Skip to main content

AI-Powered Research Platform - Advanced CLI tool for intelligent research and report generation

Project description

SearchFlow

PyPI version Python Versions License: MIT

SearchFlow, powered by ArcDevs, is an AI-Powered Research Platform and advanced CLI tool leveraging ArcDevs Intelligence for intelligent research and automated report generation.

It utilizes AI agents to connect to services and perform comprehensive searches, analyze information, and compile reports based on user queries. (For educational purposes, this project explores concepts similar to those that might be used by services like searc.ai.)

Features

  • AI-Powered Research: Employs advanced AI for in-depth information gathering.
  • Multiple Report Types: Generate summaries, detailed reports, or multi-agent analyses.
  • Customizable Tone: Adjust the writing tone of reports (Objective, Formal, Analytical, etc.).
  • Domain Filtering: Focus research on specific websites or domains.
  • Interactive Mode: Conduct multiple research queries in a single session.
  • Configurable: Save default preferences for report types and tones.
  • Multiple Output Formats: Save reports as text, Markdown, or JSON.
  • Real-time Logging: (Optional) View the AI's research process live.

Installation

You can install SearchFlow using pip:

pip install searchflow

(This command will work once the package is published to PyPI. For local development, see the section below.)

Usage

Basic Search

searchflow "your research query here"

Example:

searchflow "latest advancements in quantum computing"

Options

  • Report Type (-t or --type):

    • summary: Quick overview (~2 min)
    • multi_agents_report: Collaborative analysis
    • research_report: Comprehensive research (~5 min)
    searchflow -t research_report "CRISPR gene editing ethics"
    
  • Report Tone (-o or --tone):

    • objective: Impartial and unbiased
    • formal: Academic and professional
    • analytical: Critical evaluation
    • persuasive: Convincing and argumentative
    • informative: Clear and comprehensive
    searchflow -o formal "economic impact of renewable energy"
    
  • Specific Domains (-d or --domains): Provide a space-separated list of domains.

    searchflow -d arxiv.org nature.com "dark matter theories"
    
  • No Real-time Logs (--no-logs): Disables the streaming output of agent activities.

    searchflow --no-logs "history of the internet"
    
  • Output to File (-O or --output with --format): Supported formats: text, markdown, json.

    searchflow "Python web frameworks" -O report.md --format markdown
    searchflow "Market analysis of AI startups" -O analysis.json --format json
    

Interactive Mode

For conducting multiple queries or easily changing settings per query:

searchflow --interactive

Inside interactive mode, type help for available commands. Current settings (type/tone) are shown in the prompt. Use set <option> <value> to change them for the session.

Configuration

Set your default preferences for report type, tone, and other settings:

searchflow --config

Settings are typically saved to ~/.searchflow/config.json.

Local Development

  1. Clone the repository:

    git clone https://github.com/arcdevs/searchflow.git
    cd searchflow
    

    (Replace with your actual repository URL if different)

  2. Create and activate a virtual environment:

    python -m venv venv
    # On macOS/Linux:
    source venv/bin/activate
    # On Windows (Git Bash or cmd):
    # venv\Scripts\activate
    
  3. Install in editable mode with development dependencies: The [dev] extra typically includes tools for testing, linting, etc.

    pip install -e .[dev]
    
  4. Run the CLI: Now you can run searchflow from your terminal, and any changes you make to the source code will be reflected immediately.

    searchflow --version
    

Contributing

Contributions are welcome! Please read CONTRIBUTING.md (you'll need to create this file with guidelines for contributors) and check the issue tracker for open tasks or to report bugs.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Authors

  • KOBULA
  • UTKRASH RISHI
  • ArcDevs Corp

Powered by ArcDevs Intelligence

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

searchflox-1.0.0.tar.gz (17.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

searchflox-1.0.0-py3-none-any.whl (14.8 kB view details)

Uploaded Python 3

File details

Details for the file searchflox-1.0.0.tar.gz.

File metadata

  • Download URL: searchflox-1.0.0.tar.gz
  • Upload date:
  • Size: 17.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.7

File hashes

Hashes for searchflox-1.0.0.tar.gz
Algorithm Hash digest
SHA256 e72ca90a3b27a67e5ee37c540eaf27030ab407857eb3cabb1f634a717b8ff355
MD5 cc7dd466cec77d6bc21ba4f4be79e5dd
BLAKE2b-256 6b129c160109142d8cd2079417220a353bcb1e06cff1ec3226a8cc79f1f57784

See more details on using hashes here.

File details

Details for the file searchflox-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: searchflox-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 14.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.7

File hashes

Hashes for searchflox-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 307b08dda0d9f7935f7152fb9334bdfe11d5424797ae85bd2be6d0d034efe3aa
MD5 103a0c0e6f2cb1acebbbf345e22195db
BLAKE2b-256 a233c603f94199807a1e17e3b53c95f0f22223e0c7687462891b463be03a1a6f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page