Git Product home page Git Product logo

networker1.5's Introduction

Networker

Get Past Small Talk - Your AI-Powered Networking Assistant

Basic Summary

OpenAI has impressed the world with ChatGPT. Networker is an AI-powered tool that aims to help you overcome the barrier of small talk when networking. By helping you remember important details about people, it aims to facilitate more meaningful conversations and build deeper connections. It is the combination of OpenAI's text prompting algorithm da-vinci, combined with both Speechly and Google APIs.

Project Outcome

Once the Speech to text funcitonality is flushed out, we'll want to have the following features:

  • Networking Assistant: Networker will take any data gathered from a conversation you've had and log it, including important details as well as important facts about the person/people you've interacted with, stored in a JSON format in a MongoDB database.
  • Inquiry Assistant: Networker will gather information on you by asking rich, meaningful questions to get to know you, your connections, and help you to inquire more about life, acting as both an assistant and personal coach.

Latest deployment is held on Railway and can be found here

Py Scripts:

  • App
    • Central Application, made using TKinter for a GUI
  • Prompt
    • OpenAI's API script, pulling the text data and submitting a response.
  • STT (Speech to text)
    • Using Google Cloud's speech to text API, voice data is recognized as text for input in app.py.
  • TTS (Text to Speech)
    • Using Google Cloud's text to speech API, we can gather text and output speech here.
  • conversation.js
    • Holds prior conversation data.

Autorization Scripts (not added to GH):

  • creds.py - holds API Keys in a Python format
  • google.json - holds google authorization payload

Networker Demo

How to Use the App

  1. Push the microphone, spacebar to speak or enter into the prompt manually.
  2. For your prompt, the first word you ask is important. Use the following as a guide:
    • Update Strings = "update",'edit', 'modify': This is a general "Upsert" function that will add fields to an existing user, or build out a new one.
      Example Prompt: "Update Drew Piispanen - he likes vanilla ice cream."
      Example Response: "Drew Piispanen has been updated"
    • General Strings = 'who': This asks Networker to give general information about a person.
      Example Prompt: "Who's Drew Piispanen?"
      Example Response: "Drew Piispanen lives in Hershey, PA. He is studying data science, and is coding the 'Networker Application'. His favorite ice cream is cookie dough."
    • Reminder Strings = 'remind': This will ask Networker to remind them about a specific field of this person.
      Example Prompt: "Remind me, what's Drew Piispanen's favorite ice cream flavor?"
      Example Response: "Drew's favorite ice cream flavor is cookie dough."
  3. Networker will respond with in the response textfield, to which the following prompt can audit the last response.

Setbacks

  • Logic loops
  • High payload to request memory and/or formatting
  • Historical data not easily found.

Needs:

  • Better name identification
  • CRM backend application
  • Connection Function:



For more information, see our Medium Post.

Questions? Reach out to me:
[email protected]
Drew Piispanen

networker1.5's People

Contributors

apiispanen avatar coffee-cup avatar railway-bot avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.