Configuring Zep
Configure Zep server settings, authentication, and LLM options
You are viewing the Zep Open Source v0.x documentation. This version is no longer supported, and documentation is provided as a reference only.
The current documentation for Zep Community Edition is available here.
Zep is configured via a yaml configuration file and/or environment variables.
The zep
server accepts a CLI argument --config
to specify the location of the config file.
If no config file is specified, the server will look for a config.yaml
file in the current working directory.
Warning: Your OpenAI/Anthropic API key and Auth Secret should not be set in the config file, rather the environment variables below should be set. These can also be configured in a
.env
file in the current working directory.
Zep Server
The Zep server can be configured via environment variables, a .env
file, or the config.yaml
file. The following table lists the available configuration options.
Server Config
Authentication Config
Please see the Authentication documentation for more information on configuring authentication.
LLMs
See the LLM Configuration for more information on configuring LLMs.
Note: Anthropic does not support embeddings. If configuring Zep to use the Anthropic LLM service, you must configure Zep to use the local embeddings service.
Enrichment and Extraction
Data Management
See the Data Management documentation for more information on configuring data management.
Valid LLM Models
The following table lists the valid LLM models for the llm.model
configuration option.
Zep NLP Server
The Zep NLP Server may be configured via a .env
file or environment variables.
The following table lists the available configuration options.
Note that the NLP server’s container is not shipped with CUDA nor configured to use GPU acceleration.