Hi @Alex_MindStudio
I’m building an AI agent to analyse a CSV file (≈ 3000 rows, 40 fixed fields), hosted at a publicly accessible URL. I need to build an AI-driven data-analysis bot that:
-
reads the CSV directly from the URL;
-
treats this CSV as its sole knowledge base;
-
supports queries: filters, aggregations, comment-level retrieval, comparisons between fields;
-
returns structured results;
-
presents outputs via clean UI (Custom Interface / Dynamic HTML / Generate Asset), not raw workflow blocks.
My questions:
-
Is the packaged “Analyze CSV / Analyze Data” action the recommended solution for this use case?
-
Does it support external CSV loading from URL (not needing manual upload)?
-
Can it handle datasets of this size and return filtered subsets (e.g. all comments with sentiment = “Negative” and Department = “X”)?
-
What is the best way to build a clean user-facing UI (chatBot) so that end users don’t see the internal workflow execution steps?
-
Do you have a sample/remix project demonstrating this setup?
Thanks in advance for any guidance.
Hi @Fjmtrigo,
Here’s how your setup could look like:
- Extract Text from File / HTTP Request / Custom Function: to fetch the CSV
- Generate Asset with a SPA Bundle if you want an app-style interface where users can stay in one view to send queries and see results
- Analyze CSV to process queries and return filtered results
You can also replace the Analyze CSV block with your own Custom Function if your setup requires something more specific.
The Analyze CSV block is a good starting point for your use case
The block requires a string input, so you’ll need to fetch the CSV first using Extract Text from File, HTTP Request, or a Custom Function, then pass the string into the block
Yes, it should be able to handle datasets of that size and return subsets like the ones you described
The Generate Asset block with a SPA Bundle is likely the best option because it lets you build your own React interface that would look and work like an app
Alternatively, you could use a Custom Interface with the new minimalistic animation while the agent runs:
We don’t have a template for this yet, but I’d love to see what you build!
1 Like
Hi @Alex_MindStudio
Don’t know why but the analyze csv package is gettinbg an error when running, there a specific way to format the csv file, like UTF, or even the columns name or number of columns inside the csv?
and in the analyze csv configuration all it’s fine….
best
fernando
Hi @Fjmtrigo,
There aren’t specific requirements for how the data needs to be structured. Could you share the file so I can take a closer look?
1 Like
Hi @Alex_MindStudio
Since this database contains sensitive information, I have only shared it with you by email.
This is just a short example with near 150 line, the goal is to have the same structure but with more than 3 000 lines, do you think it’s possible?
thanks
fernando
Hi @Alex_MindStudio
I’m having a problem because I need to analyze CSV files that have more than 2,000 lines, and from what you told me, the “Analyze CSV” package works fine for this number of lines/data. Do you have any idea when this will be resolved?
In the meantime, do you have any other solution I can use to analyze this huge amount of data? I tried doing it with custom functions, and it works fine if there are 50 lines of data in the CSV file, but when I try to put 100 lines, it crashes the workflow because it doesn’t have enough computing power for so much data.
Please help me find a solution here, perhaps by splitting the CSV file into many… but how many would csv files that be?
I’m sure you’ll find a solution for me, you always do. 
thanks a lot!
fernando
Hi @Fjmtrigo,
Apologies that it’s taking us longer than expected to investigate the issue. I will get back to you as soon as I have an update.
In the meantime, could you share the debugger log links for the failed runs? I’d like to take a closer look at what might be causing the issue.
Hi @Fjmtrigo,
Thanks for sharing the links!
I can confirm that there’s no computing power limitation here. The difference between the two runs comes down to how the file data is passed into the Custom Function.
In the successful run, the CSV contents are passed in as a plain string. In the failing run, the variable contains a reference to a file stored in Large File Storage, not the file contents themselves. The function currently assumes it always receives a string, so validation fails when it gets a file reference instead.
Updating the function to detect a remote file reference and fetch the file contents before processing should resolve this.
Hope this helps!
Thanks @Alex_MindStudio , can you give me some lights how can i do this, pleaseeee.
Even if i use the user input “upload file” with the type file “csv” and the processing the “Extract Text” i always will get this LFS (Large File Storage)…
Some hints here please
Hi @Fjmtrigo,
Here’s a small sample Agent that shows how to use a Custom Function to fetch a file uploaded to Large File Storage:
https://app.mindstudio.ai/agents/content-processor-33b5ca43/remix
1 Like
Thanks @Alex_MindStudio for all your help!
Regarding the “Analyze CSV” package block, hope you continue to investigate and have good news soon. 
Do you have any idea how long it might take to resolve this issue? I am counting on this for a client use case, to analyze large data files in CSV format.
Hi @Fjmtrigo,
We’ve made an update that should resolve the issue you were seeing. Could you try running the Agent again, and let me know how it goes?
hi @Alex_MindStudio ,
Sorry to say this, but the same error occurs 
:
thanks
fernando
Hi @Fjmtrigo,
Could you share the debugger log link for the failed run? I’d like to understand whether this is the same issue or something else.
hi @Alex_MindStudio
Any updates on this topic?
thanks
fernando
