Qdrant DevContainer for File Embeddings

Name: Qdrant DevContainer for File Embeddings
Author: questmapping

@questmapping

代码仓库

关于 Qdrant DevContainer for File Embeddings

暂无概览

基本信息

分类

记忆与知识

运行时

python

传输方式

stdio

发布者

questmapping

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "qdrant_server_devcontainer_for_rag_mcp": {
      "command": "python",
      "args": [
        "ingest.py"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Qdrant DevContainer for File Embeddings?

Qdrant DevContainer for File Embeddings provides a development container setup for running Qdrant with file embeddings. It includes everything needed to index and search text documents using vector similarity search, making it ideal for developers building local semantic search or RAG systems.

How to use Qdrant DevContainer for File Embeddings?

Ensure Docker Desktop is running, open the project folder in VS Code, and click “Reopen in Container” (or use F1 → “Dev Containers: Reopen in Container”). Place your text files in the data/ directory. After the container builds, Qdrant starts automatically (access at http://localhost:6333, though the port may be dynamically assigned). Run python ingest.py from within the container to index your files.

Key features of Qdrant DevContainer for File Embeddings

Qdrant vector database runs in the background automatically
Automatic file indexing with sentence-transformers (all-MiniLM-L6-v2)
Collection local-docs created with cosine similarity
Supports .txt, .md, and .pdf files
Python environment with all necessary dependencies pre-installed
VS Code Python extension included for easy development

Use cases of Qdrant DevContainer for File Embeddings

Quickly index a folder of local text/markdown/PDF documents for semantic search
Prototype a RAG (Retrieval-Augmented Generation) pipeline without cloud services
Experiment with Qdrant’s similarity search endpoints in a reproducible environment
Build a local knowledge base for AI assistants using vector embeddings

FAQ from Qdrant DevContainer for File Embeddings

What are the prerequisites to run this DevContainer?

You need Docker Desktop running on your system, VS Code with the Remote – Containers extension, and an internet connection to download dependencies.

Where should I place my files for indexing?

Place all your text, markdown, or PDF files in the data/ directory inside the project folder before running the ingestion script.

How do I start indexing the files?

After the container is built and Qdrant is running, execute python ingest.py from the terminal inside the container.

Which file formats are supported?

The current version supports .txt, .md, and .pdf files. Other extensions will be ignored.

How do I access the Qdrant dashboard or API?

By default Qdrant is accessible at http://localhost:6333. However, the port is dynamically assigned—check the output panel after container build if that port does not work.