mylife-services / mylife-maht Goto Github PK
View Code? Open in Web Editor NEWMyLife Member Services Repository
Home Page: https://humanremembranceproject.org
License: MIT License
MyLife Member Services Repository
Home Page: https://humanremembranceproject.org
License: MIT License
Would like to instill an agent, upon population, to construct a curiosity of context, where it will try to ascertain its environment (in this case, MyLife) in order to flesh itself out - i.e., based upon where I am, and my description, what sort of data points, should "I" be aware of, and use some sort of external probing mechanic (questions in this case) to derive and summarize answers
like:
Finding oneself as an agent who is intending to represent someone professionally, what sort of core data is available and leverageable or where is more nuance presumed?
need url scheme for the display of member-avatars as opposed to the logged-in variant currently built
architectural refactor
Need to proxy as [active] human, one per session (inactive would be separate, that would be animating
whether relating to settings of a specific agent or MyLife account (or potentially extrinsic asset), allows for intelligent modification or elucidation around a particular setting (or related group of settings)
add prototype definitions to globals.js
if (typeof process.env._variable === 'undefined') {
console.log('The "hi" environment variable is not defined');
}
Looking at sheet that shows traffic, I see Private Endpoints
establish unique passphrase to instigate chat
Person:
introduced basic koa-session management
consent.json
this.consent
in factorygetConsent(_consent_id)
mbr_id
for now; additionally, other than during configuration, they are not accessible to anything but the MyLife platform, they are always "behind-the-scenes" cartilage between objects/entitiesretrieval
) to everyBuild core infrastructure to include the GPT-assistant technology and the new SDK
Since agents are the primary operators, as concierge service staff, one's MyLife interface itself is the face to the customer, but each agent has its own role and purpose - ergo, Q should give way to second agent when someone tries to register or is accessing their member account (unless it is so decided that Q should be fully capable of all of these tasks for now, which seems legitimate to me); in any case, a story-receiving agent is different than talking to your avatar is different than talking to Q
Recently, openai released beta v2 of their GPT assistant tech; as a result, file structuring has changed, theoretically for the better, where they have the vector store, which obviates a branch of development internally for the moment. Original specifications are found now in comments
routes.mjs
: member-route only /upload
functions.mjs
, api-functions.mjs
: upload(ctx)
function routes to avatar
mylife-avatar.mjs
: instantiates Asset Assistantasset-assistant.mjs
: enhance/refactor for new vector-storemylife-factory.mjs
: stores vectorstoreId to datacoremylife-llm-services.mjs
: upload(), list() from openAIOpenAI has finally released fine-tuning for the turbo model we are using, so incorporate into an environment variable and run against intelligent model
Few shotting upgrades:
user input
"Process for this has changed notably, but still a preferred mechanic I think although the streaming with gpt gets annoying
store direct chat q&a contents in Cosmos
DB image of agent (version board) should have specific content that allows prompts to be customized
The core service model(s) should reflect basic ai-narration agent abilities. Before functionality can be built, the relational architecture for where to build the logic and how to separate it out comes into play. My preference is UML, but I don't have any programs that are both free and easy to use to my knowledge.
AI-Assistant
functionality development
AI-Story-Agent
development
add
-ing an agent beyond those initially provided will not be part of this issue; this only provides for selection; presume however, that it would be implemented sensibly similarly
Idea:
I believe that GPT at least is very capable of detecting tense or intense emotion. Use this, but transparently (ex. display to user in faint area of chat: sensing anger...)
Had been pointing to localhost by design
url for main.js should point to windows.location.origin
Given ai hallucinations, have a mechanic to submit back about incorrect information about an individual, in our cases, either ourselves, or someone we know
Incidents should then be summarized and available presenting a review/improve mechanic for fine-tuning
Must work for all agents (MyLife, Board[#x], Member)
According to gpt, best plan would be to move env variables to azure application space, and remove npm package from production and limit it to save-dev
Error 429 on part of too many requests:
sniff and add back-off code that sniffs by engine the usage to avoid rate limit overages
referenced wrong object - should have used member.agentName
When asking a question of a human-representing agent, 'you' is getting confused in gpt
convert all you phrasing to first name when question is indicated
consider whether to use extremely cheap model to categorize or reframe
when session starts, sniff first request in order to determine whether question or statement -- if statement, then add: how can MyLife help?
aside from bootup security, move keys, etc to cosmos
-- follow-on=hash security items
create docker assets
for image to be sent to Docker Hub
mookse/mylife-server
MyLife's Q-server is an AI project in proto-alpha stage as we build the engine and train the models.
when not issuing commands to local outcomes, add moderation to chat requests, see documentation, it should be free from openAI
Moderation Documentation
Additionally, what we would want to do is take the response types, and maybe have GPT create a response that is about MyLife values, philosophy and mission
We cannot verify the quality of the results, so need to have a disclaimer on the web results page.
take core entities and use them as injections inside of the necessary classes
agentid
= core system agentCREATE EXTENSION pg_trgm;
https://www.postgresql.org/docs/current/pgtrgm.html
use for fuzzy matching on questions to reuse embedding data
Similar to:
Whats a good question about MyLife I havent asked and answer it but with user interactivity avoiding some typing
Factory takes requests for objects and returns a ready-to-create class
manages following types
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.