วีดีโอ

please don't use "basically" every 10seconds, thanks. It's the plague of english language all over the world

Hi, Thanks for the tutorial. Do you know if there's a way to write code that uses my local Ollama directly from any browser's console, like Chrome? I can get some text from the DOM and would like to use Ollama to do some thing with it.

There is no Vector Search anymore. Is this a workaround? How to connect your db with the {context} now?

Amazing tutorial.

Good content.

Very good content. Keep doing videos.

holy F this was the greatest explanation ever - thank you so much - I don't have the words to describe how incredibly helpful this was to me. thank you.

hats off to you sir , i really grateful to watch this video , bcz everyone using openai but it reuired money ,tqs for using hugging face api sir , i am looking for it i got it in right time sir bcz of you sir , i really become fan of you making the llm application using opensourse

Best tutorial on ChromaDB I found so far! Thanks!

Totally underrated video. Thanks for sharing.

So, for those of us who aren't coders but want to use Openrouter as if we were in Claude and using their projects to store knowledge, is that possible and if so, how?

nice video dude, really nicely explained

25:23 it's to my understanding that the first time you will always get this message because the PDF hasn't been saved to the vector database until the app has run at least once.

Thank you!!!

Outstanding content. Thanks for the effort towards making it. I have a doubt here. Since these vector stores are viewable as folders as you showed in the video, what if someone accidentally deletes a store which had been storing data for over a year ? How do I handle that ?

Great video, lots of stuff is more understandable. This video was uplodaded 3 month ago & today some of the modules have changed (chroma db / chroma search - are now one module) so it's not just step-to-step follow up to represent the same logics). Thanks for video anyway

When facing big and different information data, then using cloud vector with this cart, the result will dissapointed, we need more structure so user question really answered based on whole document searching

this is really difficult to follow - it's unfeasibly quiet for a lot of the time but then every few minutes it goes incredibly loud and frightening then back to too quiet, then too loud

Did you every get the memory working? :)

so much easier than google's guide, thank you

what langflow version are you using? The current one I am using is v 0.5.12 and the UI and block headers seems to be different.

0:00 - Introduction: Building an AI Application 0:35 - Model Sequencing and Airtable Integration 1:15 - Chrome Extension Demo and Summarization 1:57 - Customizing Model Selection and Output 2:31 - Model Output Comparison: GPT-4 Mini vs. Llama 3.1 2:56 - Project Overview and Tools 3:39 - Handling Multiple Sections and Use Cases 4:21 - Database-Driven Prompt Management 4:58 - Benefits of Database-Driven Prompts 5:40 - Airtable as a Prompt Management Tool 6:04 - Setting up Airtable: Creating a Base 8:12 - Defining Prompts Table and Fields 9:39 - Creating a Models Table 11:53 - Populating the Models Table 14:29 - Fetching and Integrating Perplexity Models 15:44 - Creating LLM Configuration Table 16:59 - Linking Models and Prompts to Configuration 18:37 - Output Strategy and Configuration 20:46 - Generating Unique Configuration Identifiers 23:06 - Python Integration: Fetching Airtable Data 27:07 - Python Code Generation with AI Assistance 28:21 - Building a Search Records Function 31:00 - Obtaining Airtable API Keys and Base ID 34:36 - Connecting to Airtable with Python 36:19 - Project Recap and Next Steps 39:48 - Dynamically Modifying Model Sequence 42:03 - Accessing System and User Prompts 43:54 - Conclusion and Future Development

Please provide all the workflow as image format for better understanding.... Great video., Thanks a lot.....

Thank you, always instructive.

You know you can just add them dependencies all in one line ?

Thank you very much, It helps me a lot

How can I change it from openAi to Gemini AI?

Can I do this in Python?

hi Jain, tks for this. can i seek your help on steps to deploy to front-end / web app - say via Azure web apps? tk u.

Can u do this with local LLM

I can’t seem to save the api key Says: API key save error

so when i run the code it doesnt open the chatbot app whats wrong?

Can I do this with gemeni Ai? I think u gotta pay for OpenAI api

please my laptop is 300usd(pre covid19) ubuntu 4gb of ram i could buy a ram of 8gb and change it, even if is aws, or cloud is great for me can you give me advice please

Why does my notebook code gives “false” instead of true?

Basically, what you did is, get a long video, divide it into short potentially viral videos. Am I right?

Thank you for the video, I am facing an issue with Vector Search. I don't have an option on langflow for "Vector Search". Please help me with the steps.

0:00 - Introduction 0:08 - Nutrition Monitor Demo 0:25 - How it Works: Google Gemini Pro 0:50 - Project Setup: Streamlit 1:06 - Creating a Virtual Environment 1:36 - Installing Streamlit 1:56 - Environment Variables and Google AI 2:14 - Creating a Python Environment 2:47 - Verifying Installation 3:39 - Coding app.py 3:47 - Importing Libraries 4:37 - Creating .env File with API Key 5:19 - Main Coding File: app.py 5:31 - Page Configuration 6:59 - Loading Environment Variables 7:12 - Configuring Google Gemini AI 7:48 - Method: Get Gemini Response 9:49 - Handling Image Upload 11:25 - Returning Image Data 12:27 - Building the Sidebar 13:57 - Building the Header 14:33 - Displaying Uploaded Image 15:48 - Implementing Submit Button Logic 17:30 - Prompt Engineering: Input Prompt 19:19 - Input Button Code 20:51 - Code Completion and Execution 22:01 - Testing with Images 24:33 - Prompt Optimization: Table Output 24:55 - Conclusion and Outro

Bro can u share thr documentation

Can u please give me the code i liked and subscribed you bro

Just asking. Why would I do this? When I can just prompt something like Meastro to just write the python code? The LLM is the interface now. I tried this and its neat, but at the end of the day, its faster to just ask Maestro to write the python. Not trying to start a riot, I just don't see why I would use this.

Good tutorial, thanks if you have integrated the translation of subs in to desired language, this video would have been even better.

Thanks for this video, this is amazing video.I just have to know how to deploy it. I have locally installed langflow in my laptop and create a project which is successfully run. Now I have to make it everyone usable, can you please guide me or suggest me? Thanks in advance.

Thank you. Loved the simplicity of this app. Learnt a lot.

really learned a lot and I think I have become the fan of you. Watching the videos are like tech movies. Moreover, I just want to say "Thankyou for efforts making me understand the core concepts".

could you please use open source models instead?

hello please can you add that extra bit of codes and update

Vector database Embedding

Thank you so much for this. It helped me a lot.