> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lytix.co/llms.txt
> Use this file to discover all available pages before exploring further.
# Prompts
> Prompt management and optimization at lytix
Lytix helps manage prompts directly in the CLI using our `lytix` cli commands.
**Note** We currently only support Typescript/Javascript.
**🚨 Prerequisite** Login & setup your `lytix` CLI [here](/CLI/cli-login).
# Sync your prompts (e.g. `git pull` your prompts)
Now you can sync your prompts to your local machine. This is the equivalent of `git pull` for your prompts.
If there are **changes that are uncommited or would cause a conflict**, you will be prompted to resolve them. You can pass the `--force` flag to skip this check and overwrite your local changes.
```bash
lytix prompt sync
```
# Create a new prompt
Now let's create our first prompt. All you need to get started is a prompt name.
```bash
lytix prompt create --promptName "my new prompt"
```
# Edit & Use The Prompt
Now let's iterate on our prompt and start using it.
### Add Variables
Lytix supports adding templated variables to your prompts. This allows you to dynamically pass in variables when you use the prompt **and get type safety** as lytix will generate a `.ts` types file for you based on the inputs
Inside `prompt.json`, the `variables` field is where you can add your variables. It supports:
* `type`: `STRING` | `NUMBER` | `BOOLEAN` - The type of the variable
* `name`: The name of the variable
For example, a `prompt.json` file with a `toEcho` variable might look like this:
```json
{
...
"variables": [
{
"type": "STRING",
"name": "toEcho"
}
]
}
```
### Update Prompts
After we've created the needed variables, we can update our system or user prompt by updating the `inputs.mdx` file:
```mdx
Please echo the following variable: ${{ toEcho }}
You are a helpful assistant.
```
### Commit Changes
Now you're ready to commit changes (e.g. `git commit && git push`).
**Note** This will **immediately** update the prompt and any incomming requests using the `promptId`
```bash
lytix prompt commit
```
### Pass `promptId` & Use Prompt
⚠️ **Important** You need to use the `v2` baseURL: `https://api.lytix.co/proxy/v2/openai`. Please follow instructions [here](/Quickstart/openai-integration) to setup the lytix OpenAI integration.
Now you are to use the `lytixPromptId` to start using your prompt. You can now pass an empty `messages` array and add the `lytixPromptId` & `lytixPromptVariables` to your request:
```ts
const client = new OpenAI({
apiKey: LYTIX_API_KEY,
baseURL: "https://api.lytix.co/proxy/v2/openai";,
defaultHeaders: {
anthropicApiKey: ANTHROPIC_API_KEY,
openaiKey: OPENAI_API_KEY,
},
});
/**
* This is dyntamically generated type based on the prompt variables defined in `prompt.json`.
* Run `lytix prompt sync` to update them
*/
const inputVariables: my_new_promptInput = {
toEcho: "This is coming from the lytix variable!",
};
const response = await client.chat.completions.create({
model: "gpt-4o-mini",
messages: [],
// @ts-expect-error lytix variables
lytixPromptId: "464df7b9-81bf-435e-96ba-b95eab905452", // This promptId comes from the `prompt.json` file
lytixPromptVariables: inputVariables,
});
```
# Delete a prompt
Once you are ready to delete a prompt, you can do so with the following command:
```bash
lytix prompt delete --promptName "my new prompt"
```