Replace PostgreSQL with Qdrant as embeddings database

[Copilot]

This PR replaces PostgreSQL (with pgvector extension) with Qdrant as the vector database for storing and searching embeddings. Qdrant is a specialized vector database optimized for similarity search operations.

Key changes:

1. Added Qdrant client as a dependency
2. Created a new qdrantClient.ts file that handles:
   • Collection initialization
   • Embedding insertion
   • Vector similarity search
3. Updated Docker configuration to use Qdrant container
4. Modified insertion and search operations to use Qdrant's API
5. Updated documentation with new setup instructions

Benefits:

• Simplified setup (no database migrations required)
• Better performance for vector similarity search
• More specialized functionality for vector operations
• Cleaner API for vector operations

Example usage:

// Search for similar content
const embedding = await createEmbedding("Rock artist");
searchEmbedding(embedding);

// Results use cosine similarity (higher scores = more similar)
Search Results: [
  {
    resource_link: 'https://en.wikipedia.org/wiki/Dark_Horse_%E2%80%93_A_Live_Collection',
    caption: 'Dark Horse – A Live Collection',
    cosine_distance: 0.8029609909628218
  },
  // ...more results
]

Fixes #1.

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.