Hybrid Search

Hybrid Text + Multimodal Search

Combines text embeddings with multimodal embeddings using weighted fusion for comprehensive retrieval across modalities.

1 stage

Read Docs

Integrate Now

No credit card to start · Build from $25/mo

Pipeline Stages

hybrid_search

filter

feature_search

View parameters

{
  "searches": [
    {
      "feature_uri": "mixpeek://text_extractor@v1/multilingual_e5_large_instruct_v1",
      "query": {
        "input_mode": "text",
        "value": "{{INPUT.query}}"
      },
      "top_k": 100,
      "weight": 0.7
    },
    {
      "feature_uri": "mixpeek://multimodal_extractor@v1/vertex_multimodal_embedding",
      "query": {
        "input_mode": "text",
        "value": "{{INPUT.query}}"
      },
      "top_k": 50,
      "weight": 0.3
    }
  ],
  "final_top_k": 25,
  "fusion": "weighted"
}

Input Schema

query

text

required

Search query text

e.g. machine learning algorithms

Use Cases

Enterprise search
Technical documentation search
Cross-modal content retrieval

Requirements

Collection must have text embeddings indexed
Collection must have multimodal embeddings indexed

Ready to use this template?

Clone it into your namespace and start querying in minutes.