zep-python 2.0.0rc3

Zep: Fast, scalable building blocks for LLM apps. This is the Python client for the Zep service.

Zep: Fast, scalable building blocks for LLM apps

Chat history memory, embedding, vector search, data enrichment, and more.

Quick Start | Documentation | LangChain and LlamaIndex Support | Discord
www.getzep.com

What is Zep?

Zep is an open source platform for productionizing LLM apps. Zep summarizes, embeds, and enriches chat histories and documents asynchronously, ensuring these operations don't impact your user's chat experience. Data is persisted to database, allowing you to scale out when growth demands. As drop-in replacements for popular LangChain components, you can get to production in minutes without rewriting code.

Zep Python Client

This is the Python client package for the Zep service. For more information about Zep, see https://github.com/getzep/zep.

Zep QuickStart Guide: https://docs.getzep.com/deployment/quickstart

Zep Documentation: https://docs.getzep.com

Installation

pip install zep-python

-- OR --

poetry add zep-python

Zep Cloud Installation

In order to install Zep Python SDK with Zep Cloud support, you will need to install a release candidate version.

pip install --pre zep-python

-- OR --

poetry add zep-python@^2.0.0rc

You will also need to provide a Zep Project API key to your zep client for cloud support. You can find out about Zep Projects in our cloud docs

Using LangChain Zep Classes with zep-python

(Currently only available on release candidate versions)

In the pre-release version zep-python sdk comes with ZepChatMessageHistory and ZepVectorStore classes that are compatible with LangChain's Python expression language

In order to use these classes in your application, you need to make sure that you have langchain_core package installed, please refer to Langchain's docs installation section.

We support langchain_core@>=0.1.3<0.2.0

You can import these classes in the following way:

from zep_python.langchain import ZepChatMessageHistory, ZepVectorStore

Running Examples

You will need to set the following environment variables to run examples in the examples directory:

# Please use examples/.env.example as a template for .env file

# Required
ZEP_API_KEY=<zep-project-api-key># Your Zep Project API Key
ZEP_COLLECTION=<zep-collection-name># used in ingestion script and in vector store examples
OPENAI_API_KEY=<openai-api-key># Your OpenAI API Key

# Optional (If you want to use langsmith with LangServe Sample App)
LANGCHAIN_TRACING_V2=true
LANGCHAIN_API_KEY=<your-langchain-api-key>
LANGCHAIN_PROJECT=<your-langchain-project-name># If not specified, defaults to "default"