RAG with Chat History using LangChain & Ollama Locally and For Free
VloĆŸit
- Äas pĆidĂĄn 29. 08. 2024
- Learn how to add a RAG chatbot app to memory using Ollama and LangChain locally and for free.
00:01 Introduction
00:35 Setup
02:16 Initialize the local model
03:57 Load data
05:15 Split data
07:06 Index the data
10:34 Create a chain to contextualize
15:04 Create a qa chain
17:25 Create a RAG chain
18:42 Inference
đ Medium: / tirendazacademy
đ X: x.com/tirendaz...
đ LinkedIn: / tirendaz-academy
â¶ïž LangChain Tutorials:
âą LangChain Tutorials
â¶ïž Generative AI Tutorials:
âą Generative AI Tutorials
â¶ïž LLMs Tutorials:
âą LLMs Tutorials
â¶ïž HuggingFace Tutorials:
âą HuggingFace Tutorials ...
đ Notebook: github.com/Tir...
đ LangGraph Blog: blog.langchain...
đ„ Thanks for watching. Don't forget to subscribe, like the video, and leave a comment.
#ai #langgraph #generativeai
What i like about your videos that you start from scratch and whoever wants to jump ahead of time can do that. Langchain practice from the very beginning is a must to stick in the brain and later become a second nature for the gen ai langchain builder... Ylcool work, learned a lot ... đđ»
Glad to hear that đ
The best tutorial!!!! Great THANK YOU
Glad you liked it!
found another gem! i will upgrade the SSD, and follow this out immediately!
I'm currently making roleplay chating AI website, and this just pop out!
Thanks a lot , very helpful tutorial, I have one question, what's the specs of the running machine (cpu, gpu, ram, os)?
If you use a local model with Ollama, system requirements depend on the model you'll use. For example, you need to have at least 8GB RAM for the 7B or 8B model version.
Thank you once again for your hard work and dedication. I look forward to watching more of your videos and learning from your expertise.
I'm glad to hear that. Thank you for your feedback.