Qdrant DevContainer for File Embeddings
Description
# Qdrant DevContainer for File Embeddings This project 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. ## Prerequisites 1. Docker Desktop must be…
About
# Qdrant DevContainer for File Embeddings This project 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. ## Prerequisites 1. Docker Desktop must be running before starting the devcontainer 2…
Details
- Author
- questmapping
- Downloads
- 222
- Categories
- Knowledge Base
Jump to
- 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
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Qdrant DevContainer for File EmbeddingsCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
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.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"qdrant devcontainer for file embeddings": {
"qdrant_server_devcontainer_for_rag_mcp": {
"command": "python",
"args": [
"ingest.py"
]
}
}
}
}McpServers
{
"qdrant_server_devcontainer_for_rag_mcp": {
"command": "python",
"args": [
"ingest.py"
]
}
}Qdrant DevContainer for File Embeddings
This project 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.
Prerequisites
1. Docker Desktop must be running before starting the devcontainer
2. VS Code with the Remote - Containers extension
3. Internet connection (for downloading dependencies)
Getting Started
1. Ensure Docker Desktop is running on your system
2. Open this folder in VS Code
3. Click the green "Reopen in Container" button in the bottom right corner
- Or press F1 and type "Dev Containers: Reopen in Container"
Project Structure
qdrant_server_devcontainer/ ├── .devcontainer/ │ ├── devcontainer.json │ └── Dockerfile ├── requirements.txt ├── ingest.py └── data/ # Place your text files hereUsage
1. Place your text files in the data/ directory
2. The container will automatically start Qdrant
3. After the container is built You should be able to access Qdrant at http://localhost:6333
4. Run the ingestion script manually from within the container:
python ingest.py
Features
- Qdrant vector database running in the background
- Automatic file indexing using sentence-transformers
- Python environment with all necessary dependencies
- VS Code Python extension pre-installed
Technical Details
- Qdrant runs on a dynamically assigned port (check the output panel after container build)
- Uses all-MiniLM-L6-v2 for text embeddings
- Creates a collection named "local-docs" with cosine similarity
- Supports text files (.txt), markdown files (.md), and PDF files (.pdf) in the data directory
Troubleshooting
1. If the container fails to start:
- Ensure Docker Desktop is running
- Check that no other process is using the dynamically assigned port
- Verify all dependencies are properly installed
2. If files aren't being indexed:
- Check that files are in the data/ directory
- Verify file extensions are supported (currently .txt, .md, .pdf)
- Ensure files are readable by the container
License
MIT License
TODO
- handle giant PDFs efficiently, - extract text per page using parallel processing, - embed and push each chunk as it’s ready, - support GPU embedding if torch.cuda.is_available()? - add support for epub filesSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
