Chatting With Your Own Data! Chat, Predict, & Analyze - FlowiseAI Tutorial #6

Подписаться 19 тыс.

Просмотров 23 тыс.

50% 1

#flowiseai #flowise #openai #langchain
We can use Retrieval Chains to create chatbots that are able to answers questions from our own data sources. These can be PDF documents, websites, databases and many more.
We will also look at adding a Pinecone Serverless database in order to store our knowledge base in a persisted database.
🙏 Support My Channel:
Buy me a coffee ☕ : www.buymeacoffee.com/leonvanzyl
📑 Useful Links:
Pinecone: www.pinecone.io/
💬 Chat with Like-Minded Individuals on Discord:
/ discord
🧠 I can build your chatbots for you!
www.cognaitiv.ai
🕒 TIMESTAMPS:
00:00 - Introduction to RAG
00:47 - Retrieval Augmented Retrieval
02:58 - Retrieval Diagram
04:09 - Create Retrieval Chain
05:17 - Adding Buffer Vector Store
06:03 - Add Embeddings
06:28 - Add Document Loaders
07:07 - PDF Document Loader
07:32 - Reason for Chunking
09:03 - Add Text Splitter
10:28 - Upserting Data
11:49 - Cheerio Web Scraper
14:49 - Add Pinecone Serverless
18:03 - Return Source Documents
18:25 - Inject Only Flow
19:06 - Prompting / System Message

Наука

Опубликовано:

27 июн 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 218

@leonvanzyl 4 месяца назад

Hope you guys enjoy this video! RAG is without a doubt one of the most important features of Langchain and Flowise. Please hit the like button and remember to subscribe. This greatly supports my channel.

@insanemedia786 4 месяца назад

please make a vedio product recommendation bot using pinecone

@dax8it 4 месяца назад

This video tutorial series is the best AI workflow/high level concept instructional I have experienced. I've worked in bits and pieces on all these things, with many of these tools, but visualizing everything "together" makes this an exceptional tutorial. Thank you for sharing this. I am officially a flowise fan now.

@beemerrox 2 месяца назад

I have to agree. This is THE best tutorial series thus far. Thank you a TON for sharing this.

@elanaestheticswithdrjaco8547 4 месяца назад

Thank You, Leon, for making yet another excellent video!

@leonvanzyl 4 месяца назад

Thank you!

@beemerrox 2 месяца назад

Just have to give a BIG THANKS! Im following Leon on all the socials because this is GOLDEN. Doing everything and every step from every video.

@envivomedia 3 месяца назад

Your tutorials are gold Leon, thank you! This stuff is so clear and helpful. I'm devouring all of it and can't wait for more!

@leonvanzyl 3 месяца назад

Thank you 😊

@gimme890 24 дня назад

Incredibly helpful. Many thanks!

@joaobranco6419 4 месяца назад

Awesome tutorial, thanks so much!

@JonBrookes 4 месяца назад

This is most informative and useful. The rate at which you bring it up to speed is really something and RAG is the killer app feature I think. I am heartily impressed with flowise now. I was admittedly something of a sceptic having worked on other 'no code / low code' solutions in the past but you've made this easy to follow and implement and I can see it working for myself. I've looked into docker implementation with flowise which also seems very sound. Many other use cases are now open to us. Thank you Leon.

@leonvanzyl 4 месяца назад

Thank you for the feedback!

@cyanrays8177 2 дня назад

Thank you sir for all of this!

@ward_jl 4 месяца назад

Another great tutorial. The pairing of topics on Flowise and Langchain is highly beneficial. Understanding Flowise first showcases the possibilities and allows for quick prototyping. Diving into coding after that enhances both my comprehension and execution. Huge fan of your work!

@leonvanzyl 4 месяца назад

Appreciate you. Thank you for the feedback 🙏

@CL-uz5ck 2 месяца назад

Hi Leon, thank you for all of your videos - so helpful. I've liked and subscribed and even watch ads to help support your channel!!

@leonvanzyl 2 месяца назад

Thank you 😊

@arthuraquino8356 4 месяца назад

Your content is always amazing!!!

@leonvanzyl 4 месяца назад

Thank you very much 🙏

@ahmedkhalidak4515 4 месяца назад

Thank You, Leon

@leonvanzyl 4 месяца назад

You're welcome 🤗

@sakarsr 20 дней назад

Thank, very informative to make my own chat on my product. Have a nice day and good health 😄

@mikew2883 27 дней назад

Great tutorial! 👍

@claudi7009 4 месяца назад

Great video and better series, keep on doing them.

@leonvanzyl 4 месяца назад

Thank you!

@senorchavo5572 3 месяца назад

dude! thank you for the content you put out...keep it coming...i have learned so much from your content.

@leonvanzyl 3 месяца назад

You're welcome

@senorchavo5572 3 месяца назад

@@leonvanzyl quick question..for larger pdfs im having trouble for it grasping the full document, is that related to the recursive character splitter?...as you say play with the parameters. i can have a 26 page document I want to injest...what would be the best way to to chunk and upsert that for the best result

@ev_casey 4 месяца назад

Yes, love the videos Leon! Keep up the great work. Would love to see your videos progress into agents calling multiple retrieval threads and tools using chain selection! Not many good resources out there on that! I know you've done in in python and js, but would love to see the Flowise equivalent!

@leonvanzyl 4 месяца назад

Will do 👍

@SRProductionsdigtal 4 месяца назад

Thank you so much for your videos! I'm a no code founder and I am always looking for videos that can help me bring solutions to my client base with my minimal coding experience your videos are highly appreciated!

@leonvanzyl 4 месяца назад

You're welcome 🤗

@RolandoLopezNieto 2 месяца назад

Top notch videos sir

@leonvanzyl 2 месяца назад

Glad you enjoyed it

@omarabutouq2755 4 месяца назад

Let's goooooo

@leonvanzyl 4 месяца назад

💪

@Ahmedgamal-qf9gy 4 месяца назад

Thank you Leon, I hope you consider creating a video demonstrating how to build a bot capable of responding to queries from users by fetching data from Google Analytics, such as clicks and views, and so on. I am pretty sure it's a good use case as every business has a Google Analytics account and this bot will be helpful to create for almost everyone watching who has a website. This would greatly enhance understanding of Flowise's capabilities, as it will be covering many aspects it offers. like custom tools, fetching multiple types of data, interaction with 3rd party APIs, and so on. This would serve as a comprehensive resource for creating advanced chatbot applications using flowise.

@leonvanzyl 4 месяца назад

Thank you. I like this example 👍

@christianhaefner 3 месяца назад

Thanks for that video! I was wondering how to update points in Pinecone. I am trying do upsert blogposts to my vector database. Once they change, the points should also be update. In the current setup, everytime I re-run the upserting process, new vectors will be created in addition to the old ones (= duplicate data, from which some is old).

@ubaisalih2987 4 месяца назад

this is really awsome especially Cheerio web scraper . you have already shared a video about using llama as an LLM , and it will be great to share a video about using llama as an embedding as well , so we will have an end to end open scouse chatbot

@leonvanzyl 4 месяца назад

The embedding side of it remains the same 👍

@ubaisalih2987 4 месяца назад

@@leonvanzyl Ollama embedding node on the Flowise requires a base URL and the model , can you please let me know how to get the base URL of Ollama from Replicate ?

@dordekodzic6279 3 месяца назад

Thank you Leon for all your hard work and time invested in educating others! Couple of questions: 1) Is there a possibility to have end user upload documents to chat? 2) Is there a way of adding metadata dynamically when upsering documents? For example, to add the document title as metadata, so the vectors can be filtered after it later in the vector database.

@leonvanzyl 3 месяца назад

You're welcome! Check out the video on using the API 👍

@sadyaz64 4 месяца назад

It is the most important subject that interests me. Thanks.if in one of your videos, you show us the use in flowise the use of an llm other than open ai. that would be great

@leonvanzyl 4 месяца назад

We will have a look at using other models as well. In practice, OpenAI is without a doubt the most commonly used model in industry, therefore I'll be using it primarily. Other topics, like function calling, require OpenAI as well 👍

@johnnythegeek 4 месяца назад

Hi Leon, great video as always. So do I create different upserts for each type of document loader using the same pinecone index and then create the retrieving chatbot using the same pinecone index for the retrieval flow?

@leonvanzyl 4 месяца назад

Correct. You will not lose the data in the database when you upsert with a different uploader.

@WayneBruton 3 месяца назад

I Leon, quick question, using the pinecone vector store there is a dropdown at the bottom, default is pinecone retriever and the other option is pinecone vector store. Am I correct in assuming that I use the vector store option to upsert and the retriever option afterwards to retrieve data?

@Myuker 3 месяца назад

Ultra useful for noobs in this part of IT!

@leonvanzyl 3 месяца назад

Glad I could help ☺️

@Chasingaxl 22 дня назад

Great video as always. I get a memory issue, which I am assuming is due to the fact that I am on the lowest render server plan. Seems to happen when I try to upset more than a couple url links that have been scraped.

@kasraasghari4913 4 месяца назад

Your tutorials are absolutely awesome. A question, can one build a kind of an Autogen i.e. a multi-agent framework using flow-wise? I personally would love to see that kind of an implementation?

@leonvanzyl 4 месяца назад

Thank you! I think Flowise might be the wrong tool for that situation. Collaborative agents is not really something Flowise can do at this stage.

@bamdee1184 2 месяца назад

@leonvanzyl, first and foremost, thanks, mate, for all the content you produce. Quick question, I'm getting a message when I run the chat that the "Ending node must be either a Chain or Agent". I followed the video exactly how you did it but having errors. Hope you can help.

@leonvanzyl 2 месяца назад

You're welcome 🤗. That's correct, the ending node should always be either a chain or agent. Check out the Getting Started video (first video in the series). It's very hard to say what the issue could be without seeing your flow.

@nitzantal5365 3 месяца назад

Wow what a great video Leon, you're a rock start ⭐ I have small question, does flowise embed chatbot (react) supports displaying images? I've seen it knows to generate links if I'm providing embeddings with links and on some of your videos I've seen it knows to display JSON structures nicely. Are there any other UI components flowise knows to display over the bot? Thanks

@leonvanzyl 3 месяца назад

Thank you ☺️. Assuming you're using a model like Dall-E or an open source model, you will typically only receive a URL. However, you could prime the bot via the system message to return URLs as markdown and display the images.

@nitzantal5365 3 месяца назад

@@leonvanzyl thanks Can you please guide me or send some documentation how could I achieve that displaying an image via system message?

@JoaquinTorroba 4 месяца назад

Great content Leon, quick question: with the increasing context windows of LLMs, will RAG still be needed?

@leonvanzyl 4 месяца назад

Absolutely, for numerous reasons. Larger prompt will incur massive costs, degrade performance and decrease accuracy.

@JoaquinTorroba 4 месяца назад

Interesting @@leonvanzyl. Also, as Dan Shipper wrote: "Retrieval will still be used to figure out which 1 million tokens are the most relevant, rather than what it's used for now: to find which 1,000 tokens are the most relevant".

@4850545 4 месяца назад

Great example, thank you Leon! I find the example with crawling via Cherio and the sitemap super exciting. Do you think you can also cover a large website with >10,000 URLs with this? And do you see an option to include several websites at once? Thank you!

@leonvanzyl 4 месяца назад

Thank you! For large websites I recommend creating a CSV extract from the database and to upload that CSV instead. Scraping large websites are a terrible idea 😁

@dmt15 4 месяца назад

thanks for your tutorial! Will there be another one for RAG but using LlamaIndex?

@leonvanzyl 4 месяца назад

I'll create a seperate crash course on Flowise Llama Index once it's out of beta 👍

@jaystanio 3 месяца назад

What is the best practice for deleting a document and updating the databases so that the flowise bot is accurate with the info it gives to the user?

@Danilo360yt 3 месяца назад

i prefer using claude-sonnet instead of GPT-3.5. my question is, its possible to use an openAI embedding with sonnet chat model ?? because i can not see any embedding model of claude anthropic. Thank you in advance Leon !! amazing videos

@leonvanzyl 3 месяца назад

I've also been playing with Claude lately and I'm really impressed. Going to make a dedicated Flowise and Claude video with RAG 👍.

@ricardofernandez2286 Месяц назад

Hi Leon, great tutorial!! Just to cover a slightly different scenario, how do you manage not to duplicate records when running multiple times the load process on vector databases like for example Chromadb? Thank you!!

@leonvanzyl Месяц назад

You can use Record Manager to prevent duplicates. ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-sNk6-ISi7i4.html

@DustinGood333 4 месяца назад

Loving this channel! My goal is to scrape my municipal website and offer a chatbot to any of the local organizations in my community. Do I have to use node to use cherrio to scrape an entire municipal webpage?

@leonvanzyl 4 месяца назад

You could definitely use Cheerio for that.

@user-lc2dh6zx5p 2 месяца назад

how do you get it to work with existing data in a vector db? I tried recreating the same node graph, and when asking the chatbot, it tells me it doesn´t know the answer(the default response if there is no context), yet from what i can see from the return source documents option, it does retrieve the right chunks, it just doesn´t seem to be able to read them? if i ask it to just print {context} as a response, it will give me the chunks, but it won´t be able to answer despite them being there

@userbaed Месяц назад

Is there a way to add a Conversational agent to this template with Serp API, so the bot can look online informational relevant to a file uploaded?

@Francotujk 4 месяца назад

Another great video like always! Very helpful! If I want to allow final users to “upsert” their pdfs, should I leave empty the file in the flowise node? And also, the API for upserting is what I should use to upload the files? How then the app “knows” which files to answer questions? (Because there will be files by a lot of users) I think it could be great a tutorial for the upsert and read of files, with a cloud hosted app, and using the responses to power a web app for final users. Thanks for eveything!

@leonvanzyl 4 месяца назад

Thank you for the message. This sounds like a great idea for a tutorial. I will cover API endpoints in this series, so maybe that will help you. As for dealing with multiple users, you can store documents under different "namespaces", so you could specify a namespace per user, and the conversation can then be limited to only answer from documents filtered on the user's namespace.

@Francotujk 4 месяца назад

@@leonvanzyl Thanks for your answer! I will look at namespaces. Waiting for the API endpoints video also! (if you can include the API for Upsert, and then read a PDF I would love it!) Thanks for all your valuable content!

@antoniomarf Месяц назад

massa demais

@IliasSeddik 22 дня назад

Hi , Thanks for your course... I've tried to use a pdf as data source and it worked perfectly for the text inside, but neither my pdf loader nor my vector store are able to get the url from the links in the PDF, any idea ?

@KaranChecker 2 месяца назад

Hi can you help with learning of automating the setup of a chatbot using flowwise for a self service SaaS product??

@user-zf1ur9lh7o Месяц назад

I am really grateful for the knowledge you give. It is really wonderful. Thank you. I noticed that this tutorial doesn't work on render but it works on my desktop. Is there a way that I can configure it to work on Render Cloud?? I appreciate your help. Thanks

@leonvanzyl Месяц назад

Thank you for the kind words. It should work on Render. What issue are you having?

@bambanx Месяц назад

Hello León, its possible read local files for example a code project without clicking upsert each time we do a change on the code, also the possibility flowise write ob this files? Also why no use free vector store like chroma? Thanks you

@jiuvk8393 3 месяца назад

Hello, I'm having 2 issues I don't know how to fix it or what to change: 1: I ask a specific question and it answers way too many things instead of just the specific question and 2: it starts asking and answering questions by itself not even related to what I specifically asked .

@pedroosorio7466 2 месяца назад

Hello. How to create a rag using a file that has sensitive information? Can I use flowise and the openai model?

@Organizational_Psychology_PhD 4 месяца назад

Love your work. I am struggling a bit with understanding the new "Additional Parameters" section of the node you demoed - Conversational Retrieval QA Chain. What are these variables they are forcing me to set about? We didn't need to define variables before. Thanks!

@leonvanzyl 4 месяца назад

I'm guessing you're referring to the chat history and context variables. Try not to remove those when changing the system message 😁. Chat history is used to keep track of the conversation history. Context, as explained in this video, is a placeholder for the context.

@Organizational_Psychology_PhD 4 месяца назад

@@leonvanzyl you guessed right. Thank you. So just to be clear - the default text work well as is - right? I am picky about my system messages. I still feel like I need to understand this new feature better😀

@user-vc9xt6tz7m 2 месяца назад

Thank you for your tutorial! I built an internal chatbot that uses Confluence documentation as a data source. One question that I have, though. Since technical documentation is never comprehensive enough to answer all the questions, I would like to add a feedback loop to my chatbot. In other words, I want the user to ask a question, get an answer, and then be able to give a "correct answer" that should be "learned" by the model itself (not just to be kept in session context - another user asking a similar question should receive the updated, corrected answer already). Is it possible to do this with Flowise? Do you have any valuable references or another video on this topic?

@dandrevs 4 месяца назад

This looks amazing. Can we replace commercial services with open source and local storage and databases for long term memory?

@leonvanzyl 4 месяца назад

You can definitely use open source alternatives. You won't really "save money" by doing so, due to hosting / infrastructure costs and the headache of dealing with scalability, updates and support yourself. I've made a point if suggesting the most affordable solutions in this series.

@dandrevs 4 месяца назад

@@leonvanzylThanks for replying. I agree. I was leaning more towards deployed this locally on my machine for learning purposes. Would that be a potential video topic in the future?

@jasonoffenburg 2 месяца назад

Many thanks for the excellent tutorial. I have set up the automation and noticed that the chunks repeat themselves and only the time is changing. I'm not a programmer so I'm wondering if this is normal or if it's using up unnecessary capacity and how I can deal with it. ------- Debbuger example: [chain/end] [1:chain:RunnableSequence > 13:chain:RunnableSequence] [25.08s] Exiting Chain run with output: { XY [chain/end] [1:chain:RunnableSequence] [26.96s] Exiting Chain run with output: { XY (THE SAME CHUNK) (... / it sends the same chunk up to four times)

@YitzhakErezKarat 3 месяца назад

Thank you for the professional and informative video. Could you please let me know if there is an option after updating Pinecone to add new information without re-starting the whole process?

@leonvanzyl 3 месяца назад

You can add new information whenever you want. No need to restart the process.

@YitzhakErezKarat 3 месяца назад

Thank you for your quick response. If I understand correctly, the new information is simply uploaded to the same index in pinecone. But is there a way to detect or track a change in the website so that only the new pages that have disappeared will be scanned and uploaded to the index in pinecone.@@leonvanzyl

@bastianstrauss 4 месяца назад

Thanks for this great tutorial. With Pinecone, however, I have not yet understood how I can delete parts of the vector store. Is there a possibility with Flowise like upsert Reverse?

@leonvanzyl 4 месяца назад

Each record contains metadata. Flowise doesn't allow for deleting data, but your application can delete all entries based on the metadata.

@rubenkhachaturov3309 3 месяца назад

I followed a guide for retrieving documents from Confluence. After the activation process concludes, the system displays buttons next to the text. Clicking any of these buttons triggers a popup within Flowise, showcasing information in JSON format. This popup also includes a URL, which seems to indicate the source page of the information. However, the URL is presented in a format that emphasizes the ending, showing from which page the information was extracted. How can I adjust the settings to obtain URL links in the format shown in your example?

@Machiuka 4 месяца назад

Very informative tutorial. Could you make one that use HuggingFace instead of OpenAI? Thank you for posting!

@leonvanzyl 4 месяца назад

Thank you. I'll definitely create a video on how to use open source models in this series. Take note that most of the advanced features only work with OpenAI, and in practice OpenAI is extremely important when creating projects for clients.

@TienPham-rf3bg 4 месяца назад

Your videos are rewarding,I've learned a lot.Can I ask if I can use nodes so that chatbots can both use my document and custom tool to retrieve user information via webhooks and save it to google sheet?I tried using the Open Assistant but the data was too misleading compared to the data in my document.Please help me, Thanks a lot!

@leonvanzyl 4 месяца назад

Thank you for the feedback. I need a better understanding of your requirement, but it seems like something that should be achievable with Agents. We haven't covered agents in this series yet, but maybe once we go over tools and retrieval agents, it would help you

@mohammd100 4 месяца назад

this is amazing work💘 please don't take forever to recored the rest of the tutorials 😁. I am facing some challenges when I upload Arabic documents specialy from PDF do you have any suggestions about that thanks inadvance

@leonvanzyl 4 месяца назад

Hahaha, these videos unfortunately take time to research, record and edit 😁

@mohammd100 4 месяца назад

@@leonvanzyl do you have any ideas about the language issues or it must be working well anyway?

@raposa158 Месяц назад

Hey man, great video. But u can explain about tokens. On this case, this big answers, how much tokens u needed? I’ve need something than I reduce the consume of tokens

@leonvanzyl Месяц назад

I highly recommend using a monitoring platform like LangSmith. There is a video on it later on in the series. ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-QghlUiQHMbw.html You can use those tools to see how many tokens are used by your flows and you can then make adjustments accordingly. You can set the maximum amount of tokens using the Additional Settings on the LLMs.

@WayneBruton 4 месяца назад

Hi Leon, Quick question, I see you have chosen the in-memory Vector store from vector stores new. My Vector Stores New is actually empty and only the deprecated vector stores are available. I did update Flowise from your first video in this series. Is there a very recent update perhaps?

@leonvanzyl 4 месяца назад

That's really strange. Try upgrading perhaps.

@WayneBruton 4 месяца назад

@@leonvanzyl Thanks Leon, that did the trick, I also still had it installed globally as well so tossed that too.

@arthuraquino8356 4 месяца назад

In your last flowise video you used upstash for memory where it creates as if it were a thread. To my question is when what is stored becomes greater than the context limit of the model used how to act?

@leonvanzyl 4 месяца назад

Hi there, I'm not sure I understand the question. Conversation memory and knowledge bases are unrelated. Apologies, maybe you could rephrase the question? I honestly want to assist.

@arthuraquino8356 4 месяца назад

@@leonvanzyl We have the conversation memory and the vector database data right? Isn't the conversation memory similar to the openai assistant threads? My question is whether in a conversation in which I am saving the data in Upstash and the amount exceeds the model's context limit, the model would not cause truncation to retrieve information?

@beppesan 3 месяца назад

Amazing video. Can I add a pinecone retrive to the OpenAI ASSISTANT?

@leonvanzyl 3 месяца назад

Unfortunately not. OpenAI Assistant uses a vector store that belongs to OpenAI. You're better off using the instructions in this series if you want to create your own assistant using Pinecone.

@beppesan 3 месяца назад

@@leonvanzyl hi, i tried to connect the Multi Retrieval QA chain to a chain tool, connected directly to the Assistant. It work! Thanks

@marcuslucasjb 22 дня назад

Is it possible to do it using API Loader instead of PdfFile? In this case the API Loader will return an json

@drtunmyatwin 3 месяца назад

it show error when I click upsert button , although I exactly what you do , I upload a pdf file from my harddrive connect to my pc. Please help me solve the problem

@leonvanzyl 3 месяца назад

What's the error?

@drtunmyatwin 2 месяца назад

@@leonvanzyl it show pinecone authorization error. Your api key are rejected and check your cofiguration. I put working upadate api key for openai and pinecone what is wrong with it

@drtunmyatwin 2 месяца назад

@@leonvanzyl I am building retriveal chatbot using openai api key and pinecone api key as in your video

@stanTrX Месяц назад

Is it better than autogen studio?

@kaisshili2327 4 месяца назад

Hello @leonvanzyl. Do you know how to integrate rerank retriever like the cohore ? thank you a lot

@leonvanzyl 4 месяца назад

I haven't tried yet actually. Sounds interesting! You think it's worth a tutorial?

@AssassinUK 4 месяца назад

Great video as always .. How would I allow the user to upload a document? Is this possible?

@leonvanzyl 4 месяца назад

Thank you. I assume that you're referring a user using your app, and not Flowise directly. It's possible to pass a file using the Flowise API. I'll definitely cover the API in this series.

@BlackBification 3 месяца назад

If I try to use Ollama with Llama 2 and Ollama Embeddings, it get this error when i upsert: "Request to Ollama server failed: 500 Internal Server Error" Any tips? Thx

@mohitpatil2236 2 месяца назад

how u got the link for side map ?

@MariushAI 4 месяца назад

Will you do a tutorial on LlamaIndex?

@leonvanzyl 4 месяца назад

Yes! Researching it now and figuring out a lesson structure.

@user-sz7op9wn4y 2 месяца назад

Maybe a dumb question, but what I do not understand is how you keep data up-to-date. Lets say I use Flowise to take a Airtable database put it in Pinecone to make it "smart", so I can chat with it. How do I keep the database up to date, how can I manage, that when something is updated in the airtable, it is being changed in the vectored database? If I press upsert data just gets Re-added, so not replaced but adds the data AGAIN. How does this work?

@dhmkkk 4 месяца назад

Hey Leon Great video. I tried this on my own but instead i am using HuggingFace embeddings and Singlestore as my vectorstore and for some reason it just generates empty url string. Is it because theres an issue in using HuggingFace embeddings?

@leonvanzyl 4 месяца назад

Hard to say. I highly encourage you to use OpenAI if you're following along 😁

@MortezaTaheri 4 месяца назад

Thank you for the video, is it possible to upsert multiple pdf Or combination of multiple files like docx pdf txt

@leonvanzyl 4 месяца назад

Yes. I do mention in the video that you can upload multiple files.

@ritaverissimo1720 2 месяца назад

Hi @Leon, on FlowiseAI website it's mentioned Digital Ocean as deployment options. My question is how could I add my AI assistant created in FlowiseAI into my github repo that has my website structure. Also, is it possible at some point to download docs in pdf format (for example) and inject them somewherelse for example in a "my user account" that I have created in my repo? Thanks!

@leonvanzyl 2 месяца назад

Check out my web embed video on adding the chatbot to any website. I don't have a video on deploying to digital ocean but the Flowise docs should guide you through the process.

@ritaverissimo1720 2 месяца назад

@@leonvanzyl Sure, I'll take a look at that video. If I have any other questions, I'll ask them there ;) Thx!

@WayneBruton 4 месяца назад

Hi Leon, quick question, When I moved to pinecone, the quality of responses deteriorated quite a lot compared to the local memory. I have tried playing with the splitting but no change. I am using a pdf doc. Would a text or word doc perhaps be better?

@leonvanzyl 4 месяца назад

Performance actually gets better over time as the service scales. I forgot to mention that in the video :-D .

@ano0810 2 месяца назад

hello @Leon have you even encountered a use case where you want to write files from a render web service and then read those files from a different render web service? Currently render does not allow for access of shared drives, so I wonder if you have encountered and solved this problem?

@leonvanzyl 2 месяца назад

I typically use AWS S3 for my projects, especially when file sharing should be possible.

@ano0810 2 месяца назад

@@leonvanzyl Thanks!

@bassamel-ashkar4005 4 месяца назад

Leon, your work is always amazing! I've hit a snag though. I want the AI to think more creatively, like ChatGPT. Right now, it's stuck just answering questions based on specific documents. For example, I gave it docs regarding Flowise, I asked what is output parser and it gave a correct response, I then asked what are the benefits of using an output parser in AI apps, it couldn't give an answer. How can I fix this and get it thinking more broadly and use the information to assist me better beyond just retrieving the information?

@leonvanzyl 4 месяца назад

Hey there. Simply adjust the system message. By default, it instructs the model to strictly answer from the context.

@bassamel-ashkar4005 4 месяца назад

Just tried this. Yeah, it works! but not perfect. it's like the assistant is sort of replying only from the information that it retrieves per single query and not the overall project and its overall knowledge of external public knowledge. for example, the assistant has good knowledge of flowise but it wouldn't apply its own knowledge if I asked it how to create a certain flow for a certain use case. Please let me know what controls this part to make it smarter. @@leonvanzyl

@abiolasamuel8092 4 месяца назад

Is Microsoft AutoGen and Langchain AutoGPT the same? Can you do a quick demo in Flowise? Thank you.

@leonvanzyl 4 месяца назад

AutoGPT has changed a lot over the past year so I'm not exactly sure what it's capabilities are. The version of AGPT that I remember was very different to AutoGen. AutoGPT is an agent tool, where AutoGen is a developer framework for building collaborative agent solutions.

@andreaskoop 4 месяца назад

Thanks for sharing! How to extend the chatbot so endusers can upload PDF files for upserting…? Is it possible?

@leonvanzyl 4 месяца назад

Absolutely. You could call the API endpoint from your application

@andreaskoop 4 месяца назад

@@leonvanzylgreat, good to know. thank you!

@garydotzlaw311 4 месяца назад

Excellent video! How come I can't hookup a "Vector Store Retriever" to the "Conversational Retrieval QA Chain", but I can hook it up to "Multi Retrieval QA Chain"? Both say they accept "Vector Store Retriever". I don't see any way to use a prompt template with "Multi Retrieval QA Chain", so that is why I wanted to try using the conversational retrieval chain.

@leonvanzyl 4 месяца назад

Thank you for the feedback 👍.

@dmitryutlik 4 месяца назад

Thank You, Leon, Can you make a video on how to set up such bots for online shops where there are a lot of different products, I can not get the bot set up correctly. Because of the large number of products, it gets confused in the articles (and for the shop is important accuracy) confused in the cost and so on. Perhaps it is necessary to prepare data in a special way. I will be glad to any help.

@leonvanzyl 4 месяца назад

Surely the sitemap option would work for you?

@dmitryutlik 4 месяца назад

@@leonvanzyl I don't know but thanks for the advice, I'll try using the sitemap, can I email you Leon in case of difficulties?

@sanava_ai 4 месяца назад

Is there a way to add the urls to the document loader manually? I need only 30 urls from a website with over 200 urls

@leonvanzyl 4 месяца назад

At this stage it seems we can only crawl one URL at a time.

@jamesarnold22 28 дней назад

These tutorials are great, but is anyone else finding the bot just struggles with the PDF? It's really poor for me. I've also found "how can i deploy flowise to render?" doesn't work but "How can I deploy Flowise to Render?" does, so it seems you have to be very precise for this to work which isn't realistic..? Unless I'm missing something? "version": "1.8.0",

@mikelewis1166 4 месяца назад

For some reason my LCEL page vector count was 5 when you had 370 in pinecone. I have my chunk size and overlap set the same. Still worked but confusing.

@leonvanzyl 4 месяца назад

Haha, don't worry about it. I actually upserted a few things during recording, which were edited out 😁

@sanava_ai 4 месяца назад

How can we make changes to the vector data base? For example, when information on a website have changed..

@fengshi9462 3 месяца назад

Hi, have you ever solve this question? I need to. automatically update my knowledge base. too😂

@sanava_ai 3 месяца назад

No I just create a new index @@fengshi9462

@stevewarby12 4 месяца назад

Hi Leon. I have adapted the chatFlow to scrape another site using the Scrape XML Sitemap method. In the URL I have entered the sitemap url and used fetch links button. This brings back a list of urls. I then press save. I then save the chatFlow. When I use upsert I get the error 'No Relative Links Found'. What piece of the jig saw am I missing please ?

@leonvanzyl 4 месяца назад

Did you select "scrape XML" from the dropdown? Think that's what it's called

@meister4831 3 месяца назад

I implemented this and built a RAG application that works like a charm thanks!! But now I have the problem that I want to add a custom tool to it but it seems I have to decide whether to build my flow EITHER using the Conversational Retrieval QA chain OR a node such as OpenAI Tool Agent that will allow me to use my tool. Sorry for asking you a technical question like this here but I didn't find an answer anywhere else. Is there a way to keep the Conversational Retrieval QA Chain and enable the flow to use custom tools at the same time? Or would I really have to switch to a Retriever Tool/Custom Tool for an Agent Node...? What is the best way to build a flow that will retrieve well in Pinecone AND make intelligent use of tools? Thanks!

@leonvanzyl 3 месяца назад

Only agent nodes can call tools. The OpenAI Tools Agent would be perfect for you. Check out my agents video to see how you can add RAG to the agent along with tools

@meister4831 3 месяца назад

@@leonvanzyl Will do, thanks!

@meister4831 2 месяца назад

@@leonvanzyl I'm a pro member of your channel now :) I found that the retrieval results of an OpenAI Tool Agent with a Retriever Tool are inferior to the response quality of the Conversational Retrievel QA Chain. My RAG flow is based on the web-scrape-qna template by Flowise so I use HTML Splitter, Cheerio, Pinecone and Conversational Retrieval QA Chain. I use a seperate flow to upsert to Pinecone and I don't use Redis at the moment. The problem is now that when I return source documents to the chat, they show up in the chat window with their relative URLs instead of the page title as is nicely seen in the screenshot in Flowise's web-scrape-qna example. When I upsert the way they show it I don't even have a metadata key in Pinecone that contains the page title... I even added a title metadata key in Pinecone with a python script but now I don't know how I get Flowise to use these titles when displaying source documents. Do you have any idea why that is? Many thanks!!

@roegger 29 дней назад

Hi Leon. I currently have the situation that I need two knowledge-bases. First I have some static data (Knowledge in for Folder Loader) and embedded to Pinecone. But I now also have some dynamic data (events) that needs to be crawled on a daily basis from a website and be updated. (so outdated infos get removed, new crawled infos can be retrieved). Do you have a solution for that? Thank you - Roman

@leonvanzyl 29 дней назад

Flowise does not have a solution for periodically updating the Vector Store (like your example of scraping the website on daily basis). However, they do offer an API that you can call from outside of Flowise to trigger the Upsert. So what you could do is to set up a Cron job that runs the Upsert API daily. This might be a good tip to include in the next Flowise Tips and Tricks video. You can set up cron jobs for free using cron-job.org.

@BorisHrzenjak 4 месяца назад

So I was following the tutorial up to a point where I had to press the green button for upsert vector store and I don't have the green button :) What's up with that?

@leonvanzyl 4 месяца назад

Upgrade your version of Flowise. Remember to save the chatflow.

@jiuvk8393 3 месяца назад

sorry I keep getting this errors and I look and online and there's nothing about them, now I'm getting "Error: overloaded" when trying to chat or trying to upsert

@MerlinStark-ig5lt Месяц назад

which embedding should I use if i want to use Claude as my Chat Model? :) Can anybody help me?

@leonvanzyl Месяц назад

Voyage AI seems to be the best option for Claude. docs.anthropic.com/claude/docs/embeddings

@meister4831 2 месяца назад

I found that the retrieval results of an OpenAI Tool Agent with a Retriever Tool are inferior to the response quality of the Conversational Retrievel QA Chain. My RAG flow is based on the web-scrape-qna template by Flowise so I use HTML Splitter, Cheerio, Pinecone and Conversational Retrieval QA Chain. The problem is now that when I return source documents to the chat, they show up in the chat window with their relative URLs instead of the page title as is nicely seen in the screenshot in Flowise's web-scrape-qna example. I don't know how I get Flowise to use these titles when displaying source documents. Do you have any idea why that is? Many thanks!!

@leonvanzyl 2 месяца назад

That's a good point. I noticed that as well. The Tools Agent node is relatively new so it's possible that it's a bug. I'll pass your message on to the Flowise team as well.

@meister4831 2 месяца назад

@@leonvanzyl I hope you pass the message on not only about the retrieval quality but especially about the source title problem! And please note that I have that problem with the source titles with the Conversational Retrieval QA Chain, not the OpenAI Tool Agent/Retriever Tool. Many thanks!❤

@MD-qh6ld 4 месяца назад

i did everything exactly as you did, when i try to ask my pdf a question from content further in the document it just throws hmm i dont know. infos from the beginning work fine. seems like it just ignores the embedded info and just gets the first few thousand tokens. a bit frustrating but i tried other chunk size and embedding models, nothing works :(

@leonvanzyl 4 месяца назад

Sorry to hear that you're having issues. RAG is a reliable method for fetching documents and you really shouldn't be having issues. It's hard to pinpoint what the issue could be based on the information you provided. I suggest that you try to use Pinecone instead of buffer memory. You can also check that the Pinecone database contains the information that you're querying. Also ensure that the information in the document is text and not images. The PDF Loader is not able / effective at extracting text from images. You might be experiencing issues with buffer memory due to hardware limitations. Let us know if you come right 👍.

@MD-qh6ld 4 месяца назад

@@leonvanzyl thank you very much for your answer! Initially i had the same problem also with pinecone. I then, through trial and error, found that for smaller .txt files, like the one you had in the older tutorial video, a chunk size of about 200 with overlap 50 worked well, but not for the larger pdf files. There i only started to not get the hmm, i dont know message when i increased the chunk size to 3000 with overlap 300. the pdfs were medical guidelines that did not have a lot of images, and it was ocr scanned. My hardware is on the high end side, but my ssd is running thin on free space, maybe thats got something to do with it. I assume there is a lot i dont yet understand about RAG as well as llms and flowise 😅. I saw another youtube video that mentioned semantic text splitters. That seemed to make a lot more sense to me than the other text splitters, do you know if that is possible to do in flowise? Also do you have content on how metadata works for RAG? Thanks again :)

@fejdraus 4 месяца назад

Tried to do exactly the same thing, but not a single document responded the way you did

@leonvanzyl 4 месяца назад

Perhaps you forgot to upsert or save the chatflow. Very hard to say with the information provided. Check the console for any errors.

@florentflote 4 месяца назад

@leonvanzyl 4 месяца назад

Thanks 🤗

@insanemedia786 4 месяца назад

please make a vedio on prpduct recommendation bot using pinecone

@leonvanzyl 4 месяца назад

Will see what I can do. Definitely want to create more project tutorials this year.

@jasonoffenburg Месяц назад

Unfortunately, it no longer works with the FlowiseAi update 1.8.0. A check via Longsmith is also no longer possible.

@leonvanzyl Месяц назад

Can you provide more information on the issues please? I literally use Flowise every day and can confirm that this still works. LangSmith simply moved to settings.

@jamesarnold22 28 дней назад

I think i'm having similar issues too on 1.8.0