Видео

I uploaded some documents then i want to deleted few documents from them but still answering the questions from the deleted documents. how to remove them from the vector database? And i don’t some services from it how to delete services? If I delete it through azure does it cause any error in gpt?

You are the only one that advanced in bot usage thank you! Is it possible that you make a video of how you using delgated graph api calls ? also i didn't understood what you have set up with ngrok for it to work, can you explain please :/

it should have been demonstrated on a real task not a bot that views your token

Hello, thank you for the practical showcase. I need a system that would allow our users to search the files through a chatbot in teams. Can I connect this to chatbot in teams or somewhere easily reachable by users of Office products?

Python was not found; run without arguments to install from the Microsoft Store, or disable this shortcut from Settings > Manage App Execution Aliases. this is showing when i am trying to create the enviornment pls help

Keep it up

Hello sir at 1st want to thank you for your videos , you helped me alot in my intenship .... this video I did the same steps but when I click on create button it show me a white blank page and no projects are created hope you help me with that soon

can you tell me the changes made in visual studio c# how will it reflect to the Azure Bot.. how can i make changes in C# code and publish which will help reflecting to the Azure bot...how can i make appsetting.json changes the way you are making changes in the video.? what are the pre-requisites

Now how to get objectid through api?

Create Directory and Local File path for a solution that is going to go to Azure?!

what is the difference between "mail" nad "userPrincipleName" ? mail comes as NULL, if I am building an applicatino to import users emails which property should i use ?

I have scopes that requires admin perimission, how would the other organizations install the app ?

i wish it was more clearly explained step by step rather than jumping from one tab to another. Great work, thanks

the way to use this is toi use it as an intent detector for specific routes and tasks : as well as all querys : All querys sent to the interface are used to build the information packet regarding the input to the model , so the intent detected by the rasa front end is passed to the llm to make a dynamic response based on the intent : as well as the mood of the speaker etc giving a real personalized query which contains data leanred from chathistory and conversation : now the rag can also be atttached here pre llm and given an intent a route given to the corect promptiong method or graph to execute based on the intent ! hence we can build personal ai systems which do rememebr and can serve a fixed purpose as wel as go off book ! but still have the dialog state and goal state to gather the slots ... these slots can now be retuned dynamically to a Pydantic or json template : to the response genrated or gathered from the model : a lloop to get the slot ! ( max turn based ) once the slots are fulfilled then it can respond to the intent as fulfilled ! ... hence slot filling is a mini graph ! .. or decision tree ! ... Hence now a hybrid system ! so your virtual assistant ( domain based can also have the dyamic nature of the llm and the llm can have the scripted nature of the dialog flow which is what it saya on the box ... ie directing the dialog along a perspective designed to return structured information as well as program conversations which perform tasks for the company : So now we can have adynamic model which is gathering data under the surface which is being used in the chat history to maintain mood and personal information or how ever you frame your ChatState ! and ChatHistory , And Associated NLP tasks as you may want to mask all data entering the rag !! and only keep the associated knowledge graphs .. and the masked sentences , ie all nouns removed and replaced with place holders , all sentences anaylised using the snowball alogirythm etc which also can be performed asa task by an agent : ( off loading the task to a hugging face space or outside gpu ) ... so this product really is OLD ! and out DATED ! because trees and graphs and multimodals rags etc ! ... but is revaldated by switching its use case ! They need to REMARKET THE PRODUCT ... UNDER A NEW USE CASE !

Guys i switched to version 3.8.1 and got thr following errors python setup.py egg_info did not run successfully and error: metadata-generation-failed × Encountered error while generating package metadata

it only give action to the name you defined in nlu.If the user give random name it doesnot work.Plx explain. Yesa Mat karo meri jannn

Hi! Thanks for this great video! Do you know how to do the same for a web chat channel? I tried this with teams and works perfectly, but now I need to do it with web chat and it does not work. I have tried many different options and still does not work. I would appreciate any help to find a way! Thanks in advance

Thanks

Thanks! it helped alot

Nicely explained every small detail 👏 Sir.. Suppose we are using a twilio number, how do we verify it while creating an app on meta developer platform for WhatsApp Cloud API ?

Hi sir , is there any internship oppertunity?

Marking my checkpoint 8:00

Marking my checkpoint 4:00

help me: i error The request body must contain the following parameter: 'code'

How to i retrieve licence group all email address using graph api.

Is this bot of yours sends notifications to a single user or to all the users at a time in Ms Teams? Can you please answer this question. Thank you in advance

Marking my checkpoint 5:30

Can I use khmer language?

I got error in rules.yml will you help me to solve it

How do you deploy such bot on premise? I dont want to use azure and their paid services

Not told any thing about use of LLM

PYTHON 3.8 IS THE CORRECT VERSION FOR USING RASA

Can you share the power automate please?

Hi, Sir. Can I ask to hire you for setting up rasa to talk to my NorBERT3 llm, and it to understand chat stories? then it need to give out a spesific response defined by rules. The respond, will be fetched by a py code, and input into a simulation code that is input to consol by a py script. I work as chat moderators, and like to use this combination to correct responses.

Amazing! You are a tech geek!🏆🏅🎖

I am getting below error when I click on "Start bot". I have latest dotnet framework version in my machine. please help Error: Command failed: dotnet build at ChildProcess.exithandler (child_process.js:308:12) at ChildProcess.emit (events.js:210:5) at maybeClose (internal/child_process.js:1021:16) at Process.ChildProcess._handle.onexit (internal/child_process.js:283:5) Output:

This is very useful content. Thank you so much for sharing this with us. For phishing email need to collect response of users from azure graph api . Can you please share something for this.

Can you please share the code

Can u create video to show data source and index using rest apis

Thanks for your video! I am getting the following error while trying to retrieve access token: "HTTP Error 400. The request URL is invalid." Do you have any idea what can it be? Maybe a permission issue?

Great series, Can u please share the github url for the code you are showing?

im encountering this error :rasa.engine.graph - Error running graph component for node train_TEDPolicy3. ActionNotFoundException: Cannot access action 'utter_weather', as that name is not a registered action for this domain. Available actions are: any idea what culd be the reason?

Hi! On my case we need to connect some tables from our Data Warehouse to a LLM (Open AI). If there are multiple tables can the model perform "Joins" to query the data based on a prompt? Our Data Warehouse is also hosted on Azure enviroment

Thanks for the great video! How would you suggest to handle the refresh token?

If I refresh the browser page in the Chat playground, my data source disappears and I have to add all of my data again and allow it to ingest & index all over again. Is there a way around that?

How do I access the attachment if I use the teams as channel. Basically, what I observed in the teams that after I attach the the file, it is uploaded in the share point location of the user. The location can be found in the ContentUrl property of the attachment object. But, the bot program does not have the access of that location and It returns the FORBIDDEN exception. Is there any solution of this problem? Thanks in advance for your suggestion.

I am not able to Add data, it is saying ' Ingestion in progress Preprocessing is in progress (0 of 2 files) Indexing has not started' Pls help

This is exactly what I am trying to do with enterprise grade datasets. Will there be a detailed video on how to do this?

can you help with connecting using managed identity. can you provide connection string

Nice work