File Search Assistant with LLM Integration
@Code-Trees
About File Search Assistant with LLM Integration
Learn how to: ✅ Build a file-search AI using natural language queries ✅ Create embeddings from local Linux files using Hugging Face models ✅ Integrate Gemini API (Google AI Studio) into your local apps ✅ Use MCP to control multiple agents with server-client architecture ✅ Apply c
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"Agentic_search": {
"command": "python",
"args": [
"main.py"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is File Search Assistant with LLM Integration?
File Search Assistant with LLM Integration combines semantic search (BERT embeddings) with Google’s Gemini large language model to enable natural‑language file queries on Linux systems. It is built as an MCP server for file‑system integration.
How to use File Search Assistant with LLM Integration?
Install Python 3.8+ and dependencies (pip install -r requirements.txt), set the GEMINI_API_KEY in a .env file, then run python main.py. Enter a natural‑language query when prompted; the system extracts a filename via the LLM, performs semantic search, and displays matching file locations.
Key features of File Search Assistant with LLM Integration
- Natural language file search queries
- Semantic search using BERT embeddings
- Gemini LLM integration for query understanding
- Automatic file extension inference
- MCP server for file system operations
- Extensible architecture
Use cases of File Search Assistant with LLM Integration
- Find a Python script that handles file operations by describing its purpose
- Locate a document by describing its content or context
- Search for files when the exact filename is forgotten
FAQ from File Search Assistant with LLM Integration
What are the prerequisites?
Python 3.8 or higher, a Linux operating system, and a Gemini API key. A CUDA‑compatible GPU is optional for faster processing.
How does the semantic search work?
It uses BERT embeddings for context‑aware file matching, combined with the LLM to convert natural language into search terms.
Where are the embeddings stored?
Embeddings are stored in the file OSData_store.pth inside the project directory.
What should I do if I get “Embeddings file not found”?
Run the command cd ~ && find / -type f 2>/dev/null >> Desktop/LLm_To_agent to rebuild the file index.
What transport or authentication does it use?
The README does not specify transport details. Authentication is handled via the Gemini API key set in the .env file.
More Search MCP servers
Tavily Mcp
tavily-aiProduction ready MCP server with real-time search, extract, map & crawl.
Kagi MCP server
kagisearchThe Official Model Context Protocol (MCP) server for Kagi Search & other tools.
Brave Search MCP Server
mikechaoAn MCP Server implementation that integrates the Brave Search API, providing, Web Search, Local Points of Interest Search, Image Search, Video Search, News Search and LLM Context Search capabilities
G-Search MCP
jae-jaeA powerful MCP server for Google search that enables parallel searching with multiple keywords simultaneously.
小红书自动搜索评论工具（MCP Server 2.0）
chenningling这是一款基于 Playwright 开发的小红书自动搜索和评论工具，作为 MCP Server，可通过特定配置接入 MCP Client（如Claude for Desktop），帮助用户自动完成登录小红书、搜索关键词、获取笔记内容及发布AI生成评论等操作。
Comments