HF spaces

.gitattributes

@@ -0,0 +1,41 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.png
+.png
+frontend/images/architecture.png filter=lfs diff=lfs merge=lfs -text
+StudybotAPI/assets/*.png filter=lfs diff=lfs merge=lfs -text
+StudybotAPI/backend/data/History_1.pdf filter=lfs diff=lfs merge=lfs -text
+

.github/workflows/checkfilesize.yaml

@@ -0,0 +1,16 @@
+name: Check file size
+on:               # or directly `on: [push]` to run the action on every push on any branch
+  pull_request:
+    branches: [main]
+
+  # to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+jobs:
+  sync-to-hub:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check large files
+        uses: ActionsDesk/[email protected]
+        with:
+          filesizelimit: 10485760 # this is 10MB so we can sync to HF Spaces

.github/workflows/githubtohfsync.yaml

@@ -0,0 +1,20 @@
+name: Sync to Hugging Face hub
+on:
+  push:
+    branches: [main]
+
+  # to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+jobs:
+  sync-to-hub:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Push to hub
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: git push https://HemanthSai7:[email protected]/spaces/HemanthSai7/StudybotAPI main

.gitignore

@@ -0,0 +1,137 @@
+marvin.toml
+.marvin-history
+marvin.egg-info
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+# dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# vector store
+studybot/vectorstore/
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+cpcli-env/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.10.9
+
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+COPY --chown=user ./StudybotAPI $HOME/StudybotAPI
+
+WORKDIR $HOME/StudybotAPI
+
+RUN mkdir $HOME/.cache
+
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -0,0 +1,56 @@
+---
+title: StudybotAPI
+emoji: 😻
+colorFrom: gray
+colorTo: blue
+sdk: docker
+pinned: false
+---
+
+# StudyBot x Streamlit
+
+✨ Streamlit is an open-source app framework for Machine Learning and Data Science teams. Create beautiful data apps in hours, not weeks. All in pure Python. ✨
+
+## Installation
+
+```bash
+pip install -r requirements.txt
+```
+
+## Start development server
+
+> If you're using the default template, **remember to set the OpenAI API key** in `main.py`.
+
+Run the following command:
+
+```bash
+cd StudybotAPI
+uvicorn app:app --reload
+```
+
+Now go to [http://localhost:4000](http://localhost:4000) and start chatting with your bot! The bot will automatically reload when you change the code.
+
+## Motive
+When studying a theoretical subject, which has a lot of concepts, dates, important events etc. No matter how hard we try to momrize them, its hard to remember them all. So, I thought of making a bot which can help us in quick revision of the subject. For example, if we are studying history, and we forget the event of 1857 revolt, we can ask the bot like **"What happened in 1857?"** and it will tell us brief answer. This will help us in quick revision of the subject.
+
+## How to use
+Input the prompt in the text box and press enter. The bot will give you the answer. If you want to ask another question, just enter the question and the bot will try to answer.
+
+## Screenshots
+![image](StudybotAPI/assets/ss1.png)
+![image](StudybotAPI/assets/ss2.png)
+![image](StudybotAPI/assets/ss3.png)
+
+## How it works
+![image](StudybotAPI/assets/flowchart.png)
+
+## Tech Stack
+![Python](https://img.shields.io/badge/python-3670A0?style=for-the-badge&logo=python&logoColor=ffdd54)
+![FastAPI](https://img.shields.io/badge/FastAPI-005571?style=for-the-badge&logo=fastapi)
+![JavaScript](https://img.shields.io/badge/javascript-%23323330.svg?style=for-the-badge&logo=javascript&logoColor=%23F7DF1E)
+![HTML5](https://img.shields.io/badge/html5-%23E34F26.svg?style=for-the-badge&logo=html5&logoColor=white)
+![GitHub Actions](https://img.shields.io/badge/github%20actions-%232671E5.svg?style=for-the-badge&logo=githubactions&logoColor=white)
+![Langchain](https://img.shields.io/badge/langchain-%23E34F26.svg?style=for-the-badge&logo=langchains&logoColor=white)
+![Huggingface](https://img.shields.io/badge/huggingface-%23E34F26.svg?style=for-the-badge&logo=huggingface&logoColor=white)
+![Streamlit](https://img.shields.io/badge/streamlit-%23E34F26.svg?style=for-the-badge&logo=streamlit&logoColor=white)
+![Docker](https://img.shields.io/badge/docker-%23E34F26.svg?style=for-the-badge&logo=docker&logoColor=white)

StudybotAPI/app.py

@@ -0,0 +1 @@
+from backend import app

StudybotAPI/backend/__init__.py

@@ -0,0 +1,40 @@
+import os
+import box
+import yaml
+
+from fastapi import FastAPI
+
+from backend.ingestion import *
+
+# from langchain.llms.huggingface_pipeline import HuggingFacePipeline
+
+
+app = FastAPI(title="StudyBot API", version="0.1.0", description="API for StudyBot Project")
+
+from backend import routes
+# from backend.retriever import EmbeddingModel
+
+
+try:
+    os.environ["TRANSFORMERS_CACHE"] = "/.cache"
+
+    with open("config.yml", "r", encoding="utf8") as ymlfile:
+        cfg = box.Box(yaml.safe_load(ymlfile))
+    app.state.emb = Embeddings(cfg) 
+
+    # llm = HuggingFacePipeline(pipeline=EmbeddingModel._initialize_pipeline())
+    # llm = LlamaCpp(
+    #     streaming=True,
+    #     model_path="models/mistral-7b-instruct-v0.1.Q4_K_M.gguf",
+    #     max_tokens=1500,
+    #     temperature=0.4,
+    #     top_p=1,
+    #     gpu_layers=0,
+    #     stream=True,
+    #     verbose=False,
+    #     n_threads=int(os.cpu_count() / 2),
+    #     n_ctx=4096
+    # )
+
+except Exception as e:
+    print(e)

StudybotAPI/backend/core/ExceptionHandlers.py

@@ -0,0 +1,27 @@
+from backend import app
+from .Exceptions import *
+
+from fastapi.responses import JSONResponse
+from fastapi.requests import Request
+from fastapi import status
+
+@app.exception_handler(ModelDeploymentException)
+async def model_deploying_exception_handler(request: Request, exc: ModelDeploymentException):
+    return JSONResponse(
+        status_code=status.HTTP_503_SERVICE_UNAVAILABLE,
+        content=repr(exc)
+    )
+
+@app.exception_handler(InfoNotProvidedException)
+async def info_not_provided_exception_handler(request: Request, exc: InfoNotProvidedException):
+    return JSONResponse(
+        status_code=status.HTTP_400_BAD_REQUEST,
+        content=repr(exc)
+    )
+
+@app.exception_handler(DataNotUploadedException)
+async def data_not_uploaded_exception_handler(request: Request, exc: DataNotUploadedException):
+    return JSONResponse(
+        status_code=status.HTTP_400_BAD_REQUEST,
+        content=repr(exc)
+    )