Query Your CSV using LIDA: Automatic Generation of Visualizations with LLMs

No video

Query Your CSV using LIDA: Automatic Generation of Visualizations with LLMs

Рет қаралды 23,310

Күн бұрын

Welcome to my tutorial on "Query Your CSV using LIDA: Automatic Generation of Visualizations with LLMs"! In this video, I'll guide you through the Streamlit app, which leverages the power of LIDA for on-the-fly graph generation based on your queries.
Diving deep into LIDA, it's a state-of-the-art tool designed for the automatic creation of grammar-agnostic visualizations and infographics. Its foundation is built on the intricate synergy between large language models (LLMs) and image generation models (IGMs). Here's a quick breakdown of LIDA's components:
SUMMARIZER: Transforms data into a concise natural language summary.
GOAL EXPLORER: Enumerates the potential visualization objectives given the data at hand.
VISGENERATOR: Responsible for generating, refining, executing, and filtering the visualization code.
INFOGRAPHER: Produces stylized graphics that stay true to the original data, powered by IGMs.
Not only does LIDA come with a handy Python API, but it also offers a versatile user interface that allows for both direct manipulation and multilingual natural language inputs. Whether you're keen on crafting interactive charts, infographics, or captivating data stories, LIDA has got you covered!
If you found this tutorial helpful, please don't forget to like, comment, and subscribe for more insightful content! Thanks for your support.
GitHub Repo: github.com/AIA...
LIDA GitHub: github.com/mic...
LIDA Main Page: microsoft.gith...
#ai #generativeai #python

Пікірлер: 67

@priyanshudubey2245 10 ай бұрын

Sir please make a playlist of Natural Language Processing. Your explanation is too good and easy to digest.

@AIAnytime 10 ай бұрын

I will do that Priyansh. Thank you.

@CesarVegaL 10 ай бұрын

Thank you for your work. Very up-to-date, so it is appreciated.

@AIAnytime 10 ай бұрын

Much appreciated!

@amitsingh-rv4hz 16 күн бұрын

Nice topic and presentation

@sidindian1982 9 ай бұрын

Excellent Work Sir 🙂

@AIAnytime 9 ай бұрын

Many thanks

@yuvrajharsh8763 10 ай бұрын

Thanks a lot for making this video Sir.

@AIAnytime 10 ай бұрын

You are most welcome

@avijit_barua 10 ай бұрын

Thank you so much creating this video

@AIAnytime 10 ай бұрын

It's my pleasure

@user-iu4id3eh1x 10 ай бұрын

Amazing idea... Thank you for this video.

@AIAnytime 10 ай бұрын

Most welcome 😊

@RedCloudServices 9 ай бұрын

wait..can this tool simply allow chat with csv better than previous options? does every answer have to be a graph?

@frankismartinez 10 ай бұрын

Just tried it based on your repo; summarization was very fast, charts were highly relevant. Gracias! Curious, how will it process a pivot table; i.e. will it understand all the dimensions? Or, will the CSV [assuming that data source type] have to be prepared for Lida's tokenization process [assuming]?

@AIAnytime 10 ай бұрын

Thanks Frank for your comment. Yeah Pivot is something we need to figure out. Later is something correct I feel. I will reply back to this comment thread once I try out myself.

@Abhi3661 3 ай бұрын

@frankismartinez Were you able to find anything relevant to the question above?

@latentbhindi837 2 ай бұрын

Does this give good results for non-numeric data or rather a dataset which is a mixture of numeric and non-numeric data?

@PurushothamReddy-ff6vp 4 ай бұрын

Hello, is there anyway to return the raster image directly into the streamlit rather than converting it into images? i lose a a lot of functionality when im converting into an image.

@azer0013 10 ай бұрын

Thank you sir you are genius ❤

@AIAnytime 10 ай бұрын

So nice of you... You are the one my friend.

@valm7397 10 ай бұрын

You are very impressive. Thank you very much.!! Do you think its possble to use lida with Mistral ?

@AIAnytime 10 ай бұрын

Yeah you can use local LLMs. You can use llmx or Vllm to Inference it within Lida. Look at Lida GitHub issues for their roadmaps.

@hawks900 10 ай бұрын

Thank you bro really great video, how to fix that list index out of range issue? I am getting that too

@sohailshaik3323 27 күн бұрын

Hi Bro This code is not working with Azure OpenAI credentials.Can you help me out if you are aware of the solution

@myfc8661 4 ай бұрын

Hi, thanks for the video, on the part of the open source (llama2) or other model like Groq, Gemini Pro, it is not so clear to set it up. Any chance you could drop the code here to set it up. That would be a great help. TQ

@siddharthachakraborty5046 8 ай бұрын

The explanation is so good. Thanks for sharing this. Just had one question, even after doing pip install lida ; getting the following error of ModuleNotFoundError: No Module named ‘lida’; now is this because I am using python 3.8? Also is there a work around. Any answer would be of immense help. Thanks.

@atulkishore9159 6 ай бұрын

Use python 3.11 and set the pycharm interpreter to the venv. The problem will be solved.

@NileshKumarPandey-vr7pw 3 ай бұрын

is there any graph representation module I can use with LAMA3 with Ollama?

@user-wp3tg8kf6t 8 ай бұрын

I am getting error: streamlit:command not found. Even after pip installing it.

@chinnibngrm272 3 ай бұрын

why getting list index out of range while generating viz can anyone know the reason please help

@muhammadtalmeez3276 2 ай бұрын

Can it answer the questions from data like: which country has highest happy rate?

@kushagrasingh7731 6 ай бұрын

LIDA Is good but the only issue is it does no perform well with more than 10 columns

@atulkishore9159 6 ай бұрын

But no real world datasets have less than 10 columns.

@kushagrasingh7731 6 ай бұрын

@@atulkishore9159 yup pandas ai is the best bet

@vaibhavsinghania8368 3 ай бұрын

hello . I am getting TypeError: 'OpenAI' object is not callable. After having tried everything. Can someone pls help? sir?

@jillanisofttech2977 10 ай бұрын

sir can you build proper application using this model and like chat with lida and also have memoery store function please. Proper End to End project b ban jyee ga

@AIAnytime 10 ай бұрын

Yes. That's on the roadmap.

@jillanisofttech2977 9 ай бұрын

Thanks btw when you build this type of project i really want.@@AIAnytime

@victorreyesalvarado8329 10 ай бұрын

thank you again crack! a question here: what version of python are you using?

@AIAnytime 10 ай бұрын

I am using python 3.10... most stable version for generative ai.

@victorreyesalvarado8329 10 ай бұрын

@@AIAnytime thx! i will try in my pc :D

@rameshh3821 3 ай бұрын

Does this work with SQL Agent/ SQL chain?

@aadarshjain671 6 ай бұрын

Hey there, Can we use LIDA without using any API Key , Can we fully download all the things in our system locally as the Base Model / LLM and then apply prompt Engineering or Fine Tuning on that model/LLM with our own data ( That may be confidential ). I want to perform Data Analytics Task on Specific data and therefore i am looking for the open source LLM's to download them locally as the Base Model and then Train it on Specific Data to answer my queries on the same (Not only Summarization but also Visualization ).

@PurushothamReddy-ff6vp 4 ай бұрын

yes, but you'll need a lot of processing power :)

@ironman5034 6 ай бұрын

Which version of llmx to use on windows?

@ChopLabalagun 9 ай бұрын

local execution requires 100GB VRAM which is crazy. 7B models takes about 21GB VRAM and its pretty slow and small CSV file like the one you provided. Pretty bad results, i would probably got the graph myself using pandas and seaborn in the same time it look running locally :D

@AIAnytime 9 ай бұрын

I agree. Not worth using open source LLMs...

@ChopLabalagun 9 ай бұрын

@@AIAnytime pretty sad it would great to generate data like this.

@rishavmishra5786 9 ай бұрын

@@ChopLabalagun Hey! so you successfully ran it on a local model? If so that's great could you possibly help me out? I'll share more info if you are up for it.

@ChopLabalagun 9 ай бұрын

@@rishavmishra5786 it depends on what model you want to run, its pretty heavy and the results are not that good. I can do better plots myself

@pulkit8723 6 ай бұрын

@@ChopLabalagun Hey! I had a few doubts related to this. Could you help resolve them if you don't mind ? I'll share more details if you're up for it.

@user-ts5xu2ci1s 10 ай бұрын

ModuleNotFoundError: No module named 'lida' if i run i got this error why?

@TanmayUmathe 10 ай бұрын

I think you haven't downloaded the module. Go to command prompt and run pip install lida.

@arkodeepchatterjee 10 ай бұрын

please make a video on how to run in cloud

@roshansawant9891 5 ай бұрын

ImportError: cannot import name 'AzureOpenAI' from 'openai' any solution?

@PurushothamReddy-ff6vp 4 ай бұрын

An error in your import openai, ensure that it is present in the scripts you are running your python from ( if you multiple python environments)

@user-ok4op5wu4p 6 ай бұрын

Can you mention versions of all libraries

@yuzual9506 Ай бұрын

LOL, sometimes i think your in my brain...I my work in La Sorbonne i try to give some AI tools for academic researchers, and they want something, and youy do another vids...THX