so I build a production

so I build a production ready a restaurant chatbot so here's the all code of it I use fast API as a backend and Langchain and Gemini and Python okay so let's try it so it is store past 5 messages summarized version of it it is greeting now let's tell my name is Vishal my name is Vishal as you can see it is keeping my name so let's tell what is your menu what do you have in menu is giving the menu now let's explain you how it actually work so first we go to here first it take input first it make every user its own session ID so the security should be handled after that it build a context of it then send to the LLM then update the memory of the summarise which keep only five messages ok so this is the whole process and the crazy part is it uses API rotation means when API one API credits end second if seconds end then go to third because Gemini API is free and trial give us less tokens so that's why I use that crazy part it this is completely open source as you can see I also deploy the same code but some more upgrades in my portfolio website as you can see here it is working correctly live and I also publish this Sadabahar restaurant bot so I will put these 3 link in the bio in the description you can visit it and the project is open source and you can use it by your own but this is only part 1 in part 2 we are going to give be even more powerful we are adding RAG System AI read from a PDF menu database order placement customer can place Google Sheet integration order save automatically into Google Sheet email confirmation customer get instant email okay so follow me if you don't want to miss part 2 if you found this useful give it a like and share it with someone who is building AI project see you in Part two