UnrealGPT
Retrieval-Augmented-Generation of over 1700+ pages of Unreal Engine documentation served through FAISS + OpenAI with LangChain
Install / Use
/learn @416rehman/UnrealGPTREADME
UnrealGPT
This is a LangChain project with over 1700+ pages of documentation scraped from https://docs.unrealengine.com/5.1/en-US/
Data is scraped using BeautifulSoup and stored in the data\scraping_cache folder. If the data is already scraped, it will be loaded from the cache instead of scraping again to save time.
FAISS is used as the vector store to store the OpenAI embeddings. The FAISS index is stored in the data folder with the .index extension. If the index is already built, it will be loaded from the cache instead of building again to save time.
To start fresh (scrapping and building the index again), delete the data folder.
How to run
All commands are run from the root of the repository.
-
Clone this repository.
-
Run
pip install -r requirements.txtto install the dependencies. -
Set the
OPENAI_API_KEYenvironment variable to your OpenAI API key on your system. -
Install langchain-serve then run
lc-serve deploy local main.
Visit http://localhost:8080/docs to interact with the API. (Make sure to provide the OPENAI_API_KEY in the request)
Related Skills
prose
349.9kOpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.
Writing Hookify Rules
109.8kThis skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.
Command Development
109.8kThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
MCP Integration
109.8kThis skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
