I am a software engineer with looooong experience, but I am super confused about AI and inner workings. I might just start this was to see how things operate at the top and turn this into code on the other side. Make more videos about langflow, very nice content. Thank you!
This is a truly excellent tutorial. It's the first time I've worked with this framework, and the video covers every detail with perfect clarity. I made some variations, using Ollama with llama3 and Chroma as a vector store, and everything went smoothly thanks to your clear explanations. Fantastic work!
31:43 What can I connect instead of "Record"? In my Langflow, there are other dots such ad Retriever, Search Results, Vector Store in the Astra DB node instead of 'langflow'. Thanks for a good tutorial by the way!
Very good and easy to follow video, although I could not make it work with Ollama in Docker. Ran into multiple issues with Astra DB as well when using Ollama Embedings failing to create a data set automatically and spilling a number of errors. Granted I am a complete beginner. Would be cool if there was a follow up tutorial showing how to do the same for local Ollama models and how to address the Ollama hosted in Docker.
Always great contents! Really clear and concise demo of langchain. Maybe you can make a video of how to allow the user to dynamically chose a website to ask questions about
Thanks @underfitted Simple and straight-forward explanation. Do you have any example where you've used the "API Request" under "Data" where based on the question, an orchestrator can call an API endpoint and pass values from the Vector output?
Thank You Santiago Thank you for sharing your insights on "Step by step no-code RAG application using Langflow." Question: Regarding your use of chunking by 1000 and embedding with a size of 1536 for OpenAI, my question is: If I were to increase the chunking size to something larger, such as 2000, would that present any issues? Would it increase or decrease the performance of the model? I'm curious to understand the tradeoffs and implications of using a larger chunking size. Does it have an impact on things like model accuracy, training time, or memory usage? I'd appreciate your insights on how the chunking size can affect the overall performance and effectiveness of the machine learning system. Thank you again for your valuable contributions. I look forward to hearing your thoughts on this follow-up question.
Hello there, thank you for amazing video, you gave me so much value!! I would like to ask if its possible to somehow create a website application interface for this chatbot, like I dont have much experience with coding so I would love to know a way how can I create a website application interface in some low code platform and then connect it somehow with the langlow chatbot to somewhat resemble ChatGPT platform, I would like to create website RAG application for students in my country. But I am not sure if its even possible, so I would be very happy for your advice. Thank you :)
Awesome, appreciate you're sharing it 👍does Langflow support other inputs from text, for example images, tables, etc. does it have OCR komponent supported too ?
Just curious but does this program have input and outputs for using voice activation and speakers for speaking? Id like to create an ai assistant for my house and like the look and feel of this because its quite si.ilar to the way unreal engine uses blueprints.
Great video @svpino, as always. However, I found that the python code using sample.json doesn't provide accurate results always as we get from the 'Run' using the browser. Even the same question that works well on browser gets a totally unrelated result on Python code when run with the json. Do you suggest anything on this?
I was following your steps, and what I found are: 1. Astra DB Search is not default at Langflow components. 2. Found it at store. 3. Astra DB Search does not have output as in your video, so I can not connect it to the prompt component. Please tell me how to fix it Thank you in advance
It seems to me that your interface looks different from mine. I don't have a core component but several other menus which I don't see in yours. What have I done wrong? Great tutorial, Man.
dude, none of this works. All of these videos seem like they will be a "low/no-code" thing, but it's always b.s. Tons of errors for those non-coders. No thanks.
something has changed since the video, it's taken over 6 hours and the install is still running Downloading wcwidth-0.2.9-py2.py3-none-any.whl (102 kB) |████████████████████████████████| 102 kB 4.2 MB/s
![Felix "Unfair" | [Stray Kids : SKZ-PLAYER]](http://i.ytimg.com/vi/Oswujxm2Ag0/mqdefault.jpg)
What I liked about this is that you start with intent and end with a result, while meticulously going through specifics, even if it is high level.
That’s the goal!
I am a software engineer with looooong experience, but I am super confused about AI and inner workings. I might just start this was to see how things operate at the top and turn this into code on the other side. Make more videos about langflow, very nice content. Thank you!
$10 per step...? This is what makes all the incoming finetunes of Lllama3 70B a game changer... that price will drop to
This is a truly excellent tutorial. It's the first time I've worked with this framework, and the video covers every detail with perfect clarity.
I made some variations, using Ollama with llama3 and Chroma as a vector store, and everything went smoothly thanks to your clear explanations.
Fantastic work!
Awesome!
Holy crap this project looks SO MUCH BETTER than Flowise, from top to bottom.
Perfect , this really opens my mind about the possibilites we can have . keep it up , these type of videos really help
Awesome! Thx for sharing Langflow. The visual approach is my wqy to go. Exactly what I was looking for. And boom, it appeared in my timeline. 😎
TY for the thoroughness in your explanation!
Very good and clear explanation! Thanks a lot for sharing the valuable information!
Very nice overview with a great example! Very well explained! Thanks!
Loved your tutorial, and I did build an chatbot that answers questions related to the Warren Buffet Investment letter.
Thank you
31:43 What can I connect instead of "Record"? In my Langflow, there are other dots such ad Retriever, Search Results, Vector Store in the Astra DB node instead of 'langflow'. Thanks for a good tutorial by the way!
Perfectly executed!
You've earned a subs ❤
And yet another great post Santiago. This is awesome!
Wow man. This is awesome!! El fantastico. Cant wait to have more tutorials, with fully local options this time. 🎉
Excellent video and tutorial! I can't wait to try it out!!!
Very good and easy to follow video, although I could not make it work with Ollama in Docker. Ran into multiple issues with Astra DB as well when using Ollama Embedings failing to create a data set automatically and spilling a number of errors. Granted I am a complete beginner.
Would be cool if there was a follow up tutorial showing how to do the same for local Ollama models and how to address the Ollama hosted in Docker.
I can not find vector search component in lang flow. Could you please tell us Which version are you using? Or alternate solution to it
I am using LangFlow v1.0.6 and there is no "Vector Search" 😞
Vector search is missing, yes. I'm trying to re-use the Astra DB component but with no success...
Always great contents! Really clear and concise demo of langchain. Maybe you can make a video of how to allow the user to dynamically chose a website to ask questions about
the Best video on the topic. thank you
Great content Santiago! Well done and structured! Thanks!
Thanks @underfitted Simple and straight-forward explanation. Do you have any example where you've used the "API Request" under "Data" where based on the question, an orchestrator can call an API endpoint and pass values from the Vector output?
Great tutorial. I'd LOVE to see someone (anyone!) demo how to use OpenAI custom agents via API...not just the vanilla core model(s) API.
I am unable to install and open the langflow in vscode please help with the process...
This is awesome, great content, perfect explanations, so helpful, 1000 thanks Santiago for sharing! 🙏
Thank You Santiago
Thank you for sharing your insights on "Step by step no-code RAG application using Langflow."
Question:
Regarding your use of chunking by 1000 and embedding with a size of 1536 for OpenAI, my question is: If I were to increase the chunking size to something larger, such as 2000, would that present any issues? Would it increase or decrease the performance of the model?
I'm curious to understand the tradeoffs and implications of using a larger chunking size. Does it have an impact on things like model accuracy, training time, or memory usage? I'd appreciate your insights on how the chunking size can affect the overall performance and effectiveness of the machine learning system.
Thank you again for your valuable contributions. I look forward to hearing your thoughts on this follow-up question.
Great video, that's exactly what I'm looking for. Thank you so much for sharing！
Fantastic tutorial!
Awesome session .... I coded along and LangFlow is pretty cool.
You did?!
Amazing video. 1. Will it lookat all the pages of the domain? 2. What if I have pdf files on the website? Do I have to do something else for that?
Hello there, thank you for amazing video, you gave me so much value!! I would like to ask if its possible to somehow create a website application interface for this chatbot, like I dont have much experience with coding so I would love to know a way how can I create a website application interface in some low code platform and then connect it somehow with the langlow chatbot to somewhat resemble ChatGPT platform, I would like to create website RAG application for students in my country. But I am not sure if its even possible, so I would be very happy for your advice. Thank you :)
Awesome, appreciate you're sharing it 👍does Langflow support other inputs from text, for example images, tables, etc. does it have OCR komponent supported too ?
Just curious but does this program have input and outputs for using voice activation and speakers for speaking? Id like to create an ai assistant for my house and like the look and feel of this because its quite si.ilar to the way unreal engine uses blueprints.
Please let me know is it possible to achieve this RAG application by using only the opensource resources
Hi! Thanks for the tutorial. How do you recommend to calculate costs to run the application in production?
Pls fix my issue I want Astra DB search under Vector search
Excellent video very helpful THANK YOU!
Exactly what I was looking for! thank you!
I have upgraded my langflow
Also installed cassandra driver using cmd prompt
Really very well explained
Excellent man! How i can use SQL database for the RAG instead of the URL to provide the context?
Great video @svpino, as always. However, I found that the python code using sample.json doesn't provide accurate results always as we get from the 'Run' using the browser. Even the same question that works well on browser gets a totally unrelated result on Python code when run with the json. Do you suggest anything on this?
I was following your steps, and what I found are:
1. Astra DB Search is not default at Langflow components.
2. Found it at store.
3. Astra DB Search does not have output as in your video, so I can not connect it to the prompt component.
Please tell me how to fix it
Thank you in advance
Unable to install Astra DB driver
in langflow , can we have "RAG + Tool usage" , at the same time.?
How should I make its UI
Did langflow just replaced stackai??! is it just the open source version of StackAI?! It is awesome!
Esto es oro Santiago, muchas gracias!
My input components missing , why is that ?
how can you set it up with Ollama?
I have Astra DB application token and api end point
Does this took work offline? Meaning it doesn't effect our data privacy please?
Really cool, thanks for sharing!
Amazing 🤯🤯🤯, Thank you Santiago
Can I use newer Python version (like 3.11.3)?
I think yes, but you should try
how to use the keys from .env to run the python code if i import your flow json without embedded keys
Use the python-dotenv library.
It seems to me that your interface looks different from mine. I don't have a core component but several other menus which I don't see in yours. What have I done wrong? Great tutorial, Man.
Make sure you run the prerelease version
I need an app where I can transcribe and summarize videos, audio files and from sites like RUclips similar to an app like Eightify or Summarify.
Thank you so much for the great video.
the URL i am working with requires login, how would it be handled in this case?
Can’t do it like this. You need to find a way to authenticate and get access to the information.
Try agents .. crewai
Great tutorial...
可以把你视频通话这里运行吗
Really good!
Nice, thanks
my python version is
3.11.9
Thanks man
Excelent!!
ok, now how do you verify the security of the app? how do you make sure it isn't stealing your customers data?
Use it for POC only .. for production that different
👌👏👏👏👏👏👏👏👏
dude, none of this works. All of these videos seem like they will be a "low/no-code" thing, but it's always b.s. Tons of errors for those non-coders. No thanks.
something has changed since the video, it's taken over 6 hours and the install is still running Downloading wcwidth-0.2.9-py2.py3-none-any.whl (102 kB)
|████████████████████████████████| 102 kB 4.2 MB/s
Awesome explanation!