Make Your RAG Agents Actually Work! (No More Hallucinations)

Поділитися
Вставка

КОМЕНТАРІ • 126

  • @leonvanzyl
    @leonvanzyl  15 днів тому +42

    The plan was to release this video as part of a paid course on agentic agents, but I decided to release it for FREE. You can support my work by hitting the like button and subscribing to my channel 🙏.
    What Flowise topics should I cover next?

    • @BirdManPhil
      @BirdManPhil 15 днів тому

      i need your help are you for hire?

    • @piero957
      @piero957 15 днів тому +4

      Add SQL as an option other than vector and web. Also, add a "user prompt enhancer" option using llama3.2 again. Another interesting option for non-English users would be add input and output translation optional steps, so an user can query let's say in Italian, the agents and the llm then works better in English, and at the end the user can have the reply in his/her language, Italian in this example. Doing all this using a music/movie SQL IMO may grab great viewers attention, both for personal as well as business solutions.

    • @kreak100
      @kreak100 15 днів тому +1

      Great work Leon, love your work up here in Joburg. An interesting use case would be to have agents go try solve a problem for a while and when they find an answer, return the answer. e.g search through a large data base sequentially and find a trend, say large abnormal increase in value, then report that.

    • @kelekcibo9172
      @kelekcibo9172 15 днів тому

      HI Leon,
      we have many Tickets in our Jira Project. I wanted to use your template for having a "JiraAI", who answers questions to tickets, etc.
      I am using self-hosted qdrant. I have an agent , but it always says stuff like, I dont know where to find it, etc.
      I am inserting the tickets via n8n. With Flowise, I only want an agent-/chatflow who answers questions in regard to tickets.
      Which video do you suggest me to watch to implement my scenario?
      Is it possible to use qdrant in the document store?

    • @gianlucagilardi6200
      @gianlucagilardi6200 15 днів тому

      When the feature comes, I cannot wait to see your take on Flowise, Ollama and Graphrag integration....

  • @sanjuburkule
    @sanjuburkule 13 днів тому +4

    Subscribed! Your speed of explanation and not missing steps is important for someone like me. You could have said 'Do so on and so forth' after showing 3 to 2 LLM nodes getting added, but you went ahead and showed it. This is very valiable for my level of people. It allowed me to forward by 10s wherever needed, but that confidence in knowing each step is useful. Thanks for creating this video. Will watch the others you referred here.

    • @leonvanzyl
      @leonvanzyl  13 днів тому

      Thank you for the feedback 🙏

  • @gmcwhinney
    @gmcwhinney 15 днів тому +6

    This is incredible Leon. Thanks for releasing this for free so that we can all learn from your obvious expertise here.

  • @gianlucagilardi6200
    @gianlucagilardi6200 15 днів тому +3

    I am definitely flabbergasted. I started fiddling with Flowise thanks to your videos but this, this is.... unbelievable. I dunno whether you have scraped your projects for paid course(s) but if you have not I am most definitely going to attend (if they have remote attendance, that is :) )

    • @leonvanzyl
      @leonvanzyl  15 днів тому

      Wow, thank you for the feedback 🙏.

  • @DresElMagnifico
    @DresElMagnifico 14 днів тому

    Great tutorial Leon. Thanks for all your work.
    Tutorials like this are great for people trying to build real-life applications. I feel the hardest thing to achieve is to go from a solution that works 75% of the time to one that can reliably perform 95% / 98% of cases against the Wild West of high-volume user inputs.
    It would be great to see more content like this with slightly more advanced techniques and complex scenarios.
    Thanks

  • @SoloJetMan
    @SoloJetMan 15 днів тому

    Thanks for putting this together. I've been debating between several agent platforms. your videos helped me narrowed it to Flowise

    • @leonvanzyl
      @leonvanzyl  15 днів тому

      Yeah, Flowise is super poweful

  • @teemunordman
    @teemunordman 12 днів тому

    Your videos are professional quality. Thank you very much for all Flowise video content!

  • @carlosavelar1300
    @carlosavelar1300 14 днів тому

    Fantastic! Leon, you are the best! Thanks a lot for sharing your knowledge with us!

  • @artur50
    @artur50 15 днів тому

    wow, incredible that you share that stuff with us! GREAT!

  • @ibrahims5636
    @ibrahims5636 7 днів тому

    i have try it, very good result for sure, the only problem right now is how do we integrate memory management, the only available option on this flow is AGENT MEMORY on state, but its sqlite based, the sqlite agent memory are not CPU friendly

  • @santiagoghione9177
    @santiagoghione9177 14 днів тому

    Excelentes tus videos Leon! Muchas gracias

  • @walberc
    @walberc 15 днів тому

    Great video Leon. Thank you so much for this.

  • @AlistairWalsh
    @AlistairWalsh 15 днів тому

    Great stuff! This is exactly the information I needed right now.

  • @MatichekYoutube
    @MatichekYoutube 13 днів тому

    very good tutorial - thank you for hard work 💙

  • @photize
    @photize 15 днів тому

    Excellent as always, opens so many advances thanks .

  • @Francotujk
    @Francotujk 14 днів тому

    Leon, you are the best! It's incredible valuable all you are doing!!
    May be, it could be nice to create more tutorials not just focusing in the Flowise UI, but in creating apps (nextJS, Streamlit, etc) that use Flowise to power the AI-Backend. Because dealing with the API of flowise (for example to upsert files and the read them by filtering, while mantaining the files private is not easy). Also, I don't know if is it possible to use the Agenflows as backend, in that case it could be nice to see a full stack app.
    Obviously not focusing too much in the UI of the app, but in how to connect it to a flowise project.
    Again, thanks for everything you are doing!

  • @OscarTheStrategist
    @OscarTheStrategist 14 днів тому

    Super useful. Thanks for the video! 🔥

  • @DataAI-k9x
    @DataAI-k9x 6 годин тому

    thank you for this.

  • @megaledafrica1080
    @megaledafrica1080 14 днів тому

    Awsome stuff Leon, thank you.

  • @Bu3askoorDXB
    @Bu3askoorDXB 14 днів тому

    Thank you as always, i kept using flowise just because of you and your videos.
    I have noticed a video where potentially using flowise api, a user can create chat flows. It might an ok idea for a video

  • @amroeser
    @amroeser 14 днів тому

    Wow, thank you so much for your videos! It's great that you're sharing your knowledge. Thank you so much! Is it possible to analyze Excel data with tools like the calculator and write a summary in Word of the differences between two Excel files?

    • @leonvanzyl
      @leonvanzyl  14 днів тому

      Absolutely!
      Sounds similar to this video:
      ua-cam.com/video/WRiVMiRI7iU/v-deo.html

  • @fabio-y5q
    @fabio-y5q 14 днів тому

    Hey Leon, really cool and interesting video!☺️
    I have a question:
    How would you implement an agentic workflow that answers questions about a document where the needed information is spread across the entire document? The retriever only gives a certain amount of related content, right? In an example, let's say we have a transcript of an interview, and I want the RAG system to tell me how many and which interview questions appear in this document. Here, the document would need to be completely searched and checked for this information. Would you integrate a loop that goes through all the chunks in the database and adds the information to a state value, or is there a more efficient way over self-reflection to implement this?
    Thank you for your absolutely amazing and interesting videos. It’s a lot of fun to recreate agentic workflows with these structured videos!🎉

  • @VishwanathStudios
    @VishwanathStudios 13 днів тому +1

    Can you do a video on how to use google sheets as a data source for a chat assistant to use directly without any third party tools.

  • @plannedillusion
    @plannedillusion 15 днів тому +1

    Leon for president 👍🏾

  • @T33KS
    @T33KS 14 днів тому

    Thank you! Always the best content on agentic flows and automation. I just have one question that I still can't find a solution for. How would you approach deploying/orchestrating/monitoring these flows? What would be your approach for production once you have multiple flows and duplicates for different clients (also valid question for n8n). Would love your insights on this.

    • @leonvanzyl
      @leonvanzyl  14 днів тому

      This is an excellent topic for a dedicated video.
      I'll try to put some thoughts down, but it's a bit toouch for a comment 😁.
      It all starts with the client's requirements. They might want to host and manage the flows themselves, so you're basically only responsible for setting things up for them.
      Alternatively they might want you to create, monitor and manage everything.
      Hosting: Flowise Cloud is a really solid option for many reasons. You don't have to worry about updating FW or scaling the platform. You can also collaborate with team members on flows.
      You could of course self host it on a VPS / Render, etc. This could be useful if there are some region restrictions.
      I would also recommend adding Langsmith to your flows. That way you can find failures and troubleshoot any issues.
      Health checks: I have an automation on n8n that calls the prediction API on a schedule that will inform me via email if the API is down or some other unwanted behaviour.

    • @T33KS
      @T33KS 14 днів тому

      @leonvanzyl that will be a great video. Especially, in the case of managing multiple instances for different clients. Thanks for taking the time to reply.

  • @magmikefpv
    @magmikefpv 15 днів тому

    Thank you Leon

  • @LemurDrengene
    @LemurDrengene 14 днів тому +1

    What is the drawing software you use in the beginning? And thanks for another great video :-)

    • @leonvanzyl
      @leonvanzyl  14 днів тому +2

      You're welcome 🤗.
      It's called eraser.io

    • @LemurDrengene
      @LemurDrengene 14 днів тому

      @@leonvanzylThx, appreciate it

  • @usiala
    @usiala 13 днів тому

    great video. thanks.

  • @sharankumar31
    @sharankumar31 10 днів тому

    Very nice

  • @AllanBrazute
    @AllanBrazute 15 днів тому

    Nice video, thank you.
    It is kind of working for me. There is one question, the first one I asked to test it, that it can't answer and I don´t understand why:
    - question: What time is it in Australia?
    - websearchLLM: 12:05 AM
    - generateAnswer: Australia is 15 hours ahead of UTC (Coordinated Universal Time) during standard time and 16 hours ahead during daylight saving time. Since you didn't specify which region, I'll - assume it's the Eastern Standard Time zone. In this case, it would be 9:05 AM on a typical day.
    - hallucinationCheck: noResponse
    - final: I'm sorry, but I couldn't find the answer to your question. You could try rephrasing the question and try again?

    • @leonvanzyl
      @leonvanzyl  15 днів тому +1

      Double check that the documents state is correctly being set in the web search tool node.
      You can also try to adjust the system prompt of the generation LLM to guide it in the right direction.

  • @MichaelHubbard
    @MichaelHubbard 14 днів тому

    Thanks you!

    • @leonvanzyl
      @leonvanzyl  14 днів тому

      Thank you very much for the super. Your support help a lot 🙏

  • @micbab-vg2mu
    @micbab-vg2mu 15 днів тому

    Great - I will try it:)

    • @leonvanzyl
      @leonvanzyl  15 днів тому

      Let me know how it went 💪

  • @PyJu80
    @PyJu80 13 днів тому +1

    Hey, im ngl, im a n8n fan, thank f. your code is in json format. One thing im trying to do is use the bolt.forked, or even the pimped version (not sure if i can qutoe, but its on here called ottodev) as an interface and have your workflow used as an http url ollama model. Whats the chances of you looking into this for me?

  • @choijungho1
    @choijungho1 14 днів тому +1

    Very surprising and admirable!
    I loaded the json file to test it locally.
    "Failed to import: Error: exportImportService.importAll - Cannot read properties of undefined (reading 'length')"
    An error occurs. Is there a solution?

    • @changtimwu
      @changtimwu 14 днів тому

      Hi! I got a similar error. My flowise version is flowise@2.1.3

    • @changtimwu
      @changtimwu 11 днів тому

      The error occurs when importing the JSON file under Chatflow instead of using the "Load agent" option in Agentflows. BTW, Flowise should display a more user-friendly error message for this scenario.

  • @krishnankuppaswamy7553
    @krishnankuppaswamy7553 6 днів тому

    Neat and super useful. You have a very good knowledge on this subject and following your contents closely.
    Unable to import the flow on the Flowise Cloud version 2.1.4. I am on trial period and trial started just a while ago.
    Status: 500
    Error: exportImportService.importAll - Cannot read properties of undefined (reading 'length')
    Any hint to make corrections to the json file would be useful.

    • @leonvanzyl
      @leonvanzyl  6 днів тому +1

      Thank you!
      It seems a lot of people are having issues with importing my flow. Investigating

    • @krishnankuppaswamy7553
      @krishnankuppaswamy7553 6 днів тому

      @leonvanzyl Thanks 🙏

  • @szood
    @szood 15 днів тому +1

    can you teach how to set up flowise with a database please?

  •  14 днів тому

    Thanks

    • @leonvanzyl
      @leonvanzyl  14 днів тому

      Thank you very much for the support 🙏

  • @AIbel3arabi
    @AIbel3arabi 3 дні тому

    can you start doing VS Vector Shift tutorials?

  • @tecnopadre
    @tecnopadre 14 днів тому

    Hey Leon, thnks for sharing. When the last LLM that generates the last answer isn't this the way a second LLM generates the answer to the same question for second time? Why wouldn't you take the previous answer if you already validate it with the condition Agent?

    • @leonvanzyl
      @leonvanzyl  14 днів тому +1

      There's no way to do a "pass through" of the generated answer.
      I guess you could change the last system prompt to "Repeat the following words" followed by the generated answer.
      I personally just like to summarise the answer. It won't add anything new,.
      Good question though. Either approach would be fine.

    • @tecnopadre
      @tecnopadre 12 днів тому

      @@leonvanzyl I'm just trying to save inbound and outbound fees. 😅

  • @youtubeccia9276
    @youtubeccia9276 15 днів тому

    excellent stuff

  • @TeamsWorkAI
    @TeamsWorkAI 15 днів тому

    Great !

  • @maniecronje
    @maniecronje 11 днів тому

    Fantasties!

  • @Chasingaxl
    @Chasingaxl 10 днів тому

    Is this Miro that you using for the diagramming?

  • @k1r0vsiii
    @k1r0vsiii 15 днів тому

    you re a flowise gandalf leon

  • @kelekcibo9172
    @kelekcibo9172 15 днів тому

    HI Leon,
    we have many Tickets in our Jira Project. I wanted to use your template for having a "JiraAI", who answers questions to tickets, etc.
    I am using self-hosted qdrant. I have an agent , but it always says stuff like, I dont know where to find it, etc.
    I am inserting the tickets via n8n. With Flowise, I only want an agent-/chatflow who answers questions in regard to tickets.
    Which video do you suggest me to watch to implement my scenario?
    Is it possible to use qdrant in the document store?

  • @EinfachJens-16
    @EinfachJens-16 14 днів тому

    great video. workflow file is not working on my maschine

    • @leonvanzyl
      @leonvanzyl  14 днів тому +1

      What seems to be the issue?

    • @EinfachJens-16
      @EinfachJens-16 9 днів тому

      @@leonvanzyl my fault. load the workflow wrong

  • @Aaron7k
    @Aaron7k 9 днів тому

    Thankss plz do in n8n

  • @revotech5980
    @revotech5980 14 днів тому

    can flowise be used for production ready products? thankyou

    • @leonvanzyl
      @leonvanzyl  14 днів тому

      Absolutely!
      I've got client apps running on Flowise in prod for over a year now. It's super stable

  • @wortellemon2943
    @wortellemon2943 10 днів тому

    after save the project, when i click chat button its automaticly give me a blank white screen

  • @joseignaciodussaillant7031
    @joseignaciodussaillant7031 День тому

    I keep getting "Error buildAgentGraph - Cannot read properties of undefined (reading 'name')" when trying to test the flow. Any tips? havent been able to find the solution anywhere

  • @김정률-i9n
    @김정률-i9n 15 днів тому

    Can I request a course on vector database metadata processing?

  • @김정률-i9n
    @김정률-i9n 15 днів тому

    How to use flowise nowhere else in the world!!!!! COOL!!!

  • @pushingpandas6479
    @pushingpandas6479 15 днів тому

    How install Lama3.2 on a digital ocean server?

    • @leonvanzyl
      @leonvanzyl  15 днів тому

      In that case I'd actually suggest you look at using Groq. It's an awesome platform for using Llama 3.2.
      I have a video on using Groq and Llama on my channel actually.

  • @BirdManPhil
    @BirdManPhil 4 дні тому

    Leon, forgive me if im wrong, but are you not for hire?

    • @leonvanzyl
      @leonvanzyl  4 дні тому

      Send me an email and I'll see if I have capacity 😁

  • @danzreview
    @danzreview 14 днів тому

    GG

  • @MariushAI
    @MariushAI 14 днів тому

    Is it possible to create a similar workflow in n8n?

    • @leonvanzyl
      @leonvanzyl  14 днів тому +2

      Well, the principles that I teach in this video is not specific to Flowise.
      It should be easy to implement in n8n. Maybe I should create an n8n tutorial on this?

    • @MariushAI
      @MariushAI 14 днів тому +1

      ​@@leonvanzyl definitely yes

  • @orangtimur6812
    @orangtimur6812 15 днів тому

    Why my flowise ui different 😢

    • @leonvanzyl
      @leonvanzyl  15 днів тому

      You need to update your Flowise instance maybe 🤔

  • @tonyseno
    @tonyseno 15 днів тому

    Like and subscribe !

  • @plannedillusion
    @plannedillusion 15 днів тому

    🤣 I'm actually building a similar system.

    • @leonvanzyl
      @leonvanzyl  15 днів тому +1

      Great minds think alike?? 🤣

  • @univer6979
    @univer6979 14 днів тому

    If my app needs to work offline without internet connection, in that case can we further improve the response by asking it to search the vector again? I had tried creating a chatbot as per your earlier video ua-cam.com/video/lJOZiRoZNJw/v-deo.html but i could still see some hallucinations and non complete responses even though the answer was there in the vector store. Any thoughts on how to improve it?

  • @DresElMagnifico
    @DresElMagnifico 14 днів тому

    Thanks

    • @leonvanzyl
      @leonvanzyl  14 днів тому

      Thank you very much for the support 🙏

  • @harrykekgmail
    @harrykekgmail 12 днів тому

    Thanks