How to Build an AI Chatbot: RAG with LangChain & Streamlit. LLM chatbot tutorial for beginners

2024 ж. 27 Сәу.
7 351 Рет қаралды

How to build an LLM chatbot using Retrieval Augmented Generation (RAG), LangChain & Streamlit - Full tutorial end-end.
Full code : github.com/SriLaxmi1993/Docum...
With this video, you will be able your own chatbot using the RAG framework. This video also provides langchain tutorial.
You will understand.
- what is langchain
- what is Retrieval Augmented Generation (RAG)
- what are embeddings
- what are vector databases
- How to deploy on streamlit using python
Takeaways :
- Document Genie is a chatbot built using the RAG Framework and Generative AI Model Gemini Pro.
- The app processes PDF documents, creates searchable vector stores, and generates accurate answers to user queries.
- RAG Framework helps avoid hallucination in language models by combining them with external knowledge databases.
- Retrieval augmented generation involves retrieval, augmentation, and generation to enhance the capabilities of language models.
- Embeddings and vector databases play a crucial role in converting text into numerical representations and finding relevant information.
langchain tutorial, streamlit tutorial, generative ai, langchain agents, python streamlit, langchain ai, python web app, machine learning, learn streamlit, how to use streamlit, openai
Chapters :
00:00 Introduction to Document Genie
02:00 How the App Works
03:00 Understanding Rack Framework
04:26 Retrieval Augmented Generation
05:24 Embeddings and Vector Databases
06:21 Code Overview
07:20 Setting up Streamlit Page
16:23 Deploying the App on Streamlit Community Cloud
16:53 Conclusion
#langchain #streamlit #python #generativeai #geminiapi #ai #ragframework
👨 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.
Sneak peek of upcoming projects:
- Text Summarization: Harness the power of Langchain and OpenAI to distill essential information from extensive texts, making comprehension faster and more efficient.
- Llama 2 Chat: Dive into conversational AI with a chatbot built on Meta's open-source Llama 2 LLM, designed for dynamic and engaging interactions.
- Social Media Toolkit: Elevate your online presence with a Hashtag and Caption Generator, utilizing the Cohere API for creative and impactful social media content.
If that sounds interesting, consider subscribing! See you in the next video 😀
Linkedin -
/ sri-laxmi

Пікірлер
  • Good job srilaxmi...why getting nervous. you are perfectly doing fine...

    @user-lq2kt4xh9q@user-lq2kt4xh9q17 күн бұрын
  • Awesome job Sri! 🙌 Please keep it up!

    @kinlearn@kinlearn2 ай бұрын
    • Thank you! Will do!

      @sri_laxmi@sri_laxmi2 ай бұрын
  • Can you do a tutorial on training a model on a PDF file data and save that model in local machine so that it can be used with out internet connection😊

    @noa2427@noa242727 күн бұрын
  • ma'am can we make a chatbot which will answer all the space related questions where I want to use nasa api to answer the questions integrated with a llm model like OLlama or huggingface llm models integrated with langchain ?

    @ASHUTOSHJOSHI-ye8hs@ASHUTOSHJOSHI-ye8hs29 күн бұрын
  • You should make Streamlit file and Langchain File different. Both has different purpose.

    @SaniyaJaswani@SaniyaJaswani9 күн бұрын
  • any ideas on how you can build a similar application with CSV files? Can we also input multiple files?

    @shivanigole1665@shivanigole166523 күн бұрын
    • did you find a solution?

      @mariospisak1864@mariospisak186420 күн бұрын
  • Awesome project! I'm hitting issues on deploying to Streamlit and wondering if others are as well. Seems like its hitting issues when trying to satisfy the requirement os for langchain. Error below: Collecting langchain_google_genai Downloading langchain_google_genai-0.0.9-py3-none-any.whl (17 kB) ERROR: Could not find a version that satisfies the requirement os (from versions: none) ERROR: No matching distribution found for os

    @bsheridan4898@bsheridan48982 ай бұрын
    • Hi. Looks like you found the solution. Thanks for sharing your project with me on LinkedIn. More tutorials coming out:)

      @sri_laxmi@sri_laxmi2 ай бұрын
    • @@sri_laxmi🙂 sure did! I had to add another library to the requirements.txt file related to PyCryptodome in order for AMS to work and also set a few versions for other libraries to install. Cant wait to see more of your tutorials!

      @bsheridan4898@bsheridan48982 ай бұрын
    • Hi - I am getting the same error. Can you please share the solve?

      @adityapuri98@adityapuri98Ай бұрын
    • what is the error? Could you share it here?@@adityapuri98

      @sri_laxmi@sri_laxmiАй бұрын
  • I am pretty much sure that prompt template is not going to work. Try asking some out of the topic questions and it will give answer, which basically fails the purpose

    @satyamoahnty@satyamoahnty12 күн бұрын
  • Hi @sri_laxmi, I am facing an error while trying the code. here is the error "ValueError: The de-serialization relies loading a pickle file. Pickle files can be modified to deliver a malicious payload that results in execution of arbitrary code on your machine.You will need to set `allow_dangerous_deserialization` to `True` to enable deserialization. If you do this, make sure that you trust the source of the data. For example, if you are loading a file that you created, and no that no one else has modified the file, then this is safe to do. Do not set this to `True` if you are loading a file from an untrusted source (e.g., some random site on the internet.)."

    @aniketchhabra8912@aniketchhabra891224 күн бұрын
    • @aniketchhabra8912 - Can you share solution on how did you resolve this error as I am also getting same error ?

      @prabhatsachan139@prabhatsachan1394 күн бұрын
    • @Sri_laxmi - Would it be possible for you to help with the resolution here for the error mentioned above?

      @prabhatsachan139@prabhatsachan1394 күн бұрын
KZhead