Add Sparse and Hybrid retrieval modes to Qdrant vector store

[janskola]

Documents the Retrieval Mode (Dense/Sparse/Hybrid) field added to the Qdrant vector store node in FlowiseAI/Flowise#6647.

Adds a new "Retrieval Modes" section (between Setup and Filtering) covering:

• The Retrieval Mode field and its three options (Dense/Sparse/Hybrid, default Dense)
• The mode-specific Additional Parameters fields: Dense Vector Name, Sparse Vector Name, Sparse Inference Model, Fusion Method
• That Sparse Inference Model defaults to qdrant/bm25, the only supported value in this version
• That creating a new collection in Sparse or Hybrid mode auto-configures both a named dense and named sparse vector

Also adds a Qdrant Hybrid Queries link to Resources, and three new/recaptured screenshots (qdrant/3.png, 4.png, 5.png).

Ref PR: FlowiseAI/Flowise#6647

[gemini-code-assist]

Caution

The consumer version of Gemini Code Assist on GitHub has been sunset. All code review activity has officially ceased.