# Welcome

**Qyver** is a Python framework designed for AI Engineers developing high-performance search and recommendation applications that integrate both structured and unstructured data.

#### **Why Qyver?**

Enhance vector search relevance by encoding metadata alongside unstructured data into vectors. Learn more at Why Qyver.

#### **What is Qyver?**

A framework and self-hostable REST API server that seamlessly connects your data, vector database, and backend services.

#### **How does it work?**

Build custom data and query embedding models using pre-trained encoders from **sentence-transformers**, **open-clip**, and custom encoders for numbers, timestamps, and categorical data. Explore concepts and use cases for examples.

If you find Qyver useful, give us a [⭐](mailto:undefined)!

<figure><img src="/files/y6SpLsW5HPvWORoic7UD" alt=""><figcaption></figcaption></figure>

### Getting Started

<table data-view="cards"><thead><tr><th></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td>Why Qyver?</td><td><a href="/files/rwrQKRPuBJQNZ8wkaFWM">/files/rwrQKRPuBJQNZ8wkaFWM</a></td></tr><tr><td><strong>Setup Qyver</strong></td><td><a href="/files/uCSpUmOUGd7F8yeXlwX2">/files/uCSpUmOUGd7F8yeXlwX2</a></td></tr><tr><td><strong>Basic Building Blocks</strong></td><td><a href="/files/51ysuAfFg4w3YWSnvv6O">/files/51ysuAfFg4w3YWSnvv6O</a></td></tr></tbody></table>

### Run In Production

<table data-view="cards"><thead><tr><th></th><th data-hidden data-card-cover data-type="files"></th><th data-hidden></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td>Overview</td><td><a href="/files/thPfsOZx8vVwko0Z44rW">/files/thPfsOZx8vVwko0Z44rW</a></td><td></td><td></td></tr><tr><td>Setup a Server</td><td><a href="/files/XJMS8fFKGM9VYBkmfMN8">/files/XJMS8fFKGM9VYBkmfMN8</a></td><td></td><td></td></tr><tr><td>Configuring your app</td><td><a href="/files/CqS8uQGIEH3sbaRaI8vc">/files/CqS8uQGIEH3sbaRaI8vc</a></td><td></td><td></td></tr><tr><td>Interacting via API</td><td><a href="/files/5oigse6rOKFiTWXoG1Al">/files/5oigse6rOKFiTWXoG1Al</a></td><td></td><td></td></tr><tr><td>Supported Vector DBs</td><td><a href="/files/jKrowCTKvw3H3TpcCmjz">/files/jKrowCTKvw3H3TpcCmjz</a></td><td></td><td></td></tr><tr><td>Multiple Embeddings</td><td><a href="/files/h4ylr0GhNNevUgwJZU8X">/files/h4ylr0GhNNevUgwJZU8X</a></td><td></td><td></td></tr><tr><td>Dynamic Parameters</td><td><a href="/files/6wNigm6N7b3PbltGGCwQ">/files/6wNigm6N7b3PbltGGCwQ</a></td><td></td><td></td></tr><tr><td>Changelog</td><td><a href="/files/hU8q5vCQdzCjR2MGQaae">/files/hU8q5vCQdzCjR2MGQaae</a></td><td></td><td></td></tr><tr><td>Framework Overview</td><td><a href="/files/D3J4hkYGFxobhtlc65lz">/files/D3J4hkYGFxobhtlc65lz</a></td><td></td><td></td></tr></tbody></table>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://qyverlabs.gitbook.io/qyverlabs-docs/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.