Building an AI Data Assistant with Streamlit, LangChain and OpenAI | Part 3

Over the past decade, chatbots have emerged as a powerful asset for businesses, organisations, and users, enhancing communication and boosting productivity. Whether it involves handling customer service inquiries or crafting captivating interactive experiences, these AI-powered platforms are transforming the landscape of information retrieval.
In this last part of our series Building an AI Data Assistant with Streamlit, LangChain and OpenAI we are delving into the creation of a chatbox, taking our AI assistant to new heights and further enhancing the user experience of our application.
—
This video is part of the series Building an AI Assistant to make your data science life easier in which we will develop an AI assistant using Streamlit, LangChain and OpenAI’s GPT models, designed to help users with their data science projects.

If you missed part 1 and 2, don’t worry! You can catch up here

If you want to take a deeper dive in data science, check out our library of courses on digiLab Academy

————————————————————————
🎵 Music
————————————————————————
Creative Commons / Attribution 4.0 International (CC BY 4.0)

————————————————————————
📌 Timestamps
————————————————————————

Intro | 00:00
Agenda | 04:34
Importing the required packages and modules | 05:48
Document indexing - document loader | 06:18
Document indexing - text splitter | 07:50
Document indexing - creating embedding | 08:54
Document indexing - creating a Pinecone account and setting index | 09:31
Document indexing - storing embeddings into Pinecone | 10:38
Document indexing - similarity search | 11:35
Enhancing user experience - adding tabs | 10:50
Auxiliary functions for our chatbox - set up | 15:16
Auxiliary functions for our chatbox - finding matches | 16:18
Auxiliary functions for our chatbox - refining queries | 16:45
Auxiliary functions for our chatbox - tracking the conversation | 17:52
Building the chatbot application with Streamlit - set up | 18:33
Building the chatbot application with Streamlit - session state | 19:10
Building the chatbot application with Streamlit - initialising the LLM | 19:42
Building the chatbot application with Streamlit - conversation buffer memory | 20:10
Building the chatbot application with Streamlit - prompt templates | 20:37
Building the chatbot application with Streamlit - conversation chain | 21:41
Building the chatbot application with Streamlit - creating the user interface | 22:14
Building the chatbot application with Streamlit - generating responses | 22:40

————————————————————————
📌 Resources
————————————————————————

————————————————————————
👱🏻‍♀️ Connect with me
————————————————————————
Twitter - @digiLab_Academy

————————————————————————
🏷️ Tags
————————————————————————
Building an AI assistant to make your data science life easier
Crafting an AI assistant using Streamlit, Langchain and OpenAI models
Creating an AI assistant to ease your path in data science
Developing a data science ally using Streamlit, Langchain and OpenAI models
Making data science easy with the aid of an intelligent assistant
Making data science effortless with the implementation of an AI assistant
Creating your a chatbot

————————————————————————
✨ Hashtags
————————————————————————

[kalicap]

Best video series on Langchain I've come across! The result is very aesthetically and functionally unique compared to the millions of chatbot tutorials out there

[hritvikpatwa]

By far the most comprehensive and perfect tutorial on Langchain I've seen. Thanks for such a detailed project.

[EmmanuelOgungbemi]

Excellent video 🎉 Dr. Anna, thank you for this series 🙏

[AxelB]

Thank you, great video series Ana!
I hope, you have revoked the Pinecone key meanwhile as it is still visible in some sections of the video.

[Hannah-ssrd]

This is a really good tutorial. Is there part 4 video coming in this topic? Looking forward it!! Thanks.

[k_vamsi]

Which pinecone Version did you use in this project

[seherbal]

Hi, thank you for this video 🧡I am learning with you. Which Python Version did you use for this project?

[BruinBearDoc]

Technically valuable, culturally destructive aesthetics that subtly undermine humanity

[swetharangaraj]

what is the process if i what to query chat from cloud mangoDB using llm and RAG

[ahrcrs]

Dear Dr. Rojo, first of all congratulation on the work you have done is very impressive and the tutorial is very didactic. Regardless of following you every step of the way, I keep getting an error on streamlit that I don't know how to overcome. I keep getting the Following:

File "C:\Users\csosa\OneDrive\Escritorio\Documentos\Python\.venv\Lib\site-packages\streamlit\runtime\state\session_state.py", line 398, in __getitem__
return self._getitem(widget_id, key)

File "C:\Users\csosa\OneDrive\Escritorio\Documentos\Python\.venv\Lib\site-packages\streamlit\runtime\state\session_state.py", line 443, in _getitem
raise KeyError
KeyError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Users\csosa\OneDrive\Escritorio\Documentos\Python\.venv\Lib\site-packages\streamlit\runtime\state\session_state_proxy.py", line 119, in __getattr__
return self[key]

File "C:\Users\csosa\OneDrive\Escritorio\Documentos\Python\.venv\Lib\site-packages\streamlit\runtime\state\session_state_proxy.py", line 90, in __getitem__
return get_session_state()[key]

File "C:\Users\csosa\OneDrive\Escritorio\Documentos\Python\.venv\Lib\site-packages\streamlit\runtime\state\safe_session_state.py", line 91, in __getitem__
return self._state[key]

File "C:\Users\csosa\OneDrive\Escritorio\Documentos\Python\.venv\Lib\site-packages\streamlit\runtime\state\session_state.py", line 400, in __getitem__
raise

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "c:\Users\csosa\OneDrive\Escritorio\Documentos\Python\Resources2\app_DS.py", line 53, in <module>
if st.session_state.clicked[1]:

File "C:\Users\csosa\OneDrive\Escritorio\Documentos\Python\.venv\Lib\site-packages\streamlit\runtime\state\session_state_proxy.py", line 121, in __getattr__
raise

Any help will be mostly appreciated