# ZepRetriever

> **Class** in `langchain_community`

📖 [View in docs](https://reference.langchain.com/python/langchain-community/retrievers/zep/ZepRetriever)

`Zep` MemoryStore Retriever.

Search your user's long-term chat history with Zep.

Zep offers both simple semantic search and Maximal Marginal Relevance (MMR)
reranking of search results.

Note: You will need to provide the user's `session_id` to use this retriever.

## Signature

```python
ZepRetriever()
```

## Description

Zep - Fast, scalable building blocks for LLM Apps
=========
Zep is an open source platform for productionizing LLM apps. Go from a prototype
built in LangChain or LlamaIndex, or a custom app, to production in minutes without
rewriting code.

For server installation instructions, see:
https://docs.getzep.com/deployment/quickstart/

## Parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `url` | `unknown` | Yes | URL of your Zep server (required) |
| `api_key` | `unknown` | Yes | Your Zep API key (optional) |
| `session_id` | `unknown` | Yes | Identifies your user or a user's session (required) |
| `top_k` | `unknown` | Yes | Number of documents to return (default: 3, optional) |
| `search_type` | `unknown` | Yes | Type of search to perform (similarity / mmr) (default: similarity,                                                         optional) |
| `mmr_lambda` | `unknown` | Yes | Lambda value for MMR search. Defaults to 0.5 (optional) |

## Extends

- `BaseRetriever`

## Properties

- `zep_client`
- `url`
- `api_key`
- `session_id`
- `top_k`
- `search_scope`
- `search_type`
- `mmr_lambda`

## Methods

- [`create_client()`](https://reference.langchain.com/python/langchain-community/retrievers/zep/ZepRetriever/create_client)

---

[View source on GitHub](https://github.com/langchain-ai/langchain-community/blob/a6a6079511ac8a5c1293337f88096b8641562e77/libs/community/langchain_community/retrievers/zep.py#L36)