KevKibe/Analyzing-Mpesa-Statements-using-Langchain-Pandas-Agent

This is a streamlit app for analyzing Mpesa Statements using Langchain Pandas Agent.

Description

This is a streamlit app for analyzing Mpesa Statements using Langchain Pandas AI Agent. You can read more about it here.

• pandas_agent.py - contains the class that instantiates the AI agent.
• pdf_processor.py - contains the class that extracts tables from the pdf and joins them using the Tabula library.
• text_preprocessing.py - contains code to preprocess the tables extracted.
• app.py - contains code to execute the streamlit app.

Installation

• Clone the repository git clone https://github.com/KevKibe/Analyzing-Mpesa-Statements-using-Langchain-Pandas-Agent.git
• Install requirements pip install -r requirements.txt
• Run the command streamlit run app.py to launch the app on localhost.

Usage

• Enter your OpenAI API Key in the sidebar.
• Upload your M-Pesa Statement.
• Enter a query in the provided text area and click the "generate" button.

Screenshots

The Agent getting an understanding of the Statement and the columns

Finding out how much I have spent on buying Internet Bundles

Finding out how much money I have sent to a specific person in total.

Finding out how much money I have sent to a another specific person in total.

Troubleshooting

• Solutions to common errors.

1. jpype._jvmfinder.JVMNotFoundException: No JVM shared library file (libjvm.so) found. Try setting up the JAVA_HOME environment variable properly. - means you do not have Java Virtual Machine installed in your environment, download it from this site and install.
2. Retrying langchain.llms.openai.completion_with_retry.<locals>._completion_with_retry in 4.0 seconds as it raised RateLimitError: Rate limit reached for text-davinci-003 in organization org-X7JScsPiE6OYrh68GPSZOkVJ 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.. - means your agent has exceeded rate limit of 3 calls/min to the OpenAI API and you need to setup a payment method to increase rate limit.