How to build chat with your data using Pinecone, LangChain and OpenAI

/ zackproser
I show step by step how to build a Chatbot using Pinecone, LangChain and OpenAI in this easy to follow tutorial for beginners.
I ingest my entire blog full of MDX posts, chunk and convert them to embeddings using LangChain and OpenAI. Then I upsert them into my Pinecone vector database to build a knowledge base that our chatbot can use to answer questions.
I build everything using a Jupyter Notebook to make it extremely easy to follow along.

[@luccafabro2]

example tutorial, very clear and useful

[@zackproser]

Thanks so much 🙏 Glad you found it useful. Stay tuned for more.

[@haimroizman6440]

Really great tutorial, thanks a lot!

[@zackproser]

Thanks so much for the feedback and support 🙏 Glad it was useful. LMK what else you'd like to see in the future.

[@haimroizman6440]

@@zackproser I still haven't thought on a specific issue, but I will be glad to update you when I'll have...

[@user5398-v7x]

Can i get the collab Notebook for this tutorial ?

[@user5398-v7x]

no worries its done thanks for the short and to the point video this was exactly what i was searching for ,seems like the Langchain and Openai packages gets updated too often a package function 5-6 months old too gets deprecated .

[@zackproser]

Certainly! Here you are: github.com/zackproser/PineconeChatbot/blob/main/Pinecone_Chatbot.ipynb

[@zackproser]

Let me know if there's anything else you'd like to see demonstrated. Thanks so much for watching!

[@user5398-v7x]

@@zackproser are there any other techniques for more accurate results ? i made a rag pipeline with solved numerical physics questions as the database but it seems like it is giving wrong options to those question i have used the GPT-4o model .

[@zackproser]

​@@user5398-v7x Roger. Glad to hear you got it working and thanks for your kind words!