Skip to main content

The system is designed to process user descriptions or inputs related to vintage gaming consoles, such as the Interton Video Computer 4000, and generate structured summaries or specifications. It focu

Project description

VintageConsoleInfo

PyPI version License: MIT Downloads LinkedIn

A Python package for extracting structured information about vintage gaming consoles from unstructured user input. Ideal for collectors, enthusiasts, and restorers who need quick access to key details like hardware specs, game libraries, and historical context.


📦 Installation

Install the package via pip:

pip install vintageconsoleinfo

🚀 Features

  • Extracts structured data from textual descriptions of vintage consoles (e.g., Interton Video Computer 4000).
  • Supports customizable LLM backends (default: LLM7).
  • Uses regex pattern matching for reliable data extraction.
  • Works with OpenAI, Anthropic, Google, or any LangChain-compatible LLM.

🔧 Usage

Basic Usage (Default LLM7)

from vintageconsoleinfo import vintageconsoleinfo

# Example input about the Interton Video Computer 4000
user_input = """
The Interton Video Computer 4000 is a 1983 console with a Z80 CPU,
4KB RAM, and a built-in keyboard. It supports games like 'Space Invaders'
and 'Breakout'.
"""

response = vintageconsoleinfo(user_input)
print(response)  # Structured output (e.g., specs, games, etc.)

Custom LLM (e.g., OpenAI)

from langchain_openai import ChatOpenAI
from vintageconsoleinfo import vintageconsoleinfo

llm = ChatOpenAI(model="gpt-3.5-turbo")
response = vintageconsoleinfo(user_input, llm=llm)

Custom LLM (e.g., Anthropic)

from langchain_anthropic import ChatAnthropic
from vintageconsoleinfo import vintageconsoleinfo

llm = ChatAnthropic(model="claude-2")
response = vintageconsoleinfo(user_input, llm=llm)

Custom LLM (e.g., Google)

from langchain_google_genai import ChatGoogleGenerativeAI
from vintageconsoleinfo import vintageconsoleinfo

llm = ChatGoogleGenerativeAI(model="gemini-pro")
response = vintageconsoleinfo(user_input, llm=llm)

🔑 API Key Configuration

Default (LLM7)

  • Uses LLM7_API_KEY from environment variables or falls back to a default.
  • Free tier rate limits are sufficient for most use cases.
  • Get a free API key: LLM7 Registration.

Override API Key

response = vintageconsoleinfo(user_input, api_key="your_llm7_api_key")

📌 Parameters

Parameter Type Description
user_input str Text describing a vintage console (required).
api_key Optional[str] LLM7 API key (optional; defaults to env var).
llm Optional[BaseChatModel] Custom LangChain LLM (optional; defaults to ChatLLM7).

📝 Notes

  • The package uses LLM7 by default (via langchain_llm7).
  • For production use, ensure your LLM backend meets rate limits.
  • Extracted data follows a structured format (regex-based).

📜 License

MIT


📧 Support & Issues

Report bugs or request features at: 🔗 GitHub Issues


👤 Author

Eugene Evstafev 📧 hi@euegne.plus 🔗 GitHub: chigwell


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

vintageconsoleinfo-2025.12.21163636.tar.gz (4.5 kB view details)

Uploaded Source

Built Distribution

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

vintageconsoleinfo-2025.12.21163636-py3-none-any.whl (5.2 kB view details)

Uploaded Python 3

File details

Details for the file vintageconsoleinfo-2025.12.21163636.tar.gz.

File metadata

File hashes

Hashes for vintageconsoleinfo-2025.12.21163636.tar.gz
Algorithm Hash digest
SHA256 b79b623eef1b7b86ffb44695fc87562793cfa7adc8d0b0daf2cf4167ed0e9740
MD5 1168c2280d9f9c78536195767eee72e8
BLAKE2b-256 c8a2255e756d82da5573e47f1537680370fcbef337143cc4046c35aa23682234

See more details on using hashes here.

File details

Details for the file vintageconsoleinfo-2025.12.21163636-py3-none-any.whl.

File metadata

File hashes

Hashes for vintageconsoleinfo-2025.12.21163636-py3-none-any.whl
Algorithm Hash digest
SHA256 6bae7c593302bd8cc13cba93989474ab4c2c1d8773a10a001f08fee2dbad361d
MD5 cd303d7487ee3e557aef82176d73f15b
BLAKE2b-256 6ccc9ef63e6f6815385514c2675e020b4027da5934e1c406703b1a3cbdb81766

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