Agentic_search
by Code-Trees
This project combines semantic search capabilities with Large Language Models (LLM) to provide intelligent file search functionality in Linux systems. It allows users to search for files using natural language queries.
Last updated: N/A
What is Agentic_search?
Agentic_search is an intelligent file search assistant that integrates Large Language Models (LLMs) with semantic search to enable natural language file queries in Linux systems. It leverages BERT embeddings and Google's Gemini LLM to understand user intent and locate files based on their content and context.
How to use Agentic_search?
To use Agentic_search, first clone the repository and install the required dependencies. Configure your Gemini API key in a .env file. Then, run the main.py script and enter your search query when prompted. The system will extract the relevant filename, search the file system using semantic search, and display matching file locations.
Key features of Agentic_search
Natural language file search queries
Semantic search using BERT embeddings
File system integration with MCP server
Gemini LLM integration for query understanding
Automatic file extension inference
Use cases of Agentic_search
Finding specific files based on their content description
Quickly locating files without knowing their exact names
Searching for files related to a particular topic or task
Automating file search workflows using natural language commands
FAQ from Agentic_search
What is the purpose of the MCP server?
What is the purpose of the MCP server?
The MCP server handles file system operations efficiently.
What LLM is used for natural language understanding?
What LLM is used for natural language understanding?
Google's Gemini LLM is used for natural language understanding.
What is BERT used for?
What is BERT used for?
BERT embeddings are used for context-aware file matching in semantic search.
What do I do if I encounter the error 'Embeddings file not found'?
What do I do if I encounter the error 'Embeddings file not found'?
If you encounter the error "Embeddings file not found", run: cd ~ && find / -type f 2>/dev/null >> Desktop/LLm_To_agent
Can I extend the search capabilities of this tool?
Can I extend the search capabilities of this tool?
Yes, the architecture is designed to be extensible, making it easy to add new search capabilities.