Python Langchain Tutorial: Use 3 Different LLMs in 10 Mins

Learn how to easily switch between LLMs in Langchain for your Python applications: OpenAI's GPT-4, Amazon Bedrock (Claude V2), and Google Gemini Pro.
Or if none of these suit your needs, you can also implement your own interface.
📚 Chapters
00:00 Introduction
01:43 Getting Started
03:18 Creating the Base App
05:33 How To Use OpenAI GPT-4
07:42 How To Use Claude/Llama2 (via AWS)
09:33 How To Use Google Gemini Pro
10:27 Custom LLMs
👉 Links
🔗 Code: github.com/pixegami/langchain...
🔗 Langchain LLMs: python.langchain.com/docs/int...
🔗 Custom LLM: python.langchain.com/docs/mod...
🔗 AWS Bedrock: aws.amazon.com/bedrock
🔗 Google AI API: makersuite.google.com/app/apikey
🔗 How to Get Started with AWS: • How to Get Started wit...

[@bec_Divyansh]

Would love to see how huggingface can be used here. If possible please drop a video describing it, thanks!

[@c4rb0nx16]

@pixegami TBH this channel got me so much interest and motivation to do something new and your contents are really impressive. 🔥

[@pixegami]

Really glad to hear that! Thank you, and good luck :)

[@Midnightmicroscope]

Fantastic video! I would love more tutorials about setting this up on a local LLM. I love the example used in this video but I don’t like the idea of having to send bank statements to LLMs in the cloud. 😅

[@pixegami]

Good call out. I'm looking at doing something like that for my next video :)

[@papalikedrawing]

Thank you very much

[@pixegami]

You're welcome!

[@raonitimo23]

Excellent video and content in general. I'll leave an idea: do a similar video on funcchain, it's a pythonic library that encapsulates some of the langchain complexities.

[@NathanSTLPillai]

"Nvidia Inference Microservice" demo will be a good addition

[@pixegami]

I haven't looked into that yet, but thanks for the suggestion :)

[@NathanSTLPillai]

Excellent video.
What developer tools need to develop these applications ?
In general for GenAI development.

[@sshlich]

Vector databases, embeddings, langchain, cloud computing (aws, gcp)

[@rossholland879]

hey man ! Please do a tutorial on LLM agents and using a custom APi as a tool

[@pixegami]

It's a good idea. Thanks for the suggestion :)

[@botondvasvari5758]

and how can I use big models from huggingface ? I can't load them into memory because many of them are bigger than 15gb, some of them are 130gb+ . Any thoughts?

[@dxb526]

Langchain is a great tool but is there any use to it if I will only use one LLM i.e., GPT?

[@Amr-Ibrahim-AI]

yes. It streamlines writing applications that use LLMs. It's true that you can do everything without LangChain, but using it would make your life much easier

[@pixegami]

Yup, it gives you a lot of boilerplate utilities like templates, chains, and a bunch of other integrations.

[@bukitsorrento]

LLM datasette

[@bukitsorrento]

Phidata!

[@bukitsorrento]

Magentic

[@shahnaz9026]

you didn't use azure open ai llm because most of the companies using closed openai like azure so.. We can learn azure open ai services so create video with azure open ai llm with multimodal support rag application ( input multiple pdfs with images and tables and text) and integrate with streamlit..
post the vdo by using azure open api key
Azure open ai embedding and azurechatopenai for multiple pdfs rag application..
Using azure open api end point there are no videos on RUclips so it would be helpful.. 😊