Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

How to work with multiple csv files in the same agent session ? is there any option to call agent with multiple csv files, so that the model can interact multiple files and answer us. #1958

Closed
balaji-skoruz opened this issue Mar 24, 2023 · 12 comments · Fixed by #5009
Closed

How to work with multiple csv files in the same agent session ? is there any option to call agent with multiple csv files, so that the model can interact multiple files and answer us. #1958

balaji-skoruz opened this issue Mar 24, 2023 · 12 comments · Fixed by #5009

Comments

@balaji-skoruz
Copy link

No description provided.

@pradosh-abd
Copy link

+1

@pmcray
Copy link

pmcray commented Mar 30, 2023

I would also be interested in whether there is some way of ingesting two or more CSV files of pandas dataframes. I would try doing a Compare and Contrast on the two files.

@skylark400
Copy link

+1

@MohammedAlhajji
Copy link
Contributor

The easiest way I think you'd be able to do this is through specifying them in the input variables and adding them to the prefix

@shakyawar-dev
Copy link

+1

5 similar comments
@kresnandika
Copy link

+1

@JustinGOSSES
Copy link

+1

@Uchoa-Gui
Copy link

+1

@Jonny-P
Copy link

Jonny-P commented Apr 28, 2023

+1

@Leanstuka
Copy link

+1

@ViolaSongsy
Copy link

The easiest way I think you'd be able to do this is through specifying them in the input variables and adding them to the prefix

could you please elaborate on this? thanks!

@injuryholmes
Copy link

+1 Any Pro has a solution yet?

@NickL77 NickL77 mentioned this issue May 20, 2023
Merged
dev2049 pushed a commit that referenced this issue May 25, 2023
@NickL77 @hwchase17
Add Multi-CSV/DF support in CSV and DataFrame Toolkits (#5009)
7652d2a 
Add Multi-CSV/DF support in CSV and DataFrame Toolkits
* CSV and DataFrame toolkits now accept list of CSVs/DFs
* Add default prompts for many dataframes in `pandas_dataframe` toolkit

Fixes #1958
Potentially fixes #4423

## Testing
* Add single and multi-dataframe integration tests for
`pandas_dataframe` toolkit with permutations of `include_df_in_prompt`
* Add single and multi-CSV integration tests for csv toolkit
---------

Co-authored-by: Harrison Chase <[email protected]>
Undertone0809 pushed a commit to Undertone0809/langchain that referenced this issue Jun 19, 2023
@NickL77 @hwchase17 @Undertone0809
Add Multi-CSV/DF support in CSV and DataFrame Toolkits (langchain-ai#…
96ec35a 
…5009)

Add Multi-CSV/DF support in CSV and DataFrame Toolkits
* CSV and DataFrame toolkits now accept list of CSVs/DFs
* Add default prompts for many dataframes in `pandas_dataframe` toolkit

Fixes langchain-ai#1958
Potentially fixes langchain-ai#4423

## Testing
* Add single and multi-dataframe integration tests for
`pandas_dataframe` toolkit with permutations of `include_df_in_prompt`
* Add single and multi-CSV integration tests for csv toolkit
---------

Co-authored-by: Harrison Chase <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Add Multi-CSV/DF support in CSV and DataFrame Toolkits NickL77/langchain