search

amitgupta4407 / All_About_PDF

This is a complete website in which you can chat with pdf, extract meta data, text, links, image, and lot more . Check my blog for more details: https://medium.com/@amit.2503719/allaboutpdf-tool-for-data-extraction-and-talking-to-pdf-using-chatpdf-feature-f2daea15a59c
https://amitgupta4407-all-about-pdf-app-dmn92l.streamlit.app/
MIT License
28 stars 11 forks source link

How can we chat with multiple files? #1

Open MirzaAreebBaig opened 11 months ago

MirzaAreebBaig commented 11 months ago

If we can chat with multiple files at once that will be better for searching & sorting documents rather than opening one by one. If this can be implemented all the chunk can be uploaded and chat with a clear problem solving & getting which document has what.! Thank you in advance to consider this request.

amitgupta4407 commented 11 months ago

Thank you for your suggestion. I will implement this feature next week. Is there anything else I can help with? 😊

amitgupta4407 commented 11 months ago

FileQueryHub

I have added this feature as a separate application named FileQueryHub. You can have a look at it on https://allaboutpdf-multiple-filequery-feature.streamlit.app/. This application allows you to upload multiple textual files like txt, pdf, excel, sql, csv. Is there anything else I can help with? 😊

@MirzaAreebBaig

MirzaAreebBaig commented 11 months ago

Hey, Great thank you for this. How is this project being progressed as per the road map? The features are exciting which you have mentioned over there.

amitgupta4407 commented 11 months ago

I have implemented this feature as a separate application. Visit this. I think this feature will work fine (as this have same logic as chatPDF) but I haven't tested this feature as of now I don't have open-ai API key.

As of now I have checked my log file and got this error. Retrying langchain.embeddings.openai.embed_with_retry.<locals>._embed_with_retry in 4.0 seconds as it raised RateLimitError: Rate limit reached for default-text-embedding-ada-002 in organization org-9o************Ep on requests per min. Limit: 3 / min. Please try again in 20s. Contact us through our help center at help.openai.com if you continue to have issues. Please add a payment method to your account to increase your rate limit. Visit https://platform.openai.com/account/billing to add a payment method..

and this error messages was generated by a program that is using the OpenAI API. The error messages indicate that the program has exceeded the rate limit for the default-text-embedding-ada-002 model in the org-9otlv*****Ep organization. The rate limit for this model is 3 requests per minute. The program is attempting to retry the request after a delay, but it continues to receive the same error message. The error message suggests adding a payment method to the account to increase the rate limit and provides a link to the OpenAI billing page for this purpose.

One more point, if you are trying to use this application for large textual file let us say 300+ pages then you are preferred to run this application locally as I have hosted it on free tier provided by streamlit which provide a limited compute and storage.

I would be grateful if you could kindly review my application and let me know if there are any issues. I am always here to help and would be happy to assist in any way I can 😊🙏