Overview
What is DeepRe - AI駆動の深い調査レポート生成ツール?
DeepRe - AI駆動の深い調査レポート生成ツール is a Deno-based CLI tool that automatically generates in-depth research reports on a specified theme. It leverages the Google Gemini AI API to iteratively collect and evaluate information until sufficient quality is reached, then produces a comprehensive report in Markdown format. The tool is designed for users who need systematic, automated research on any topic, with full Japanese language support.
How to use DeepRe - AI駆動の深い調査レポート生成ツール?
Install globally with deno task install, then run deepre "調査テーマ". Optionally specify an API key with -k, output directory with -o (default ./research), Gemini model with -m (default gemini-2.0-flash), and iteration count with -i (default 10). The API key can also be set via the GEMINI_API_KEY environment variable. Development tasks include deno task deepre for running in dev mode and deno task check-all for linting, type checking, formatting, and tests.
Key features of DeepRe - AI駆動の深い調査レポート生成ツール
- Iterative research process with automatic quality evaluation
- Integrates with Gemini 2.0 AI models for advanced search and analysis
- Automatically generates an optimal research plan from a theme
- Full Japanese language support for themes and output
- Produces formatted Markdown reports
Use cases of DeepRe - AI駆動の深い調査レポート生成ツール
- Preliminary research for academic projects
- Market trend and competitive analysis
- Technology trend investigation
- In-depth information gathering on specific topics
FAQ from DeepRe - AI駆動の深い調査レポート生成ツール
What runtime and API key are required?
Deno runtime is required, along with a Google Gemini API key. The key can be passed via the GEMINI_API_KEY environment variable or the -k command-line option.
What is the default model and iteration count?
The default Gemini model is gemini-2.0-flash and the default iteration count is 10. You can override both with the -m and -i flags respectively.
What output format does DeepRe produce?
Reports are output as formatted Markdown files. The default output directory is ./research, configurable with the -o flag.
Does DeepRe support Japanese?
Yes, it fully supports Japanese for both setting themes and generating output. The README and usage examples are also in Japanese.
