Thread by @EdenEmarco177

1/8 🚀 Let's go step by step on "Chat with your Repo" assistant powered by @LangChainAI🦜🔗 and @pinecone🌲all running smoothly on @googlecloud☁️ Run- this was demoed at yesterday's HUGE @googlecloud @pinecone event in Tel Aviv 🇮🇱

@hwchase17 counting on you for next time😎

2/8 Step 1? Vectorize your repository files. With using @googlecloud VertexAI embeddings and a couple of lines of @LangChainAI you simply ingest these vectors into @pinecone vectorstore.

3/8 Now, we use @googlecloud VertexAI embeddings along with context retrieved from @pinecone to augment the user's original prompt to @googlecloud PaLM 2 LLM. This enables is also called in context learning. With @LangChainAI again is just a couple of lines of code

4/8 📦🔄 Then, now its containerization time. The application is neatly packed using a Dockerfile, and a Cloud Build CI/CD pipeline is constructed to automate and streamline deployments to @googlecloud.

5/8 💡✅ The final step? Just sit back and let @googlecloud Cloud Run handle all the "ilities" - scalability, availability, durability. The brilliance of serverless - write code and let Google worry about the infrastructure. #GCP #CloudRun 🌩️

6/8 🎙️💬 Special thanks to @pinecone🌲 @MutayRoei @miararoy for an insightful talk on Retrieval Augmented Generation and handling LLM's illucinations. This deep dive added immense value to our understanding of AI.

7/8

7/8 Github repo can be found here
github.com/g-emarco/githu…

8/ Finally want to give a huge shoutout to @Therealmayul with helping and orchestrating such an amazing event