Build a Talking Fully Local RAG with Llama 3, Ollama, LangChain, ChromaDB & ElevenLabs: Nvidia Stock

🔰 Hands-on Tutorial to Build RAG with Ollama, Llama 3, Langchain & ElevenLabs for Nvidia Stock.

3rd video in my LLM series video (Fully Local RAG).

︾︾︾︾︾︾︾︾︾︾︾︾︾︾︾︾︾︾︾︾
︽︽︽︽︽︽︽︽︽︽︽︽︽︽︽︽︽︽︽︽

MENTIONED IN VIDEO

📚 Link to Python Code ➡︎

I show you how to build a fully local Retrieval Augmented Generation (RAG) pipeline for Nvidia Stock Analysis using Llama 3, Ollama, LangChain, and ChromaDB.
Together, we parse PDFs, split text, and create embeddings stored in ChromaDB, a vector database.
You'll learn how to combine RAG with prompt engineering to chat with
complex PDF documents and use ElevenLabs to generate audio from text.
Perfect for those interested in RAG LLM, Ollama, local LLMs like Llama 3 ,Elevenlabs & Nvidia stock analysis with AI (which goes further than OpenAI GPT).

Extra effect: This a Hands-on tutorial where you learn what is rag & what is langchain in practice (using large language models (LLMs) in practice)

⏰ Timecodes ⏰
0:00 Introduction Build a Talking Fully Local RAG with Llama 3, Ollama, LangChain, ChromaDB & ElevenLabs | Stock Advisor
0:42 Parsing PDFs with Langchain
2:14 Text Splitting with LangChain
3:35 ollama python install & Ollama Embeddings & Nomic (ollama tutorial)
6:10 Storing Embeddings in ChromaDB Vector Databse
7:32 FAISS & Qdrant Vector databases (langchain tutorial)
8:29 MultiQueryBuilder with Llama 3 & Ollama (how to run llama 3 locally)
10:56 RAG + Prompt Engineering for Nvidia Stock chatting with Llama 3 (local llm)
12:41 how to use elevenlabs & Generating Audio with ElevenLabs
14:47 Hugging Face

#llama3 #llm #ollama #langchain #elevenlabs #vectordatabase #chromadb #ai #nvidiastock #python #genai #embedding #huggingface #languagemodels #largelanguagemodels #openai #gpt #promptengineering

[Qwme]

I absolutely adore the way you present information with such calmness and clarity. It's like a soothing breeze on a hot day! Thank you immensely, Dr. Maryam. Words can't fully capture the depth of my gratitude for your incredible guidance!

[hamidraza]

your videos are amazing and very excellent in the context of artificial intelligence and machine learning, lots of love and thanks from lahore pakistan

[techhfolks]

Your efforts are always seen in content 💯Always appreciated.

[katelyapina]

Looks like the tutorial crashes at the monent of looking for a directory, nedds a little fix. The video is absolutelly awesome and insightfull.

[hamza-kacem]

That was such a clear and insightful explanation. Thanks a lot <3

[rivascf]

Excellent video—useful, informative, and easy to comprehend and follow. On a separate note, the presentation is beautiful, and the editing work is great! Please continue publishing this amazing material. 👍

[Naejbert]

Thank you! It is very useful and much appreciated 😊

[paulobirek]

Thank you for this! I'm curious about your thoughts on HyDE retriever as opposed to multi-query? I'm struggling with greater accuracy in a software manual of 4500 pages I'm trying to have in my RAG pipeline. I'm attempting semantic chunking of the document today. But, I've tried splitting the PDF, it often loses context. This seems to happen often with concepts widely dispursed across the document. For example "financial management" which is referenced frequently in other sections of the manual but has it's own dedicated sections.

[shuntera]

What I never see in these RAG tutorials is how you modify the contents of the RAG. How do you remove old/redundant data from the vector database and update or add new content. How do you modify an existing PDF for example and have the database remove the old data and add the new data?

[jim]

I have been working with a RAG for awhile and I haven't had much luck with the accuracy of local models, especially if the data is structured data which I assume is because it doesn't ingest well into a vector database. For example if you have a pdf that contains an extension list, the data is structured and not connected in a way that works well with cosign similarity search. I had thought about putting the structured data into a SQL database and using semantic routing to decide whether to pull context from a SQL database versus vector database. Do you have an opinion about using SQl databases with vector databases to increase accuracy?

[davidtindell]

From a NEW Subscriber" " Wow, Wow, Wow, .... wow, ...Wow !" [to quote our latest "Pitch Meeting"] ...

[ozycozy]

Is it common practice to re generate embeddings and vector db in case you don't get good answer or you have better way of chunking? You might have hundreds of pdf files.

[Jcs-rryt]

Am I able to purchase your trainings if I'm in the USA?

[HXMS]

Cool. But by 'fully local' do you mean 'running on google colab'?

[globetrotterbyme]

hi i need yor help: i have an exprience rag piple line with llama 3.1 and try to rag for persian characters but it doesnt work and llama answer incorrect the questions .. a have did alot of research and it seems the embedding model is not work for persian characters ..can you offer any embedding model to embedd persian correctly?

[pythonyousufparyani]

I hope, Ollama will not take whole memory of my pc. Why not using HuggingFace hosted Llama3? I will try to code your tutorial though :) Since it will be on Colab, I don't think it makes any difference. So, I will code it.

[paulkwok]

I don't find 4 pdf in the notebook folders. is it possible to put the pdf into the folder

[anianait]

still no free alternative to Elevenlab?