Coder Social home page Coder Social logo

shashipal95 / ai-senior Goto Github PK

View Code? Open in Web Editor NEW

This project forked from logisx/ai-senior

0.0 0.0 0.0 437 KB

AI Assistant, an end-to-end LLMOps project, fine-tuned to provide support for coding and design questions based on the latest trends in the industry.

License: MIT License

Python 39.96% Makefile 2.66% Jupyter Notebook 57.38%

ai-senior's Introduction

Logo

πŸ“‹ Table of Contents

πŸš€ Your personal Senior Assistant

Introducing AI Senior!
Your friendly AI companion offering experienced guidance for all your tech queries. From coding hiccups to tech dilemmas, AI Senior has your back. Simplify your tech journey with AI Senior by your side!

Work is in progress... πŸ—οΈ

Python PyTorch JupyterLab Bytewax AWS Qdrant LLMs HuggingFace Comet Beam LangChain REST Gradio Docker CI/CD Terraform

Architecture

🧰 Tech Stack

  • ML: Python, PyTorch, JupyterLab
  • Data Services: Bytewax, AWS, Qdrant
  • Training: LLMs, HuggingFace, Comet, Beam
  • ChatBot & UI: LangChain, REST-API, Gradio
  • Deployment: Docker, Terraform

πŸ“ Project structure

🚧 Work in progress 🚧

|   .beamignore
|   .env
|   .gitignore                  <- Specify files to be ignored by git
|   LICENSE                     <- Project license
|   Makefile                    <- Makefile with commands like `make data` or `make train`
|   README.md                   <- The top-level README for developers using this project.
|   requirements.txt            <- The requirements file for reproducing the analysis environment, e.g. generated with `pip freeze > requirements.txt`
|   setup.py                    <- Make this project pip installable with `pip install -e`
|   test_environment.py
|   tox.ini
|   .venv
|                   
+---assets                       <- Store public assets for readme file
|   |   architecture.png
|   \---logo-color_cropped.png
|               
+---config                       <- Stores pipelines' configuration files
|       data-params.yaml
|       inference-params.yaml
|       model-params.yaml
|       paths.py
|       
+---data
|   |   .gitkeep
|   |   
|   +---external                 <- Data from third party sources.
|   |       .gitkeep
|   |       
|   +---interim                  <- Intermediate data that has been transformed.
|   |       .gitkeep
|   |       
|   +---processed                <- The final, canonical data sets for modeling.
|   |   |   .gitkeep
|   |   |   documents_newsapi_news.json
|   |   |   
|   |   \---fine-tuning
|   |           testing_data.json
|   |           training_data.json
|   |           
|   \---raw                      <- The original, immutable data dump.
|           .gitkeep
|           
+---docs
|       commands.rst
|       conf.py
|       getting-started.rst
|       index.rst
|       make.bat
|       Makefile
|       
+---logs
|       .gitkeep
|       running_logs.log
|       
+---models                      <- Trained and serialized models, model predictions, or model summaries
|   |   .gitkeep
|   |   
|   \---cache
|           .gitkeep
|           
+---notebooks                   <- Jupyter notebooks for research.
|       .gitkeep
|       research-01-data-api-usage.ipynb
|       
+---references
|       .gitkeep
|       
+---reports
|   |   .gitkeep
|   |   
|   \---figures
|           .gitkeep
|           
+---src                          <- Source code for use in this project.
|   |   __init__.py             <- Makes src a Python module
|   |   
|   +---data                    <- Scripts to download or generate data
|   |   |   .gitkeep
|   |   |   generate_training_data.py
|   |   |   run_data_pipeline.py
|   |   |   __init__.py
|   |   |   
|   |   +---modules
|   |   |       data_preprocessor.py
|   |   |       newsapi_data_loader.py
|   |   |       qdrant_data_uploader.py
|   |   |       training_data_generation.py
|   |   |       __init__.py
|   |   |       
|   |   \---pipeline
|   |           data_download.py
|   |           data_preprocessing.py
|   |           data_upload.py
|   |           
|   +---models                  <- Scripts to train models and then use trained models to make predictions
|   |   |   .gitkeep
|   |   |   requirements.txt
|   |   |   run_inference_pipeline.py
|   |   |   run_training_pipeline.py
|   |   |   steps.txt
|   |   |   train_run.py
|   |   |   __init__.py
|   |   |   
|   |   \---training_pipeline
|   |       |   constants.py
|   |       |   metrics.py
|   |       |   models.py
|   |       |   __init__.py
|   |       |   
|   |       +---api
|   |       |       inference.py
|   |       |       training.py
|   |       |       __init__.py
|   |       |       
|   |       +---data
|   |       |       qa.py
|   |       |       __init__.py
|   |       |       
|   |       \---prompt_templates
|   |               prompter.py
|   |               
|   \---utils                  <- Utility functions and classes
|       |   computation_management.py
|       |   configuration_management.py
|       |   file_management.py
|       |   __init__.py
|       |   
|       \---logging
|               __init__.py
|               
\---src.egg-info

πŸ’» Run Locally

  1. Clone the project
  git clone https://github.com/Logisx/AI_Senior.git
  1. Go to the project directory
  cd my-project
  1. Install dependencies
  pip install -r requirements.txt

🚧 Work in progress 🚧

πŸ—ΊοΈ Roadmap

🚧 Work in progress 🚧

βš–οΈ License

MIT License

πŸ”— Links

linkedin

πŸ“š References & Citations

Inspired by awesome Hands-on LLMs Course made by Paul Iusztin, Pau Labarta Bajo and Alexandru Razvant

Check it out!

ai-senior's People

Contributors

logisx avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    πŸ–– 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. πŸ“ŠπŸ“ˆπŸŽ‰

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 ❀️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.