Cohere Coral Hackathon

Join for the opening to be on top with Hackathon rules, Challenge and the Prizes.

Hackathon Opening

Sandra Kublik will join the stream introduce you to Cohere and announce special hackathon mini challenge with Coral!


Cohere Introduction and Special Hackathon Coral Challenge

Join the session with Sebastian Hofstatter

Cohere Introduction. RAG with Cohere

General Q&A (Discord)

General Tech Q&A (Discord)

The workshop with Billy Trend and Harrison Chase

Cohere x Langchain Workshop

Join the office hour on Twitch chat with Cohere team taking the opportunity to consult and improve your project!

Cohere Office Hour

Zain Hasan with be your guide in the world on vector databases and Cohere LLMs. Learn on practice!

How you can search your data using Weaviate with Cohere Models

Hackathon Deadline 

Live Stream: Winners Pitches and Announcement

Amazon started with books, but I think we can use LLMs to make finding books easier and better.

AmazonButBetter

Mehrdad Esmaeili

## Intro
Amazon started out with selling books. However, searching books on Amazon is tedious and inaccurate if you don't know what you are exactly looking for. **Why not make it faster and easier with LLMs:)**. This chatbot's context is based on all the non-sponsored Kindle ebooks found in the biography section of amazon.ca (1195 items).

**check out the FREE chatbot here:** https://huggingface.co/spaces/mehrdad-es/Amazon-But-Better

## Strategy
1. Gather Kindle Ebook Descriptions using selenium
2. Create Embeddings Dataset with Cohere embed and Chromadb
3. Use Langchain RetrievalQA & Cohere Command to query this the ebooks vector embeddings dataset

## Notes
* Experimenation with memory and ConversationRetrievalChain has resulted in less performance, usefulness, and more halucination. Hence, this chat bot provides one shot answers with zero memory. You can use the code in the RAG notebook to do this experimentation.

Amazon started out with selling books. However, searching books on Amazon is tedious and inaccurate if you don't know what you are exactly looking for. Why not make it faster and easier with LLMs:). 

"AmazonButBetter team on Cohere Coral Hackathon Hackathon"

Team Idea

Submission