Code Monkey home page Code Monkey logo

datachat's Introduction

DataChat: Conversational Data Analysis with Ollama

DataChat is an interactive web application that lets you analyze and explore your datasets using natural language. Simply upload your CSV or Excel file, and start asking questions about your data in plain English. DataChat leverages the power of Ollama (gemma:2b) for language understanding and LangChain for seamless integration with data analysis tools.

Ollama LangChain Streamlit License: MIT

Features

  • Intuitive Chat Interface: Ask questions about your data in a conversational manner.
  • Support for CSV and Excel Files: Easily upload your data from common file formats.
  • Powerful Data Analysis: Get answers to questions about trends, statistics, distributions, and relationships within your data.
  • Seamless Integration: Leverages LangChain to connect Ollama with data analysis tools like Pandas.

Getting Started

  1. Prerequisites:

  2. Installation:

    git clone [https://github.com/WizKnight/DataChat]
    cd DataChat
    pip install -r requirements.txt
  3. Running the App:

    streamlit run src/main.py

    This will open DataChat in your web browser.

Usage

  1. Upload Data: Click "Select a file..." and choose your CSV or Excel file.
  2. Start Chatting: Type your questions about the data in the chat input box.
  3. Get Answers: DataChat will process your question and display the answer in the chat.

Examples

  • "What is the average age of customers?"
  • "How many sales were made in each region?"
  • "Which product category has the highest revenue?"
  • "Show me a histogram of customer ages."

Customization

  • LLM: Experiment with different Ollama models or versions for improved performance.
  • Data Analysis Tools: Extend DataChat by adding custom LangChain tools to integrate with other analysis libraries or APIs.
  • UI/UX: Customize the Streamlit interface to match your preferences.

License

This project is licensed under the Apache 2.0 License.

Acknowledgements

  • This project is inspired by the growing potential of large language models and their application to data analysis.
  • I thank the developers of Ollama, LangChain, and Streamlit for their excellent tools and resources.

datachat's People

Contributors

wizknight avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.