iflow-mcp_amansingh0311-mcp-qdrant-openai 0.1.0__py3-none-any.whl

iflow_mcp_amansingh0311_mcp_qdrant_openai/mcp_qdrant_server.py

@@ -0,0 +1,164 @@
+#!/usr/bin/env python3
+"""
+Qdrant MCP Server - Provides vector search capabilities using OpenAI embeddings
+"""
+
+import os
+import json
+from typing import Dict, List, Optional, Any
+from dataclasses import dataclass
+
+# Load environment variables from .env file
+try:
+    from dotenv import load_dotenv
+
+    load_dotenv()
+except ImportError:
+    print(
+        "Warning: python-dotenv not installed. Environment variables must be set manually."
+    )
+
+import openai
+from qdrant_client import QdrantClient
+from qdrant_client.http.models import Filter, FieldCondition, MatchValue
+
+from mcp.server.fastmcp import FastMCP, Context
+
+
+# Initialize Qdrant client
+def get_qdrant_client() -> QdrantClient:
+    """Get Qdrant client from environment variables or defaults"""
+    url = os.getenv("QDRANT_URL", "http://localhost:6333")
+    api_key = os.getenv("QDRANT_API_KEY", None)
+
+    if url.startswith("http"):
+        return QdrantClient(url=url, api_key=api_key)
+    else:
+        # For local file-based storage
+        return QdrantClient(path=url)
+
+
+# Function to create embeddings
+def get_embedding(text: str, model: str = "text-embedding-3-small") -> List[float]:
+    """Get embeddings from OpenAI API"""
+    client = openai.OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
+
+    response = client.embeddings.create(model=model, input=text)
+
+    return response.data[0].embedding
+
+
+# Create MCP Server
+mcp = FastMCP("Qdrant-OpenAI")
+
+
+@dataclass
+class QdrantContext:
+    client: QdrantClient
+
+
+@mcp.tool()
+async def query_collection(
+    collection_name: str,
+    query_text: str,
+    limit: int = 5,
+    model: str = "text-embedding-3-small",
+) -> str:
+    """
+    Search a Qdrant collection using semantic search with OpenAI embeddings.
+
+    Args:
+        collection_name: Name of the Qdrant collection to search
+        query_text: The search query in natural language
+        limit: Maximum number of results to return (default: 5)
+        model: OpenAI embedding model to use (default: text-embedding-3-small)
+
+    Returns:
+        JSON string containing search results
+    """
+    # Get Qdrant client from context
+    client = get_qdrant_client()
+
+    # Generate embedding for query
+    query_vector = get_embedding(query_text, model)
+
+    # Search Qdrant
+    try:
+        search_result = client.search(
+            collection_name=collection_name,
+            query_vector=query_vector,
+            limit=limit,
+        )
+
+        # Format results
+        results = []
+        for scored_point in search_result:
+            result = {
+                "id": scored_point.id,
+                "score": scored_point.score,
+                "payload": scored_point.payload,
+            }
+            results.append(result)
+
+        return json.dumps({"results": results}, indent=2)
+
+    except Exception as e:
+        return json.dumps({"error": str(e)})
+
+
+@mcp.tool()
+async def list_collections() -> str:
+    """
+    List all available collections in the Qdrant database.
+
+    Returns:
+        JSON string containing the list of collections
+    """
+    client = get_qdrant_client()
+
+    try:
+        collections = client.get_collections()
+        return json.dumps(
+            {"collections": [c.name for c in collections.collections]}, indent=2
+        )
+    except Exception as e:
+        return json.dumps({"error": str(e)})
+
+
+@mcp.tool()
+async def collection_info(collection_name: str) -> str:
+    """
+    Get information about a specific collection.
+
+    Args:
+        collection_name: Name of the collection
+
+    Returns:
+        JSON string containing collection information
+    """
+    client = get_qdrant_client()
+
+    try:
+        collection_info = client.get_collection(collection_name)
+        return json.dumps(
+            {
+
+                "vectors_count": collection_info.vectors_count,
+                "points_count": collection_info.points_count,
+                "dimension": collection_info.config.params.vectors.size,
+                "distance": collection_info.config.params.vectors.distance,
+            },
+            indent=2,
+        )
+    except Exception as e:
+        return json.dumps({"error": str(e)})
+
+
+def main():
+    """Main entry point for the MCP server"""
+    mcp.run(transport="stdio")
+
+
+if __name__ == "__main__":
+    # Run the server
+    main()

iflow_mcp_amansingh0311_mcp_qdrant_openai-0.1.0.dist-info/METADATA

@@ -0,0 +1,116 @@
+Metadata-Version: 2.4
+Name: iflow-mcp_amansingh0311-mcp-qdrant-openai
+Version: 0.1.0
+Summary: MCP Qdrant Server with OpenAI Embeddings
+Requires-Python: >=3.10
+Requires-Dist: mcp>=1.2.0
+Requires-Dist: openai>=1.0.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: qdrant-client>=1.6.0
+Provides-Extra: cli
+Requires-Dist: mcp[cli]; extra == 'cli'
+Description-Content-Type: text/markdown
+
+[![MseeP.ai Security Assessment Badge](https://mseep.net/pr/amansingh0311-mcp-qdrant-openai-badge.png)](https://mseep.ai/app/amansingh0311-mcp-qdrant-openai)
+
+# MCP Qdrant Server with OpenAI Embeddings
+
+[![smithery badge](https://smithery.ai/badge/@amansingh0311/mcp-qdrant-openai)](https://smithery.ai/server/@amansingh0311/mcp-qdrant-openai)
+
+This MCP server provides vector search capabilities using Qdrant vector database and OpenAI embeddings.
+
+## Features
+
+- Semantic search in Qdrant collections using OpenAI embeddings
+- List available collections
+- View collection information
+
+## Prerequisites
+
+- Python 3.10+ installed
+- Qdrant instance (local or remote)
+- OpenAI API key
+
+## Installation
+
+### Installing via Smithery
+
+To install Qdrant Vector Search Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@amansingh0311/mcp-qdrant-openai):
+
+```bash
+npx -y @smithery/cli install @amansingh0311/mcp-qdrant-openai --client claude
+```
+
+### Manual Installation
+1. Clone this repository:
+
+   ```bash
+   git clone https://github.com/yourusername/mcp-qdrant-openai.git
+   cd mcp-qdrant-openai
+   ```
+
+2. Install dependencies:
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+## Configuration
+
+Set the following environment variables:
+
+- `OPENAI_API_KEY`: Your OpenAI API key
+- `QDRANT_URL`: URL to your Qdrant instance (default: "http://localhost:6333")
+- `QDRANT_API_KEY`: Your Qdrant API key (if applicable)
+
+## Usage
+
+### Run the server directly
+
+```bash
+python mcp_qdrant_server.py
+```
+
+### Run with MCP CLI
+
+```bash
+mcp dev mcp_qdrant_server.py
+```
+
+### Installing in Claude Desktop
+
+```bash
+mcp install mcp_qdrant_server.py --name "Qdrant-OpenAI"
+```
+
+## Available Tools
+
+### query_collection
+
+Search a Qdrant collection using semantic search with OpenAI embeddings.
+
+- `collection_name`: Name of the Qdrant collection to search
+- `query_text`: The search query in natural language
+- `limit`: Maximum number of results to return (default: 5)
+- `model`: OpenAI embedding model to use (default: text-embedding-3-small)
+
+### list_collections
+
+List all available collections in the Qdrant database.
+
+### collection_info
+
+Get information about a specific collection.
+
+- `collection_name`: Name of the collection to get information about
+
+## Example Usage in Claude Desktop
+
+Once installed in Claude Desktop, you can use the tools like this:
+
+```
+What collections are available in my Qdrant database?
+
+Search for documents about climate change in my "documents" collection.
+
+Show me information about the "articles" collection.
+```

iflow_mcp_amansingh0311_mcp_qdrant_openai-0.1.0.dist-info/RECORD

@@ -0,0 +1,6 @@
+iflow_mcp_amansingh0311_mcp_qdrant_openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+iflow_mcp_amansingh0311_mcp_qdrant_openai/mcp_qdrant_server.py,sha256=oddX4Yccy7rNQdtXCfLaW-1Z9FWpmQ33lVoOSJuXs-I,4275
+iflow_mcp_amansingh0311_mcp_qdrant_openai-0.1.0.dist-info/METADATA,sha256=RA6WM_gZWdLNBntjljcg152PSX1nszSQx1Rw4ec_2uY,2955
+iflow_mcp_amansingh0311_mcp_qdrant_openai-0.1.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+iflow_mcp_amansingh0311_mcp_qdrant_openai-0.1.0.dist-info/entry_points.txt,sha256=5Y0zdzV8uqQe7R2ao6p9g2Rh0C0jF72MO9bLmAZO81c,103
+iflow_mcp_amansingh0311_mcp_qdrant_openai-0.1.0.dist-info/RECORD,,

iflow_mcp_amansingh0311_mcp_qdrant_openai-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.28.0
+Root-Is-Purelib: true
+Tag: py3-none-any

iflow_mcp_amansingh0311_mcp_qdrant_openai-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+mcp-qdrant-openai = iflow_mcp_amansingh0311_mcp_qdrant_openai.mcp_qdrant_server:main