Coder Social home page Coder Social logo

videoinsightbot's Introduction

VideoInsightBot

VideoInsightBot is a Streamlit project with an AWS-hosted backend that leverages the power of AI to transcribe videos, provide quick meeting summaries, and answer questions based on the transcribed content. The project allows to use AWS services such as AWS transcribe for transcription and models such as the Claude Instant hosted on AWS Bedrock for analysis.

Features

  • Video Transcription: Upload any video, and the bot will transcribe its content using the AWS Transcribe Service.

  • Meeting Summary: Receive a quick summary of the meeting and identify action items extracted from the transcribed content.

  • Q&A with LLM: Ask questions related to the video, and the bot will utilize the transcribed context to provide relevant answers.

  • Backup to S3: All files, including transcriptions and summaries, are uploaded to AWS S3 for backup and storage purposes.

Technologies Used

The project incorporates the following services and packages:

  • AWS S3 Bucket: Used for storing files and backups.

  • Bedrock: Hosts the Claude V2 model for video transcription.

  • Langchain: Provides natural language processing capabilities.

  • Streamlit: Powers the user interface for seamless interaction.

  • Boto3: Interacts with AWS services, including S3.

  • Pydub and Moviepy: Used for audio processing and video manipulation.

Screenshots

    1. Upload a video

Alt text

    1. Analyse a video

Alt text

    1. Check History

Alt text

    1. Summarize a video

Alt text

Live Demo

Link

Getting Started

To run this repository:

  1. Clone the repository to your local machine.
  2. Login using AWS CLI.
  3. Install dependencies using the pip install -r requirements.txt command.
  4. Run frontend using streamlit run frontend.py.

Deployment

  • Initialize Terraform: terraform init
  • Validate the Terraform configuration: terraform validate
  • Apply the Terraform configuration: terraform apply -auto-approve
  • To delete the resources: terraform destroy

Now, you're ready to explore the capabilities of VideoInsightBot and enhance your video interaction experience.

Feel free to contribute, report issues, or suggest improvements. Happy video botting!

videoinsightbot's People

Contributors

priyansh007 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.