Видео

The best video series about langchains I've seen on RUclips. Short, concise, and straight to the point. I've learned so much from your video, especially for this one, since I struggled with the concept of RAG for a while. I express my deepest gratitude for your effort and your video. Just a little small tips, it would be even more awesome if you could explain a bit more about what each line of code does, maybe like explain its contexts or the syntax, or maybe why this code is necessary here. Overall, thanks!

If you are coming around to this tutorial today (Flowise version 1.8.1+) both the CRA (Conversational Retrieval Agent) and the OpenAI Tools Agent are being deprecated in favor of NEW Tool Agent. If you are running into errors related to schema invalidation (especially when using the Retrieval tool) OR facing invalidation of a particular regular expression you should be able to simply drop in the Tools Agent, rewire your inputs and off you go.

Leon, I tried installing to Render using the procedure given in the video and received the following error, the fork I am using is up to date as of 06/16/2024: June 16, 2024 at 9:38 AM failed f2a0ffeBugfix/Check for proper thread id and avoid throwing error (#2551) check for proper thread id and avoid throwing error Exited with status 127 while building your code. Read our docs for common ways to troubleshoot your deploy. Also, the Flowise documentation specifies using Docker for the build, however that also failed with the same error. Any help is appreciated, Wayne

Thanx for this ... subscribed!!

Do you think its possible to build a bot like this just using hugging face models ? Thanks for the tips

outstanding video on RAG using LangChain ! Amazing work !!

Fascinating! sparking so many ideas/concepts!

I am loving these tutorial. Yet, I am confused about what happened to the feature of John the pirate once Hope came in, then both of them when the holiday feature was included. It is as if they disappeared rather than took part of the aggregate of functions. Would you clarify? Thank you.

Has anyone got a free solution for using a function calling compatible chat as im getting errors using chatollama function within my agent flow.

Hey Leon, Im here watching this video now as you recommended from another comment to me from another video. Thank you so much this makes sense why you dont need crewai!. I am having some touble using ollama3 instead of openai (I dont have any money to pay for the api credits at the moment). Any tips? Im using the function version of Ollama chat and I've had to set the temperature to 0.1 to get results but the output seems to stop at the product designer and nothing else.

Hi can you pls try some usecases with API Chain?

Hi Leon, I posted a comment yesterday and somehow it disappeard. Besides telling you how good your explanation was, I was wondering what was the advantage of using Flowise for building chatbots when this platform seems to give you many of the cumbersome task you have to manually solve in flowise,already solved, like not having to deal with splitting , embedding, vector databass, etc. Why should I keep working with flowise? I guess there must be a good reason. Your wisdom will be much appreciated!! Thank you!! Ricardo

Leon can you help me? I tried to use pinecone as the vector store, and the retriever tool to connect to the conversational agent, but when i ask anything thats in the vector store i get: "received tool input did not match expected schema", do you know why?

Thanks @leonvanzyl for the very detailed and explanatory playlist. I hit a blocker while following along. I have setup Flowise using docker and so far, its been working fine. But after I added the IfElse function, I get the following error: TypeError: nodeInstance.run is not a function at utilBuildChatflow (/usr/local/lib/node_modules/flowise/dist/utils/buildChatflow.js:253:34)

great video Leon. Is there a way to add crew ai and use it within flowise?

Hey Leon, great video series on Flowise. I'm just starting out with AI and your videos are very helpful. I am a bit stuck however and hoping you can help? Im trying to use the serp api tool to search for an image (anything) but the I'm not getting the image back in the chat window. Is there a way to do this?

Hey Leon, great video series on Flowise. I'm just starting out with AI and your videos are very helpful. I am a bit stuck however and hoping you can help? Im trying to use the serp api tool to search for an image (anything) but the I'm not getting the image back in the chat window. Is there a way to do this?

Nice, Can you allow worker to pick up value entered dynamically from user? for example : put prompt some questions and use the answer from the user

where is the code link? In GitHub langchain i cant find this code

Clear, understandable, and very helpful.. great tutorial. Thank you!

This is much more better than even Udemy courses and other paid courses......I could not understand the langchain docs... But it seems I would be able to call myself an AI developer now ❤❤❤

hello, I already have a well-tuned model that I can use, I have the mxtral8X7B. and for the pricing remains the same, even if I use my model??

Can you attach a tool that can retrieve data from RAG database to an agent worker and then pass the results to another agent worker?

Great stuff a usual. So I was thinking If I wanted to mix custom tools and conversational chain, would it be best to use agents or a mix of IF conditions?

Hey Leon, Can we all integrate the data collector to Google sheets so that the name, email can be seen there?

Super cool. As always. Just a quick query... Why is the temperature 0?

@leonvanzyl awesome content. One thing that I'd mention is 'gpt 3.5 turbo instruct' is not a weak model. But infact "instruct" models are different from "chat" models. Chat models are optimised for chatting flow whereas instruct are optimised to follow instructions, In that case instruct models expect a specific format and little more details in set of instructions that it needs to follow, and often time ends up giving more deterministic output compared to chat models

Your a legend. Thanks mate.

you just earned a sub my friend, great series!!

Great job! as always Leon thank you, would ♥ to see it in Flowise too 🙏

Friend, I'm trying to use the retriever tool, but unfortunately the Tool Agent can't "see" it. It completely ignores the Retriver Tool, even though it is completely configured. And what could it be? And what to do to agree? Thank you very much and congratulations for the content

I've noticed OpenAI stopped to give credits to test for free, then I am using Gemini.

Hey, is there any way in chat output to have a default message in the start of every chat output (Basically for every session_id) ? Thanks a lot in advance !

Thank you very much for the explanation! How can we combine ConversationalRetrieverQAChains with that? They don't use Templates

Great job. Thanks for all of videos. I am learning a lot.

Good morning Leon. Great video, but I have a question. When I terminate my terminal, flowise stops working and I can't communicate with the bot anymore. Is there a way to make it work without terminal being open?

Leon, As usual, it's an excellent video. I use VectorShift for some of my clients. The only real problem is the URL in the embedded code. I would like it to be truly white-label. I would also like to see a similar video for Flowise, especially the recursive web scrapping. Wayne

Leon this is very nice video , thank you

more more more!!!! :) 🥰

nice

Thanks again Leon

I NEED HELP WITH FLOWISE CAN YOU HELP ME BUILD NESTED AGENTS (like if one agent generates a response the other agent should reprompt it to further improve this can go in a loop to get the best quality output)

Nice explanation, please make this type project with langchain js. How to trained model with custom data, vector store and retrieve data. I am searching video for how to trained chatbot using custom data with javascript.

Which would you choose for production if you had to only choose one? Flowise, Langflow or Vectorshift?

Perfect timing on this video! I was tasked with building something like this for a client. This video helps alot.

blessedbrother

For everyone who is getting the error: "Error: Invalid JSON in the IfElse's Input Variables: SyntaxError: Expected ',' or '}' after property value in JSON at position" it's supposed to being fixed in the next releases. Meanwhile you can change a couple of things in order to make it work. Remove the Output Parser in the first LLM Chain (sentiment) and change the Prompt as follows: Determine if the following review is positive. Return "positive" or "negative" only options: {review} Then in the IfElse function, change the if logic to: if ($sentiment == "positive") { return true; } It should work. Good luck! BTW, great playlist, I really enjoy how Leon incorporates concepts step by step. Great work!!

Hi In the Voyage AI Embeddings how can I choose or add different models like voyage-law-2 ? Thanks in advance

Super helpful video @leon.. I want to give the worker some custom data via text file. How can I do that? I did try connecting another chatflow but it stops the main agentflow. Awaiting your response.

Hey I had a question, if you want to do this for a client will you have to ask for their Google Account Password?