init

.github/workflows/push-docker-image.yml

@@ -0,0 +1,28 @@
+name: CI - Build and Push Docker Image
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+jobs:
+  push_to_registry:
+    name: Push Docker image to Docker Hub
+    runs-on: ubuntu-latest
+    env:
+      CONTEXT_SUBDIR: .
+    steps:
+      - name: Check out the repo
+        uses: actions/checkout@v4
+
+      - name: Log in to Docker Hub
+        run: docker login -u amithkoujalgi -p ${{ secrets.DOCKERHUB_ACCESS_TOKEN }}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: Dockerfile
+          push: true
+          tags: amithkoujalgi/pdf-bot:1.0.0

.gitignore

@@ -0,0 +1,171 @@
+# 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/
+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/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .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
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+
+.idea/
+.idea/**
+.DS_Store
+*.pyc
+*.egg-info/**
+
+
+.vscode/
+.npm/

Dockerfile

@@ -0,0 +1,10 @@
+FROM python:3.8.18
+
+WORKDIR /app
+
+COPY ./requirements.txt /app/requirements.txt
+RUN pip install -r /app/requirements.txt
+
+COPY ./pdf_bot /app/pdf_bot
+
+CMD ["streamlit", "run", "/app/pdf_bot/app.py"]

README.md

@@ -0,0 +1 @@
+# ollama-pdf-bot

docker-build.sh

@@ -0,0 +1,2 @@
+#!/bin/bash
+docker build --rm --file Dockerfile -t amithkoujalgi/pdf-bot:1.0.0 .

docker-compose.yml

@@ -0,0 +1,23 @@
+services:
+
+  ollama:
+    image: ollama/ollama
+    ports:
+      - 11434:11434
+    volumes:
+      - ~/ollama:/root/.ollama
+    networks:
+      - net
+
+  app:
+    image: amithkoujalgi/pdf-bot:1.0.0
+    ports:
+      - 8501:8501
+    environment:
+      - OLLAMA_API_BASE_URL=http://ollama:11434
+      - MODEL="orca-mini"
+    networks:
+      - net
+
+networks:
+  net:

install.sh

@@ -0,0 +1,2 @@
+#!/bin/bash
+pip install -r requirements.txt

pdf_bot/app.py

@@ -0,0 +1,124 @@
+import os
+from pathlib import Path
+from typing import Optional
+
+import requests
+import streamlit as st
+
+from pdf_helper import PDFHelper
+
+
+def pull_model(model_name_):
+    print(f"pulling model '{model_name_}'...")
+    url = f"{ollama_api_base_url}/api/pull"
+    data = f'{"name": "{model_name_}"}'
+    headers = {'Content-Type': 'application/json'}
+    _response = requests.post(url, data=data, headers=headers)
+    print(_response.text)
+
+
+title = "PDF Bot"
+
+model_name = os.environ.get('MODEL', "orca-mini")
+
+ollama_api_base_url = os.environ.get('OLLAMA_API_BASE_URL', "http://localhost:11434")
+pdfs_directory = os.path.join(str(Path.home()), 'langchain-store', 'uploads', 'pdfs')
+os.makedirs(pdfs_directory, exist_ok=True)
+
+print(f"Using model: {model_name}")
+print(f"Using Ollama base URL: {ollama_api_base_url}")
+print(f"Using PDFs upload directory: {pdfs_directory}")
+pull_model(model_name_=model_name)
+
+st.set_page_config(page_title=title)
+
+
+def on_upload_change():
+    clear_chat_history()
+
+
+def set_uploaded_file(_uploaded_file: str):
+    st.session_state['uploaded_file'] = _uploaded_file
+
+
+def get_uploaded_file() -> Optional[str]:
+    if 'uploaded_file' in st.session_state:
+        return st.session_state['uploaded_file']
+    return None
+
+
+with st.sidebar:
+    st.title(title)
+    st.write('This chatbot accepts a PDF file and lets you ask questions on it.')
+    uploaded_file = st.file_uploader(
+        label='Upload a PDF', type=['pdf', 'PDF'],
+        accept_multiple_files=False,
+        key='file-uploader',
+        help=None,
+        on_change=on_upload_change,
+        args=None,
+        kwargs=None,
+        disabled=False,
+        label_visibility="visible"
+    )
+
+    if uploaded_file is not None:
+        bytes_data = uploaded_file.getvalue()
+        target_file = os.path.join(pdfs_directory, uploaded_file.name)
+        # print(uploaded_file)
+        set_uploaded_file(target_file)
+        with open(target_file, 'wb') as f:
+            f.write(bytes_data)
+
+# Store LLM generated responses
+if "messages" not in st.session_state.keys():
+    st.session_state.messages = [{"role": "assistant", "content": "Hello, I'm your PDF assistant."}]
+
+# Display or clear chat messages
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.write(message["content"])
+
+
+def clear_chat_history():
+    st.session_state.messages = [{"role": "assistant", "content": "Hello, I'm your PDF assistant."}]
+
+
+st.sidebar.button('Reset', on_click=clear_chat_history)
+
+# User-provided prompt
+if prompt := st.chat_input(disabled=False, placeholder="What do you want to know from the uploaded PDF?"):
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    with st.chat_message("user"):
+        st.write(prompt)
+
+if st.session_state.messages[-1]["role"] != "assistant":
+    source_file = get_uploaded_file()
+    if source_file is None:
+        with st.chat_message("assistant"):
+            with st.spinner("Thinking..."):
+                placeholder = st.empty()
+                full_response = 'PDF file needs to be uploaded before you can ask questions on it 😟. Please upload a file.'
+                placeholder.markdown(full_response)
+        message = {"role": "assistant", "content": full_response}
+        st.session_state.messages.append(message)
+    else:
+        with st.chat_message("assistant"):
+            with st.spinner("Thinking..."):
+                question = dict(st.session_state.messages[-1]).get('content')
+                pdf_helper = PDFHelper(
+                    ollama_api_base_url=ollama_api_base_url,
+                    model_name=model_name
+                )
+                response = pdf_helper.ask(
+                    pdf_file_path=source_file,
+                    question=question
+                )
+                placeholder = st.empty()
+                full_response = ''
+                for item in response:
+                    full_response += item
+                    placeholder.markdown(full_response)
+                placeholder.markdown(full_response)
+        message = {"role": "assistant", "content": full_response}
+        st.session_state.messages.append(message)