This adds support for vector specific HNSW configurations. This allows to set different HNSW parameters for different vectors in a multi-vector collection better fine tune performance.

In this example create collection request, modified_vector utilizes different HNSW parameters:

{
    "vectors": {
        "simple_vector": {
            "distance": "Dot",
            "size": 10
        },
        "modified_vector": {
            "distance": "Dot",
            "size": 300,
            "hnsw_config": {
                "m": 123,
                "ef_construct": 456
            }
        }
    },
    "hnsw_config": {
        "m": 1000,
        "ef_construct": 1000
    }
}

Tasks

• Accept vector specific HNSW params via REST/gRPC, and validate these
• Persist vector specific HNSW configs
• Add vector specific HNSW config to segment config
• Base vector specific config (diff) upon collection config (full)
• Use vector specific HNSW config when building graphs
• Update OpenAPI/gRPC files
• Add basic integration test

After merge

• Remove previous branch (multi-vector-hnsw-config)
• Update documentation
• Do the same for the quantization configuration (Add vector specific quantization configuration #1680)

All Submissions:

• Have you followed the guidelines in our Contributing document?
• Have you checked to ensure there aren't other open Pull Requests for the same update/change?

New Feature Submissions:

1. Does your submission pass tests?
2. Have you lint your code locally using cargo fmt command prior to submission?
3. Have you checked your code using cargo clippy command?

Changes to Core Features:

• Have you added an explanation of what your changes do and why you'd like us to include them?
• Have you written new tests for your core changes, as applicable?
• Have you successfully ran tests with your changes locally?