Відео

which terninal are you using?

congratulations Amazing work , really helpful for developer community and novice developers as well, indeed you are doing great work

Damn Praison. This is great! Thanks for sharing all these.

I ran everything as you did from a Raspberry Pi5 (I had to create a virtual environment). When I logged in for the first time (admin admin), I got Auto with the Chainlit logo with the words "str expected, not NoneType". What is that? Is this because I have not yet provided my API key? On a separate note, on the left panel it says "Conversations are not persisted."

Wooohooo!!! 1) Can we save these as some kind of prepared workflows for later? So if a similar request is being done, that it is reused? 2) can you please implement the code snippet to call it from terminal/python? 3) any plans to save history locally?

does NIM make running LLMs faster?

Great video! Thank you for sharing :) Could one do this for flutter / dart to update existing code from openai for chat gpt 3.5 turbo to groq for llama3 model? Obviously the api key needs to change, and the api url, and model name, but what else for parameter names, etc. would be required based on open ai vs groq api would also need adjusting?

all these will work on only models with function calls right sir ?? shall we use gpt3.5 trubo?? pls tell me

nice, can you add your own knowledge base and do RAG?

Awesome job, thanks a lot, man.👏

@MervinPraison how can one add praison backend to work with flask or django project

Nice! That really is a good starting point that leads to more productivity.

Hi, how are you? Great video ! I have a question. In AutoGen, there are TeachableAgents. I want to build an assistant like Alexa or Google, but using an LLM behind it. My question is, what would you recommend more? Using MemGPT for this or using TeachableAgents?

Awesome 🙌🏻

A very good high-level summary. By any chance, could you please create a more in-depth tutorial video that covers each step in detail based on the high-level summary you provided? I don't mind the video takes longer time, even 1 hour!!!

I guess every job all that it does is google search and produce reports ? 😆

1 word: AWESOME !!!

Can it perform tasks on my pc? Like working on my websites and running my ecom businesses by responding to emails and deleting junk mail etc A real virtual assistant

Tools? Awesome brother, but i cant find anything in the description, on the tools

Errors and simple fixes for non-developers (that worked for me). 1. pip install error related to C++14 Visual Studio package not installed; Possible fix: Install an older version of Python (like 3.11.9) 2. export CHAINLIT_AUTH_SECRET error; This error likely means you're on Windows. Windows doesn't recognize the export command by default. Solution for Windows: Copy and paste the following line into your command prompt or terminal: $env:CHAINLIT_AUTH_SECRET="YOUR_SECRET_KEY_HERE" Make sure to replace YOUR_SECRET_KEY_HERE with your actual secret key.

🥳🤯🥳💥

Well done Mervin it is pretty awesome

Hey merwin, can we use gemini api instead of open ai api?

So great! Thank you! 😀 But I cannot find the tools... even I cannot edit the agents and task definition. It whould be great to integrate Ollama as provider. Thank you nyway great project

where is the tools?

very nice love it

im on a macbook . the input - praisonai ui- does not work for me i get this error. File not found: /Users/darth/ui

incrível, top top top 👏👏👏👏👏👏👏👏

🏆 Cheers for sharing! It would be helpful for your non-dev viewers if you created a video on how to follow alone and try these examples with platform providers online. Whether we don't have the hardware or aren't allowed to use the hardware at work.

Rather amazing!!

Good work Mervin!!!

I prefer Continue it is much more fun to work with

Mervin, you should mix it with this village UI we would see the face of the agents talking to each other in pixel art

install instructions are a bit "spartanic" and the experiment failed.

Whoa nice work Mervin

This is amazing! I tried already to run this software, finally i have an guide.

I am getting some errors when I run the app. What are the tools I need to install before hand? TIA!

redo the video from scratch, because nothing was understood. you go too fast and it makes no sense

It's cool but isn't it exposing the data to model? If so, then it could a possible risk

Please from next onwards do Mathematics which is very demanding for students n research who needs math tutors from Ai

can LLM OS be done with vectorshift?

nicee, thank you :-) can you please make a video on LLM OS on AWS?

can you please put a video on LLM OS on AWS?

Worsted tutorial always, Not a detailed video

the UI it is very ugly 😢

I didn't even wanted to try it, but thank you for the great video tutorial. Now I am sure I will never use Mesop Google released yet another trash😂 - my trash is also free.

🎯 Key points for quick navigation: 00:00 *🔍 Introduction to TxtAI's capabilities* - Introduction to TxtAI, an all-in-one solution for text processing and analysis. - Enables embedding creation, indexing, SQL querying with natural language, and pipeline creation. 01:09 *📦 Setting up TxtAI environment* - Steps to set up a TxtAI environment including creating a Conda environment, activating it, and installing TxtAI. - Additional package installations for comprehensive feature exploration. 02:06 *🔍 Performing semantic search* - Demonstrates semantic search capabilities using TxtAI, querying with phrases like "Feelgood story" and "climate change". - Shows how to execute searches in the terminal and interpret results effectively. 03:14 *🔄 Updating and deleting embeddings* - Steps to update embeddings using upsert function and verify changes. - Process of deleting specific embeddings and confirming the deletion results. 04:06 *💾 Saving and loading embeddings* - Saving embeddings using save function and reloading them for verification. - Ensures data persistence and retrieval integrity through saving and loading mechanisms. 04:46 *🔑 Keyword and dense vector index search* - Implementing keyword and dense vector index searches in TxtAI. - Understanding the distinctions and practical applications of each indexing method. 06:10 *🌐 Hybrid search with sparse and dense indexes* - Combining sparse and dense vector indexes for hybrid search capabilities. - Discusses optimal use cases for sparse and dense indexes based on data characteristics. 08:01 *📊 Graph-based embeddings and categorization* - Utilizing graph-based embeddings in TxtAI to categorize data automatically. - Demonstrates setting up graph attributes and performing structured queries on categorized data. 09:25 *🧠 Using large language models (LLM)* - Integration of large language models (LLM) in TxtAI for advanced text processing tasks. - Example of querying with natural language and retrieving contextualized responses. 10:09 *🔄 Creating RAG-based applications and workflows* - Building RAG-based applications using TxtAI's pipeline and creating contextual workflows. - Integration of context and questions to leverage large language models efficiently. 11:30 *🔄 Implementing TxtAI workflows* - Setting up and executing TxtAI workflows using YAML configuration. - Example of translating text inputs into different languages using TxtAI workflows. 12:52 *🛠️ Conclusion and advanced TxtAI applications* - Summary of TxtAI's comprehensive capabilities for embedding solutions. - Encouragement to explore further and integrate TxtAI into advanced application development. Made with HARPA AI

🏆 Cheers for sharing!

Mervin, did you do an update of this with GPT Vo?

Is it possible to run Mesop as HTTPS, as with Streamlit?