LlamaIndex & DataStax Hackathon Developer Resources


LLAMAINDEX RESOURCEs (REQUIRED)

Getting Started Pack:

• Create-llama: ( https://www.npmjs.com/package/create-llama ) will generate a basic frontend & backend hooked up to llamaindex
  
  
• RAGs: (https://github.com/run-llama/rags ) is a demo of building llamaindex apps using streamlit
  
  
• Demo: www.secinsights.ai is a demo of a full-stack llamaindex app that handles complex queries over multiple documents
  
  
• docs.llamaindex.ai is our Python documentation, ts.llamaindex.ai is our typescript docs
  
  
• llamahub.ai is our library of connectors to data sources, agent tools, and pre-built code snippets called llamapacks

 
DATASTAX

• Sign up for Astra DB for free - https://dtsx.io/3HFj81p
• Astra DB Docs - https://docs.datastax.com/en/astra/astra-db-vector/get-started/quickstart.html
• AstraDB + LlamaIndex (Python) - https://docs.datastax.com/en/astra/astra-db-vector/integrations/llamaindex.html
• AstraDB + LlamaIndex (TypeScript) - https://docs.datastax.com/en/astra/astra-db-vector/integrations/llama-typescript.html
• Get started building a basic chat using Python, LlamaIndex and Astra DB - https://github.com/datastax/ai-chatbot-starter
• Demo - https://tswift.ai is a demo of a full-stack JS app with full source code and a technical write-up here: https://www.datastax.com/blog/using-astradb-vector-to-build-taylor-swift-chatbot

sponsor resources:

NVIDIA

• Get started with LLM development on local Windows PC
  
• RAG Developer reference project running locally on Windows PC with LlamaIndex and Llama-13B
  
• LlamaIndex – NVIDIA TensorRT-LLM Integration
  
• RAG Technical Brief
  
• Explore AI Foundation Models

Bentoml

• $100 BentoCloud credits for each team to use for the hackathon.
• Unified AI Application Framework: With BentoML, you can easily build AI products with any pre-trained models, ship to production in minutes, and scale with confidence.
• BentoML is the platform for software engineers to build AI products.
  
  Find them on our Slack channel.

vectara

LlamaIndex and using Vectara as a ManagedIndex.

How to use Vectara with LlamaIndex:

• Sign-up to get your free Vectara account here
• We've created a Jupyter notebook with some canonical examples for how to use Vectara with LlamaIndex, including some advanced usage such as Auto-retrieval and QueryFusionRetriever
• Vectara API docs
• Note: Vectara is offering a case reward to the team that most effectively incorporates their technology into their project.
  
  Find them on our Slack channel.
  
  
  

RENDER

• Render is offering free credits for each team at the the RAG-a-thon. 
• Render is the modern cloud for application developers and teams. Render lets you deploy easily, then scale with confidence. 
• Quickly spin up web services, static sites, cron jobs, and more. Easily set up enterprise-grade data stores, private networks, load-based autoscaling, DDoS protection, and more. Collaborate with your team with built-in project management and testing features.
  
  Find them on our Slack channel.

diffbot

• Diffbot is a VC-backed AI startup that crawls the entire public web and uses AI to produce the world's largest knowledge graph. 
•   Diffbot is offering $100 in free credit per team for their new cloud LLM product (think GPT-4 quality output RAG-ged over the world's largest knowledge graph of the web)

Find them on our Slack channel.

Participants are welcome to use any open-source tool available.

Do you want to find other open-sourced models?

• Go to https://huggingface.co/ and explore models and datasets available at the top-right and hack-away. Also, their chat-ui is available at https://github.com/huggingface/chat-ui , Check out for inspiration.
  

Other:

Open AI 

• Sign up using your email and go to  https://platform.openai.com/account/api-keys
• Navigate to User -> API Keys, and Create a Secret key. Note: You can create multiple secret keys if necessary.