py --query "Your research topic" --stream
bash
scripts/deep_research.py --query "Your research topic" --stream

Output

输出结果

The script saves results to timestamped files:
  • deep-research-YYYY-MM-DD-HH-MM-SS.md
    - Final report in markdown
  • deep-research-YYYY-MM-DD-HH-MM-SS.json
    - Full interaction metadata
脚本会将结果保存至带时间戳的文件中：
  • deep-research-YYYY-MM-DD-HH-MM-SS.md
    - 最终报告（Markdown格式）
  • deep-research-YYYY-MM-DD-HH-MM-SS.json
    - 完整交互元数据

API Details

API详情

  • Endpoint: 
    https://generativelanguage.googleapis.com/v1beta/interactions
  • Agent: 
    deep-research-pro-preview-12-2025
  • Auth: 
    x-goog-api-key
    header (NOT OAuth Bearer token)
  • 端点：
    https://generativelanguage.googleapis.com/v1beta/interactions
  • Agent：
    deep-research-pro-preview-12-2025
  • 认证：使用
    x-goog-api-key
    请求头（而非OAuth Bearer令牌）

Limitations

局限性

  • Requires Gemini API key (get from Google AI Studio)
  • Does NOT work with Antigravity OAuth authentication
  • Long-running tasks (minutes to hours depending on complexity)
  • May incur API costs depending on your quota
  • 需要Gemini API密钥（可从Google AI Studio获取）
  • 不支持Antigravity OAuth认证方式
  • 任务耗时较长（根据复杂度不同，从数分钟到数小时不等）
  • 根据你的配额情况，可能会产生API费用