1.0.27 • Published 4 months ago

gpt-researcher v1.0.27

Weekly downloads
-
License
MIT
Repository
github
Last release
4 months ago

GPT Researcher

The gpt-researcher npm package is a WebSocket client for interacting with GPT Researcher.

Website Documentation Discord Follow

PyPI version GitHub Release Open In Colab Docker Image Version

English | 中文 | 日本語 | 한국어

🔎 GPT Researcher

GPT Researcher is an open deep research agent designed for both web and local research on any given task.

The agent produces detailed, factual, and unbiased research reports with citations. GPT Researcher provides a full suite of customization options to create tailor made and domain specific research agents. Inspired by the recent Plan-and-Solve and RAG papers, GPT Researcher addresses misinformation, speed, determinism, and reliability by offering stable performance and increased speed through parallelized agent work.

Our mission is to empower individuals and organizations with accurate, unbiased, and factual information through AI.

Installation

npm install gpt-researcher

Usage

Basic Usage

const GPTResearcher = require('gpt-researcher');

const researcher = new GPTResearcher({
  host: 'http://localhost:8000',
  logListener: (data) => console.log('logListener logging data: ',data)
});

researcher.sendMessage({
  query: 'Does providing better context reduce LLM hallucinations?'
});

Log Data Structure

The logListener function receives log data with this structure:

{
  type: 'logs',
  content: string,    // e.g., 'added_source_url', 'researching', 'scraping_content'
  output: string,     // Human-readable output message
  metadata: any       // Additional data (URLs, counts, etc.)
}

Common log content types:

'added_source_url': New source URL added
'researching': Research status updates
'scraping_urls': Starting URL scraping
'scraping_content': Content scraping progress
'scraping_images': Image processing updates
'scraping_complete': Scraping completion
'fetching_query_content': Query processing

Parameters

  • task (required): The research question or task to investigate
  • reportType (optional): Type of report to generate (default: 'research_report')
  • reportSource (optional): Source of the report data (default: 'web')
  • tone (optional): Tone of the report
  • queryDomains (optional): Array of domain names to filter search results

Advanced usage

const researcher = new GPTResearcher({
  host: 'http://localhost:8000',
  logListener: (data) => console.log('Log:', data)
});

// Advanced usage with all parameters
researcher.sendMessage({
  task: "What are the latest developments in AI?",
  reportType: "research_report",
  reportSource: "web",
  queryDomains: ["techcrunch.com", "wired.com"]
});
1.0.27

4 months ago

1.0.26

4 months ago

1.0.25

4 months ago

1.0.24

4 months ago

1.0.23

4 months ago

1.0.22

4 months ago

1.0.21

4 months ago

1.0.20

4 months ago

1.0.9

4 months ago

1.0.8

4 months ago

1.0.7

4 months ago

1.0.6

4 months ago

1.0.5

4 months ago

1.0.4

6 months ago

1.0.3

6 months ago

1.0.2

6 months ago

1.0.1

6 months ago

1.0.0

6 months ago