xkonti
Allows to publish a ntfy notification using a fluent builder configuration.
Usage example
Create valimport { ntfy } from "https://esm.town/v/xkonti/ntfy";
await ntfy()
.toServer(Deno.env.get("ntfyServer"))
.asUser(Deno.env.get("ntfyUser"), Deno.env.get("ntfyPassword"))
.toTopic("testing")
.withMessage("Hello there!")
.withTitle("First test")
.withViewAction("My website", "https://xkonti.tech")
.withTags("package", "val-town")
.withPriority("high")
.publish();
⚠️ For the notification to be sent it needs to be published (publish
function).
Use helper
Executes specified functions that can modify the notification. Can be used to streamline authentication, apply common operations, etc.
Create valimport { ntfy } from "https://esm.town/v/xkonti/ntfy";
const toMyNtfyServer = (builder: ReturnType<typeof ntfy>) => {
builder
.toServer(Deno.env.get("ntfyServer"))
.asUser(Deno.env.get("ntfyUser"), Deno.env.get("ntfyPassword"));
};
await ntfy()
.use(toMyNtfyServer)
.toTopic('home-automation')
.withMessage('You left the front door open')
.publish();
You can pass it multiple functions.
Functions
toServer(url)
- optional
Specifies a server that the notification will be sent do. By default it's https://ntfy.sh
.
asUser(user, password)
- optional
Authenticates with the user and password. Please use ValTown's secrets for this.
usingToken(token)
- optional
Authenticates using the provided token. Please use ValTown's secrets for this.
toTopic(topic)
- required
Specifies which topic to publish the message to.
withMessage(message, markdown)
- required
Specifies the main message of the notification. You can also flag it as markdown by passing true
as a second argument. By default markdown
is false
.
Create valawait ntfy()
.toTopic('home-automation')
.withMessage('Your garage is **flooding**!', true)
...
withTitle(title)
- optional
Sets the title of the notification.
Create valawait ntfy()
.toTopic('home-automation')
.withTitle('Garage')
.withMessage('You left the front door open')
...
withPriority(priority)
- optional
Sets the priority of the notification. Possible from lowest to highest priority: min
, low
, default
, high
, max
Create valawait ntfy()
.toTopic('home-automation')
.withMessage('You left the front door open')
.withPriority('high')
...
Alternatively you can use dedicated functions: .withMinPriority()
, .withLowPriority()
, .withDefaultPriority()
, .withHighPriority()
, .withMaxPriority()
Create valawait ntfy()
.toTopic('home-automation')
.withMessage('You left the front door open')
.withHighPriority()
...
withTags(...tags)
- optional
Sets tags of the notification. This overrides any previously existing tags.
Create valawait ntfy()
.toTopic('home-automation')
.withMessage('You left the front door open')
.withTags('door', 'safety')
...
withDelay(delay)
- optional
Sets the delay for notification delivery. Read ntfy docs for more info.
Create valawait ntfy()
.toTopic('home-automation')
.withMessage('You left the front door open')
.withDelay('tomorrow, 10am')
...
withViewAction(label, url, clear?)
- optional
Adds an action button that opens a website or app when tapped.
label
- Label of the action button in the notificationurl
- URL to open when action is tappedclear
- Clear notification after action button is tapped (defaults tofalse
)
Create valawait ntfy()
.toTopic('home-automation')
.withMessage('You left the front door open')
.withViewAction('View Val', 'https://www.val.town/v/xkonti/ntfy')
...
withBroadcastAction(label, intent?, extras?, clear?)
- optional
Adds an action button that sends an Android broadcast intent when tapped.
label
- Label of the action button in the notificationintent
- Android intent name, default isio.heckel.ntfy.USER_ACTION
extras
- Android intent extras.clear
- Clear notification after action button is tapped (defaults tofalse
)
Create valawait ntfy()
.toTopic('home-automation')
.withMessage('You left the front door open')
.withBroadcastAction('Selfie', 'Take picture', { 'cmd': 'pic' })
...
withHtmlAction(label, url, method?, headers?, body?, clear?)
- optional
Adds an action button that sends a HTTP request when tapped.
label
- Label of the action button in the notificationurl
- URL to which the HTTP request will be sentmethod
- HTTP method to use for request, default isPOST
headers
- HTTP headers to pass in request.body
- HTTP body as a stringclear
- Clear notification after action button is tapped (defaults tofalse
)
Create valawait ntfy()
.toTopic('home-automation')
.withMessage('You left the front door open')
.withHtmlAction(
'Self-destruct',
'https://self.destruct/initiate',
'POST',
{ 'Authentication': 'Bearer 123' },
'{"countdown":60}'
)
...
withClickUrl(url)
- optional
Makes the notification open the specified URL when clicked (tapped).
withRawAttachment(filename, filedata)
- optional
Attached a file to the notification. Only one file can be attached.
Create valawait ntfy()
.toTopic('home-automation')
.withMessage('You left the front door open')
.withRawAttachment('todo.txt', 'Nothing!')
...
withUrlAttachment(url)
- optional
Attaches a file that is hosted elsewhere (URL).
withIcon(url)
- optional
Sets an icon for the notification.
viaEmail(email)
- optional
Sends the notification via email instead.
viaPhoneCall(number)
- optional
Sends the notification via a phone call. The number defaults to yes
, which makes it use the first phone number defined on your ntfy account.
withoutCache()
- optional
Disables the cache for the notification. Read the docs on caching for more info.
withoutFirebase()
- optional
Disables Firebase forwarding for the notification. Read the docs on Firebase for more info.
withUnifiedPush()
- optional
Indicates intent of using the Unified Push for the notification. Read the docs on Unified Push for more info.
A simple Rest API that allows for you GPT to save and recall snippets of data (memories). You can read my blog post explaining it in detail here: xkonti.tech
Demonstration
First conversation:
What GPT sent do the API:
{
"name": "Life Essence and Biological Processes",
"description": "Explore the role of life essence in enabling biological processes, with a focus on how dimensional interference, particularly from the Incorporeal dimension, facilitates the existence of these processes. This exploration should delve into the complex interplay between the Physical and Incorporeal dimensions, examining how life essence acts as a crucial element in the emergence and sustenance of life in the Physical dimension.",
"summary": "Expanding on the role of life essence in biological processes, emphasizing the interaction between the Physical and Incorporeal dimensions.",
"reason": "To deepen the understanding of how life essence, influenced by dimensional interference, is essential for biological processes in the novel's universe."
}
Separate conversation somewhere in the future:
Setup
There are several steps to set up the API:
- deploy and configure the API
- create the API key for your GPT
- add an action for the API in you GPT
- add prompt section to your GPT so that it can use it properly
Deploying the API on Val Town
Deploy your own memory API. You can fork the following Val to do it: https://www.val.town/v/xkonti/memoryApiExample
In the code configure the appropriate values:
apiName
the name of your API - used in the Privacy Policy (eg.Memory API
)contactEmail
- the email to provide for contact in the Privacy Policy (eg.some@email.com
)lastPolicyUpdate
- the date the Privacy Policy was last updated (eg.2023-11-28
)blobKeyPrefix
- the prefix for the blob storage keys used by your API - more info below (eg.gpt:memories:
)apiKeyPrefix
- the prefix for you API Keys secrets - more info below (eg.GPTMEMORYAPI_KEY_
)
Create API keys
The Memory API is designed to serve multiple GPTs at the same time. Each GPT should have it's own unique name and API key.
The name is used for identifying the specific GPT and appended to both:
blobKeyPrefix
- to maintain separate memory storage from other GPTsapiKeyPrefix
- to maintain separate API key for each GPT
- Please pick a unique alphanumeric name for your GPT. For example
personaltrainer
. - Generate some alphanumeric API key for your GPT. For example
Wrangle-Chapped-Monkhood4-Domain-Suspend
- Add a new secret to your Val.town secrets storage. The Key should be the picked name prefixed by
apiKeyPrefix
. Using the default it would beGPTMEMORYAPI_KEY_personaltrainer
. The value of the secret should be the API key itself.
The memories of the GPT will be stored in the blob storage under the key blobKeyPrefix + name
, for example: gpt:memories:personaltrainer
.
Adding GPT action
- Add a new action in your GPT.
- Get the OpenAPI spefication by calling the
/openapi
endpoint of your API - Change all
<APIURL>
instances within the specification to the url of your deployed API. For examplehttps://xkonti-memoryapiexample.web.val.run
- Set the authentication method to basic and provide a base64 encoded version of the
<name>:<apiKey>
. For example:personaltrainer:Wrangle-Chapped-Monkhood4-Domain-Suspend
->cGVyc29uYWx0cmFpbmVyOldyYW5nbGUtQ2hhcHBlZC1Nb25raG9vZDQtRG9tYWluLVN1c3BlbmQ=
- Add the link to the privacy policy, which is the
/privacy
endpoint of your API. For example:https://xkonti-memoryapiexample.web.val.run/privacy
Adding the prompt section
To make your GPT understand the usage of your new action you should include usage instruction in your prompt. Here's an example of such instructions section:
# Long-term memory
At some point the user might ask you to do something with "memory". Things like "remember", "save to memory", "forget", "update memory", etc. Please use corresponding actions to achieve those tasks. User might also ask you to perform some task with the context of your "memory" - in that case fetch all memories before proceeding with the task. The memories should be formed in a clear and purely informative language, void of unnecessary adjectives or decorative language forms. An exception to that rule might be a case when the language itself is the integral part of information (snippet of writing to remember for later, examples of some specific language forms, quotes, etc.).
Structure of a memory:
- name - a simple name of the memory to give it context at a glance
- description - a detailed description of the thing that should be remembered. There is no length limit.
- summary - a short summary of the memory. This should be formed in a way that will allow for ease of understanding which memories to retrieve in full detail just by reading the list of summaries. If there are some simple facts that have to be remembered and are the main point of the memory they should be included in the summary. The summary should also be written in a compressed way with all unnecessary words skipped if possible (more like a set of keywords or a Google Search input).
- reason - the reason for the remembering - this should give extra information about the situation in which the memory was requested to be saved.
The memory accessed through those actions is a long-term memory persistent between various conversations with the user. You can assume that there already are many memories available for retrieval.
In some situations you might want to save some information to your memory for future recall. Do it in situations where you expect that some important details of the conversation might be lost and should be preserved.
Analogously you can retrieve memories at any point if the task at hand suggests the need or there isn't much information about the subject in your knowledge base.
Allows for automatic generation of Hono API comatible with GPTs. Endpoints' inputs and outputs need to be specified via types from which the Open API spec is generated automatically and available via /gpt/schema
endpoint.
Usage example:
Create valimport { GptApi } from "https://esm.town/v/xkonti/gptApiFramework";
import { z } from "npm:zod";
/**
* COMMON TYPES
*/
const ResponseCommandSchema = z.object({
feedback: z.string().describe("Feedback regarding submitted action"),
command: z.string().describe("The command for the Mediator AI to follow strictly"),
data: z.string().optional().describe("Additional data related to the given command"),
}).describe("Contains feedback and further instructions to follow");
export type ResponseCommand = z.infer<typeof ResponseCommandSchema>;
/**
* INITIALIZE API
*/
const api = new GptApi({
url: "https://xkonti-planoverseerai.web.val.run",
title: "Overseer AI API",
description: "The API for interacting with the Overseer AI",
version: "1.0.0",
});
/**
* REQUIREMENTS GATHERING ENDPOINTS
*/
api.nothingToJson<ResponseCommand>({
verb: "POST",
path: "/newproblem",
operationId: "new-problem",
desc: "Endpoint for informing Overseer AI about a new problem presented by the User",
requestSchema: null,
requestDesc: null,
responseSchema: ResponseCommandSchema,
responseDesc: "Instruction on how to proceed with the new problem",
}, async (ctx) => {
return {
feedback: "User input downloaded. Problem analysis is required.",
command: await getPrompt("analyze-problem"),
data: "",
};
});
export default api.serve();