carl-feat/multimodal-bots#42
Open
CarlKho-Minerva wants to merge 24 commits intoHyperbolicLabs:masterfrom
Open
Conversation
Add a new example demonstrating a conversational AI bot that provides real-time news and information using Google's Gemini model and search capabilities. Key features: - Real-time voice interaction using Daily.co - Latest news retrieval using Google Search API - Natural conversation with Gemini AI model - Voice synthesis for bot responses - Voice activity detection for smooth interaction Project structure: - Configuration settings and environment variables - Daily.co service integration - Main application pipeline setup - Logging utilities - Comprehensive README with setup instructions Dependencies: - Core: aiohttp, fastapi, pydantic, websockets - AI/ML: google-generativeai, pipecat-ai[google] - Audio: pyloudnorm, silero-vad, soxr - Services: daily-python
feat: Add screen-share capability. refact: simplify all utility files -> runner.py extra: welcomes user to hyperbolic labs on entry.
…bility and pricing format
feat(gpu-marketplace-bot): enhance marketplace data fetching with advanced filtering and sorting options
…ce features and usage instructions
… improved error handling and response structure
CarlKho-Minerva
changed the title
connorch
force-pushed
the
master
branch
2 times, most recently
from
4781f36 to
bbb41c0
Compare
- Introduced REGION_MAP to convert region codes to friendly names. - Updated price formatting to convert from cents to dollars in the fetch_marketplace_data function. - Added new marketplace_output.txt file to store GPU marketplace data. - Created test.ipynb to demonstrate fetching and saving GPU data.
…user use case inquiries and personalized GPU recommendations.
Refactor GPU marketplace bot configuration and main logic to enhance user interaction and context awareness
…s and .dockerignore
Author
|
###TLDR: Marketplace Interactions + ability to see Video (screenshare/camera) all in one .py
More details below: Core Functionality and Bot Logic:
Environment and Configuration:
Deployment and Dependencies:
Documentation:
|
…d error handling; update HTML response for improved user experience.
…ealth check server and improve HTML response for bot status.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request introduces three different bots (
multimodal-gpu_marketplace-bot,multimodal-live_search-bot, andmultimodal-video-bot) to enhance AgentKit's functionality and improve user interaction.ScreenShare + Verbal Queries — Bounty Completed - Watch Video
Main Application:
multimodal-gpu_marketplace-bot/main.py: Implemented the main logic for fetching marketplace data, setting up the voice assistant, and handling user interactions.multimodal-live_search-bot/main.py: Implemented the main logic for providing real-time news updates using Google Gemini and handling user interactions.multimodal-video-bot: Ability to view content on shared screen and video feed active!