Content
# DeepRe - AI-driven Deep Research Report Generation Tool
DeepRe is a Deno-based CLI tool that utilizes the Google Gemini AI API to automatically generate deep research reports on specified themes. It collects high-quality information through multiple iterations of research and creates comprehensive reports.
## Features
- **Iterative Research Process**: Research is repeated until the quality of information is sufficient.
- **Automated Evaluation System**: Automatically assesses the richness of the collected information.
- **Gemini API Integration**: Advanced search and analysis leveraging the latest Gemini 2.0 model.
- **Automated Research Planning**: Plans the optimal research approach based on the theme.
- **Full Support for Japanese**: Supports theme setting and output in Japanese.
- **Markdown Format Reports**: Results are output as formatted Markdown.
## Installation
### Prerequisites
- Deno runtime
- Google Gemini API key (set as the `GEMINI_API_KEY` environment variable or specify at runtime)
### Global Installation
```bash
deno task install
```
## Usage
### Basic Usage
```bash
deepre "Research Theme"
```
### Options
```bash
deepre "Research Theme" -k "GEMINI_API_KEY" -o "./output" -m "gemini-2.0-pro" -i 15
```
- `-k, --api-key`: Gemini API Key (can also be obtained from the environment variable `GEMINI_API_KEY`)
- `-o, --output-dir`: Output directory (default: ./research)
- `-m, --model`: Gemini model to use (default: gemini-2.0-flash)
- `-i, --iterations`: Number of research iterations (default: 10)
## Setting Environment Variables
```bash
# macOS/Linux
export GEMINI_API_KEY="Your Gemini API Key"
# Windows (Command Prompt)
set GEMINI_API_KEY=Your Gemini API Key
# Windows (PowerShell)
$env:GEMINI_API_KEY="Your Gemini API Key"
```
## Development
```bash
# Run in development mode
deno task deepre
# Lint, type check, format, and test
deno task check-all
# Individual checks
deno task lint
deno task check
deno task fmt
deno task test
```
## Use Cases
- Preliminary research for academic studies
- Market trends and competitive analysis
- Technology trend research
- Detailed information gathering on specific topics
## License
[MIT License](LICENSE)
Connection Info
You Might Also Like
MarkItDown
Python tool for converting files and office documents to Markdown.
Fetch
Retrieve and process content from web pages by converting HTML into markdown format.
chatbox
User-friendly Desktop Client App for AI Models/LLMs (GPT, Claude, Gemini, Ollama...)
Continue
Continue is an open-source project for seamless server management.
semantic-kernel
Build and deploy intelligent AI agents with Semantic Kernel's orchestration...
repomix
Repomix packages your codebase into AI-friendly formats for easy integration.