Build Chatbot using Streamlit & Ollama | llama2 | No ChatGPT API

Поділитися
Вставка
  • Опубліковано 15 вер 2024

КОМЕНТАРІ • 19

  • @CoderzColumn
    @CoderzColumn  5 місяців тому +1

    Do check out my other chatbot creation videos that uses front-end other than Streamlit.
    Gradio-Ollama Chatbot -> ua-cam.com/video/EON9jBnItUU/v-deo.html
    Panel-Ollama Chatbot -> ua-cam.com/video/ilAZdYvlKKM/v-deo.html
    Chainlit-Ollama Chatbot - > ua-cam.com/video/FVh32fVFf3c/v-deo.html

  • @gomgom330
    @gomgom330 Місяць тому

    So it just run on our local enviroment, no need internet? But what if we share it on streamlit cloud, can it run as we know streamlit cloud doesn't have high resource or even GPU

    • @CoderzColumn
      @CoderzColumn  Місяць тому

      Yes. It runs on our local computer and does not need internet for it,
      Now for sharing it on streamlit cloud is not possible with ollama because streamlit does not let u run ollama there and yes it does not have high resource or GPU.
      You can deploy Ollama on some cloud instance (Gcloud or AWS) and then access it through API. You can then replace code to access ollama through that cloud instance based URL (base_url parameter). That's one solution.
      Another solution would be to use OpenAI rest API but it is not free. Recently, I have started using Groq REST API which is free. They provide latest Open source models like Llama-3.1, though there is request limit (30 requests per minute). Also, there models are full and not quantized one like Ollama hence more accurate.

    • @gomgom330
      @gomgom330 Місяць тому

      @@CoderzColumn aahh i see, so we can build and host our model in server that have high resource, then we use it as rest API for streamlit web app that we share, thx for explain.

    • @CoderzColumn
      @CoderzColumn  Місяць тому

      Yea. You can use it other platforms than Streamlit because just like openai API, your models are available through API. You can even create models for custom uses.
      But i feel the cloud instance are bit pricey. You'll need good instance with 16/32/64 GB RAM and one with high GPU RAM. The cost increases fastly with specs.
      You know if you have some spare system with GPU lying around then you can use it as well.You'll have to keep it on all the time and initially, you'll have to do few firewall settings to make it accessible to outside world on internet. This one can be cheaper hopefully but you'll still have to pay for electricity for keeping this system on (which has GPU hence more electricity usage).

    • @gomgom330
      @gomgom330 Місяць тому

      @@CoderzColumn yep you right, even if we make own server to host Rest API, we can use it for any use case. thx for response

  • @alic4818
    @alic4818 5 місяців тому

    Another great video! I would like the chatbot to present to the user (being a university student) different career profiles/paths (including requirements and salary e.g to becoming a project manager) based on their skills and interests, also showing them clickable questions regarding career guidance like looking for graduate jobs? Would you know how I can be able to do this? Thanks

    • @CoderzColumn
      @CoderzColumn  5 місяців тому +1

      Well !!! This is very customized bot requirements. You'll have to add these components manually by reading docs of streamlit.
      If you use Gradio as front-end then there is way to include sample examples (Example Query & Responses) in chatbot.
      www.gradio.app/guides/creating-a-chatbot-fast#customizing-your-chatbot

    • @alic4818
      @alic4818 5 місяців тому

      @@CoderzColumn I would like to make my own UI or maybe on streamlit as I can deploy on streamlit cloud for people to use. So I will need to look up documents on adding these components then. I used ChatGPT to help me add and some works but not all. This might sound much but would you please be able to join a team’s call to discuss this. Would extremely appreciate your support helping a student out.

  • @mohammadyahya78
    @mohammadyahya78 2 місяці тому

    amazing thanks

  • @cursedsinner99
    @cursedsinner99 4 місяці тому

    why you are underrated buddy?

    • @CoderzColumn
      @CoderzColumn  4 місяці тому

      Thanks for your comment. Really appreciate it.
      It takes time to grow youtube channel and I feel that there are quite better creators than me. I am still growing.

    • @cursedsinner99
      @cursedsinner99 4 місяці тому

      @@CoderzColumn using your code
      I give it an update
      Switchable among Multiple llms and multiple roles
      New chat and retrieve old chats and
      With pdf uploading without langchain
      Am using that gui as AImployee instead of employee in my new startup
      Still messing with the code
      And trying to give internet access
      And more features to do even few works behalf of me

    • @CoderzColumn
      @CoderzColumn  4 місяці тому

      Wow. You seem to have gone a long way ahead of me. Great Job. Keep it up. Thanks for sharing with us.

  • @arjuns5732
    @arjuns5732 3 місяці тому

    Nice video. Have you made the sso based authentication video ?

    • @CoderzColumn
      @CoderzColumn  3 місяці тому

      Thanks for feedback. No, I haven't made video on authentication for chatbots yet. Its on my radar and planning to make some videos on adding authentication to Chatbots. But as of now, there are none.

  • @opokuandrew5716
    @opokuandrew5716 2 місяці тому

    You are so underrated and I still don't get it