FAISS Vector Library with LangChain and OpenAI (Semantic Search)

In this video, we take a look at the Facebook AI Similarity Search (FAISS) vector library. Through a few examples, we will grab a document, chunk it, set up embeddings, and search through it.
Interested in discussing a Data or AI project? Feel free to reach out via email or simply complete the contact form on my website.
📧 Email: [e-mail]
🌐 Website & Blog: ryannolandata....
🍿 WATCH NEXT
OpenAI/Langchain Playlist: • How to Build Your Firs...
Vector Embeddings: • LangChain (OpenAI) Vec...
Langchain Chains: • LangChain Chains for B...
Streamlit Langchain: • Learn to Build Excitin...
MY OTHER SOCIALS:
👨‍💻 LinkedIn: / ryan-p-nolan
🐦 Twitter: / ryannolan_
⚙️ GitHub: github.com/Rya...
🖥️ Discord: / discord
📚 *Data and AI Courses: datacamp.pxf.i...
📚 *Practice SQL & Python Interview Questions: stratascratch....
WHO AM I?
As a full-time data analyst/scientist at a fintech company specializing in combating fraud within underwriting and risk, I've transitioned from my background in Electrical Engineering to pursue my true passion: data. In this dynamic field, I've discovered a profound interest in leveraging data analytics to address complex challenges in the financial sector.
This KZbin channel serves as both a platform for sharing knowledge and a personal journey of continuous learning. With a commitment to growth, I aim to expand my skill set by publishing 2 to 3 new videos each week, delving into various aspects of data analytics/science and Artificial Intelligence. Join me on this exciting journey as we explore the endless possibilities of data together.
*This is an affiliate program. I may receive a small portion of the final sale at no extra cost to you.

[@RyanAndMattDataScience]

Hey guys I hope you enjoyed the video! If you did please subscribe to the channel! Join our Data Science Discord Here: discord.com/invite/F7dxbvHUhg If you want to watch a full course on AI check out Datacamp: datacamp.pxf.io/XYD7Qg Want to solve Python data interview questions: stratascratch.com/?via=ryan I'm also open to freelance data projects. Hit me up at [e-mail] *Both Datacamp and Stratascratch are affiliate links.

[@eugenmalatov5470]

Just a question: FAISS is now using only CPU not GPU. I have Windows. How can I get FAISS run with my GPU? If not what alternative vectorbases should I use? It makes a large difference in terms of performance doesnt it?

[@palanikumarmsc]

When I do date related query with FAISS why FAISS not returning perfect result? Do I need to update query for Vector search?

[@MehreenMunsif]

similarity_search gives 4 most similar texts? because I'm getting from 0th to 3rd index results when i query something.

[@stanTrX]

Thanks, how can we apply it to tables such as csv or even sqlite tables?

[@amalasebastian9968]

hey, I want to see how embeddings look/is stored in vectorStore. I want to store the embeddings in a CSV format. I am using FAISS only. How to store it in CSV format?

[@genie52]

hey man this is _really_ good work!! keep on going!

[@RyanAndMattDataScience]

Thank you!

[@EulerKernighan]

Hi Ryan, you have now idea how this video of yours was good for me. I really appreciate it. Do you know how I can replace the OpenAI stuff and Jan AI (Jan is an offline AI thing that you can download to your computer and remove the dependency from cloud providers/service/internet connection. Thanks again! Keep the good stuff coming! btw, who would say Metallica would help learning AI, huh? LOL

[@RyanAndMattDataScience]

Haha glad you like the Metallica. I haven’t heard of jan AI but maybe something to look at in the future. I’m about to crush out a series on dbt so will look after

[@EulerKernighan]

@@RyanAndMattDataScience tagged along! Can't wait to learn more stuff!

[@pavankumartalari387]

Small Doubt did you pay for OPENAI api key ? Because I have not paid it . If we pay only we would able to use the Embedding models ?

[@RyanAndMattDataScience]

I didn’t pay when I made this video. I had to pay last week for gpt vision

[@pavankumartalari387]

@@RyanAndMattDataScience thank you so much, learnt a lot from this video.

[@ralphanthony5198]

Great video! Good job. Love Metallica as well!!!

[@RyanAndMattDataScience]

Thanks

[@varunsharma9757]

Brother saw some of your other videos as well , you are doing a superb job here. It feels bad when I see quite a low response from the audience even though your videos are exceptionally knowledgable . keep working hard bro you will grow , best wishes

[@RyanAndMattDataScience]

Thanks man I’m going to continue to push and learn/post videos. Working on getting leetcode out weekly now with a few other vids.

[@davidtindell950]

Ryan, really appreciate you adding how to save and load FAISS vector database at end of this vid. I ran several repeated tests against my saved VDB and it appeared to make NO DIFFERENCE in Open usage or Costs for today = Aug 3, 2024!😂

[@davidtindell950]

Thank You. A very important and timely topic. Thank You!. Next, best embeddings ?

[@davidtindell950]

New Subscriber !

[@MehreenMunsif]

I don't understand the difference between query and retriever. Can someone help me understand this?

[@vikramn2190]

Absolutely brilliant and useful video. You are the REAL rockstar (no pun intended :))! If you are ever looking for content ideas .... here's one: Do a video on building a RAG pipeline on AWS Bedrock. The AWS platform is phenomenal but the documentation is often confusing. And they have a ton of really useful features (like Guardrails).

[@RyanAndMattDataScience]

I haven’t used AWS yet. I’m trying to get thrown into a few AWS projects at work but no luck :/ I do want to learn AWS and make vids on it.

[@senthilbalajiganesan]

Hey bro, this is an amazing tutorial, it would be great if you share the code link

[@RyanAndMattDataScience]

I need to add it on GitHub. I’m just so behind with it

[@chukiatsakjirapapong933]

Hi bro, Great Video. Hope to see next!

[@RyanAndMattDataScience]

Np see you in the next vid

[@m4rc1_n4ch0s]

Great video!

[@RyanAndMattDataScience]

Thanks