Giter VIP home page Giter VIP logo

multimodal-agent-starter's Introduction

Multi-modal Agent Starter

This repository hosts example AI Agents that you can deploy and use on Steamship in seconds.

Each sub-folder contains a fully-working example:

  • ai-character-with-stable-diffusion - A character whose personality you can customize. Can generate Stable Diffusion images and send them back to the user.
  • ai-character-with-voice - A character you can customize and deploy. Responds to the user with a generated voice instead of text.
  • question-answering-bot - A QA Bot that can learn PDFs, YouTube transcripts, and text and then answer questions about them.

Developer Instructions

  1. Pick a starter project among the folders here. Copy and rename that folder so that it becomes your own.
  2. Follow the README.md instructions inside your new project

Getting Help

The best places to learn about adapting these starter projects are:

Contributing

We welcome your own agent starter projects!

To contribute one:

  • Clone this repository
  • Create your example in its own folder
  • Deploy your example agent to Steamship
  • Send us a pull request, along with the example agent handle for us to try

multimodal-agent-starter's People

Contributors

dkolas avatar douglas-reid avatar eniascailliau avatar eob avatar gitonup avatar maxwfreu avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar

multimodal-agent-starter's Issues

Broken links for Question Answering Bot section in multimodal-agent-starter repo

In the multimodal-agent-starter/question-answering-bot/ section, the following sentences have broken links:

  1. This repository is designed to pair with this Agent Building Guidebook.
    Note: Should the link be https://docs[dot]steamship.com/... instead of https://docs[/]steamship.com ?

  2. You can be up and running in under a minute. A full setup walk-through is here.
    Note: This link prompts a 404, and seems to be missing a subdirectory if the path nomenclature is to match the 'Running your agent' and 'Deploying your agent' links.

Voice output empty when following captain picard example

Using the example file src/example_agents/captain_picard_with_voice.py as outlined in the docs, the output after submitting a prompt looks like this:
[ { "uploadType": null, "tags": [], "mimeType": "audio/mp3", "text": "", "uploadBytes": null, "id": "D6389C71-9E25-4EC9-AC2E-770C525E5B94", "contentURL": null, "index": 0, "url": null, "fileId": "33A85E66-504D-4239-B1B9-1DFD2BDDA766", "publicData": true } ]

contentURL and URL are null, there is no audio data delivered, only the IDs.
Also doesn't work with the API key setup or other voice IDs:

speech.generator_plugin_config = { "voice_id": "your-voice" "elevenlabs_api_key": "your-api-key" }

CURL or python post request made on agent API endpoints does not works

Hi i have deployed and agent and can successfully make calls to agent from python client, but when testing for CURL or with python post request , it returns the below error everytime.

(Instance name is being changed for privacy)

CURL snipped from the dashboard:
curl -X POST \ https://random.steamship.run/randomname/random-c9h/prompt \ -H 'Content-Type: application/json' \ -H 'Authorization: HIDDEN' \ -d '{"prompt":"Hello"}'

Error:
{ "status": { "state": "failed", "statusCode": "DataMissing", "statusMessage": "Unable to find instance. URL = \/random-c9h\/random-c9h\/prompt Owner = 756B423B-06C4-48D5-9F88-679F8615B84 WorkspaceHandle = random-c9h, handle = random-c9h" } }

why so ๐Ÿค”?

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.