DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to combine keyword and semantic search in one query with Qdrant

Use hybrid search with dense and sparse vectors so results match both meaning and exact terms.

Short answer: Run Qdrant locally or on Qdrant Cloud; then Store a dense vector for meaning and a sparse vector for full-text search on each point; Query both vectors in a single request and merge results with Reciprocal Rank Fusion. All steps.

Who it is forA team whose semantic search misses exact product codes and names that keyword search would catch.

The problemPure semantic search is fuzzy on exact terms, and pure keyword search misses paraphrases.

The outcomeOne query that blends semantic and keyword matches, merged with a fusion strategy such as RRF.

What you need first

  • Docker for the local server, or a free tier cluster on Qdrant Cloud
  • A client library, for example the Python client
  • Embeddings from a model of your choice

Steps

  1. Run Qdrant locally or on Qdrant Cloud
  2. Store a dense vector for meaning and a sparse vector for full-text search on each point
  3. Query both vectors in a single request and merge results with Reciprocal Rank Fusion
  4. Tune results with Maximal Marginal Relevance or the Relevance Feedback Query if needed
  5. Install the Qdrant agent skills so your coding assistant can help with hybrid search and quantization choices

Prompt for your agent

Using qdrant/qdrant, set up a collection with dense and sparse vectors for <dataset>, run hybrid queries merged with Reciprocal Rank Fusion, and compare the top 5 results against dense-only search for <queries>.

Caveat. The README describes hybrid search but leaves the query syntax to the docs and client libraries.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for qdrant/qdrant and "Combine keyword and semantic search in one query"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer