https://github.com/ojasskapre/langchain-apps

The project features two applications: a *Research Assistant* that generates research reports using LangChain, OpenAI's GPT-3.5, DuckDuckGo Search API; and a *Chat With Video* app that allows users to upload videos, transcribe audio with OpenAI's Whisper, and store the embeddings in Pinecone vector DB.
https://github.com/ojasskapre/langchain-apps

langchain openai pinecone python streamlit

Last synced: about 2 months ago
JSON representation

The project features two applications: a *Research Assistant* that generates research reports using LangChain, OpenAI's GPT-3.5, DuckDuckGo Search API; and a *Chat With Video* app that allows users to upload videos, transcribe audio with OpenAI's Whisper, and store the embeddings in Pinecone vector DB.

• Host: GitHub
• URL: https://github.com/ojasskapre/langchain-apps
• Owner: ojasskapre
• Created: 2024-05-17T02:28:57.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2024-05-29T05:38:20.000Z (8 months ago)
• Last Synced: 2024-10-19T16:10:01.718Z (3 months ago)
• Topics: langchain, openai, pinecone, python, streamlit
• Language: Python
• Homepage:
• Size: 3.12 MB
• Stars: 6
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: Readme.md

Awesome Lists containing this project

README

        
# Langchain Applications

## Research Assistant

This project aims to create a research assistant using LangChain and OpenAI's GPT-3.5 model. The assistant can generate comprehensive research reports based on user-provided topics. The system utilizes web scraping, text summarization, and search query generation to gather and analyze information from various online sources.

- [Demo](https://youtu.be/DjuXACWYkkU?si=_v1Yz0R9ygpTopP3)

- [Readme](./research-assistant/Readme.md)

Reference (https://youtu.be/DjuXACWYkkU?si=_v1Yz0R9ygpTopP3)

## Chat With Video

This project is a Streamlit based application allows users to upload videos, transcribe their audio using OpenAI's Whisper, and create embeddings with LangChain-OpenAI and store the embeddings in Pinecone Vector DB for further querying. Users can then chat with the video content by selecting transcribed videos and asking questions.

- [Demo](https://youtu.be/jAmMG8sjI5c)

- [Readme](./chat-with-video/Readme.md)