FREE Local RAG Chatbot with Ollama - Streamlit and Langchain. Build with open-source Mistral ai

"Step-by-Step Guide to Building a RAG Chatbot with Ollama, streamlit, Mistral ai and Langchain

Build Retrieval Augmented Generation (RAG) chatbot locally. The app leverages Ollama, a tool that allows running large language models (LLMs) locally, along with the Mistral 7B open-source model for text embeddings and retrieval-based question answering. Specifically, we'll be using the nomic-embed-text model for generating embeddings, which is a high-performing open embedding model with a large token context window outperforming OpenAI embeddings

In this tutorial you will learn :

- how to run ollama locally
- use ollama langchain
- using ollama embeddings
- Using open source model Mistral ai Ollama
- Build RAG ollama
- Use Ollama library python
- Using ollama APIs
- install ollama in python
- how to run ollama run mixtral:8x7b
- run ollama mac

👨 WHO AM I -

I'm Sri Laxmi an AI product Manager who lives in San Francisco, CA. On this channel, we will learn how to build generative AI applications and use AI tools that can help us launch the projects that inspire us and, consequentially, lead the lives we've always dreamed about.

Linkedin -

/ sri-laxmi

[abhipawar]

Your videos can be understood by even a class 8 child, so simple!!

[deanosaureflex]

Your video is incredibly useful thank you and keep going like ethis !!

[shreyasbs]

Nice. Please do some more videos on privacy of data while implementing rag systems

[KumR]

Thank you.. had to tweak the code a little but this is great ..

[emailvarun]

Hi, I am assuming these embeddings and the docs are completely on my local and my docs(if I use my own pdf docs instead of URLs) are not shared anywhere.

[_yurisales]

How can I make my streamlit + chromadb application faster? I'm loading locally 30 pdf files and when I run the application, It takes like 40 minutes to load the documents and, after, load the streamlit interface. Is there a way where I can reduce this time? Is there a way to work with multithreading or multiparallelism in chromadb?

[alfonsor.]

Hi, Amazing Video, and very useful. Please, could you add any other video on using pdf or txt files instead of websites (www.), thanks!

[aousabdo]

Great tutorial, thank you. Is it possible to share the github of the code?

[souvikbhattacharya]

How can I upload specific personalised pdfs in order to chat to it ?

[jonzh]

Thanks for simple demo.

Is it possible to use same embedding to chat with different model, since olama have variety model, I don’t want to same source file to keep multiple vector db.
If not possible, how to overcome this?

[muhammadsagor]

ValueError: Error raised by inference API HTTP code: 404, {"error":"model 'nomic-embed-text' not found, try pulling it first"}
anyone face this?

[atulkishore]

mam i am getting error there is something wrong in this code i have given 4 urls and still its not displaying the result..
ERROR: Number of requested results 4 is greater than number of elements in index 3, updating n_results = 3
when i given 4 urls then i am not getting this log message but query is not displaying .
PLEASE HELP MAM

[atulkishore]

embedding=embeddings.ollama.OllamaEmbeddings(model='nomic-embed-text'),
)
issue in this line also

AttributeError: module has no attribute ollama
embedding=embeddings.ollama.OllamaEmbeddings(model='nomic-embed-text'),