---
title: "LlamaIndex"
sidebarTitle: "LlamaIndex"

---

import {
  PyFrameworksLlamaindexAddReranker,
  PyFrameworksLlamaindexFiltering,
  PyFrameworksLlamaindexHybridSearch,
  PyFrameworksLlamaindexQuickStart,
} from '/snippets/integrations.mdx';

## Quickstart {#quickstart}

LlamaIndex is a well-known framework for building LLM-powered agents over your data with LLMs and workflows.
You can build your LlamaIndex pipeline and persist your metadata and embeddings in LanceDB via the `LanceDBVectorStore` class.

First, install the LlamaIndex-LanceDB integration.

<CodeBlock filename="bash" language="bash" icon="terminal">
pip install llama-index-vector-stores-LanceDB
</CodeBlock>

Run the below script as an example.

<CodeBlock filename="Python" language="Python" icon="python">
  {PyFrameworksLlamaindexQuickStart}
</CodeBlock>

The vector store connector will open an existing LanceDB directory or create the directory if it does not exist.

### Filtering {#filtering}
For metadata filtering, you can use a Lance SQL-like string filter as demonstrated in the example above. Additionally, you can also filter using the `MetadataFilters` class from LlamaIndex:
<CodeBlock filename="Python" language="Python" icon="python">
  {PyFrameworksLlamaindexFiltering}
</CodeBlock>

### Hybrid Search {#hybrid-search}
For complete documentation, refer [here](https://docs.lancedb.com/search/hybrid-search). This example uses the `colbert` reranker. Make sure to install necessary dependencies for the reranker you choose.
<CodeBlock filename="Python" language="Python" icon="python">
  {PyFrameworksLlamaindexHybridSearch}
</CodeBlock>

In the snippet above, you can change/specify `query_type` when creating the engine/retriever
to use different search strategies, such as vector search or FTS.

## API reference {#api-reference}

<Card
  title="LlamaIndex Vector Stores API reference"
  href="https://developers.llamaindex.ai/python/framework-api-reference/storage/vector_store/lancedb/"
>
See the official LlamaIndex Vector Stores API reference for more details.
</Card>