# Rank documents by relevance with AI

Source: https://openflow.run/en/integrations/topics/semantic-search/

[All integrations](https://openflow.run/en/integrations/)

Create text embeddings and rerank documents by relevance to improve semantic search.

[View available services](https://openflow.run/en/integrations/topics/semantic-search/#topic-services)

20,000 free app calls per month (paid services billed separately)

## What you can do

Connect a query with the most relevant passages in a document collection. Generate text embeddings for similarity workflows or rerank candidate documents around a research question.

### Rank documents by relevance

Create text embeddings and rerank documents by relevance to improve semantic search.

### Search team knowledge

Retrieve relevant passages from indexed team documents.

## Available services

### [AIsa](https://openflow.run/en/integrations/aisa/)

Provided by Open Flow

Create text embeddings and rerank documents by relevance to improve semantic search.

1121 actionsAPI key

### [OOMOL RAG](https://openflow.run/en/integrations/oomol_rag/)

No authorization

Use OOMOL services with your current team.

18 actionsNo authorization

## All actions

3 actions

### Create Jina Embeddings

Compute Jina embedding vectors for supplied text without storing a retrieval index. AISA documents 1024-dimensional output for the supported models; billing is token-based.

`aisa.create_jina_embeddings`

### Rerank Jina Documents

Rank supplied documents against a query using a Jina reranker, preserving original indexes for retrieval pipelines. No provider index or stored document collection is created; billing is token-based.

`aisa.rerank_jina_documents`

### Retrieve

Retrieve the most relevant text chunks from the current OOMOL team's knowledge base.

`oomol_rag.retrieve`

No actions match your search.
