!!! Warning "Secure Your Zep Deployment"
If you are deploying Zep to a production environemnt or where Zep APIs are exposed to the public internet,
please ensure that you secure your Zep server.
Review the [Security Guidelines](security.md) and [configure authentication](auth.md).
Failing to do so will leave your server open to the public.
Enter a Blueprint Name (we suggest zep
) and provide your OpenAI API key, which will be stored as a secret.
Click Apply
.
!!! note "OpenAI or Anthropic API Key Required"
An OpenAI API key is required to run Zep. Please ensure that you enter it in the step above. To configure Zep to use Anthropic or other LLM services, please see [Configuring LLM Services](llm_config.md).
This takes a few minutes.
Follow the server authentication instructions here. Do not skip this step. Failing to do so will leave your server open to the public.
Retrieve your Zep server URL from the Render web console.
https://zepXXXXX.onrender.com
=== "Python"
```python
from zep_python import ZepClient
zep = ZepClient("https://zepXXXXX.onrender.com", api_key) # Replace with Zep API URL
```
=== "TypeScript/JS"
```javascript
import { ZepClient } from "@getzep/zep-js";
const zep = new ZepClient.init("https://zepXXXXX.onrender.com", apiKey); // Replace with Zep API URL
```
Next steps: Using Zep's Python and TypeScript/JS SDKs
!!! question "Web UI disabled for Render deploys"
For security reasons, Zep deployments to Render default to disabling the web UI. The Zep web UI is not secured by
JWT authentication and should only [be enabled](config.md) if you deploy Zep as a [private service](https://render.com/docs/private-services).
Three services are deployed:
zep
- the Zep servernlp
- a back-end private service responsible for several NLP taskszep-postgres
- a Postgres database
The blueprint defaults to the standard tier. You can change these settings in the Render web console.
!!! note "This blueprint is not optimized for production"
This blueprint by default deploys in the smallest possible configuration.
Depending on the embedding model you use, you may need to increase the memory and CPU allocated to the `nlp` service.
Please see [the production deployment guide](production.md) for more information.
- Setting up authentication
- Developing with Zep SDKs
- Learn about Extractors
- Setting Zep Configuration options
- Learn about deploying to production