An AI research bot that uses web sources
Project description
AI Research Assistant
An automated research tool that uses web scraping, AI, and natural language processing to gather, analyze, and synthesize information on specified topics.
Features
- Automated web searching and content extraction
- AI-powered content analysis and summarization
- Duplicate content detection and removal
- Progress tracking and research history
- Customizable research parameters
- Structured output in various formats
- File-based research organization
Requirements
- Python 3.x
- OpenAI API key
- Internet connection
Dependencies
openai
googlesearch-python
requests
beautifulsoup4
datetime
Installation
- Clone the repository
- Install required packages:
pip install openai googlesearch-python requests beautifulsoup4
- Set up your API key
Usage
researchBot = ResearchSession()
researchBot.apiKey = 'your-api-key'
researchBot.topic = 'Your Research Topic'
researchBot.numSources = 3 # Number of desired sources
researchBot.outputFormat = 'formal essay' # Or other format
researchBot.startResearch()
File Structure
The program creates a research folder with timestamped subfolders containing:
links.txt: List of discovered URLshistory.txt: Research session historyextracted_data.txt: Processed content from sourcesfinal_research.txt: Final compiled research output
Key Methods
webSearch(): Performs Google searchesreadWebpage(): Extracts content from URLsgetAIResponse(): Interfaces with AI for analysiscleanLinksFileForDuplicates(): Removes duplicate sourcescleanExtractedDataFileForDuplicateData(): Removes redundant contentfinalize(): Generates final research document
Research Process
- Conducts web searches for relevant sources
- Extracts and processes content from sources
- AI analyzes and summarizes information
- Removes duplicates and organizes data
- Continues until research criteria are met
- Generates final formatted document
Notes
- Requires valid API key for AI services
- Research quality depends on source availability
- Internet connectivity required throughout process
- Output format can be customized
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
gptresearch-5.0.1.tar.gz
(18.4 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file gptresearch-5.0.1.tar.gz.
File metadata
- Download URL: gptresearch-5.0.1.tar.gz
- Upload date:
- Size: 18.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3c8771812faa99ee4bb81bf8ef65d0181d57d74a89ef46c5fa6d0e1d03964149
|
|
| MD5 |
d3c325d4bcd456e32bdf9bf1b4c80f93
|
|
| BLAKE2b-256 |
75ff6461ef3ae2967c31e3aebeb1dd63f7fe5bb87c5a6aa040f3d64f800e9f64
|
File details
Details for the file gptresearch-5.0.1-py3-none-any.whl.
File metadata
- Download URL: gptresearch-5.0.1-py3-none-any.whl
- Upload date:
- Size: 19.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
632966957da70e2f1d47d8ec1e2eb7087bf93c633be3a369c6eaf6b1206011a1
|
|
| MD5 |
5236b716d9d334a91b605eb7be8a67e9
|
|
| BLAKE2b-256 |
d077f87a63613075574ee3817568d9bcc29970759fa584a78fb4eaecb1180557
|