initial setup commit

.flake8

@@ -0,0 +1,10 @@
+[flake8]
+exclude =
+    venv
+    .venv
+    __pycache__
+    notebooks
+    data
+# Recommend matching the black line length (default 88),
+# rather than using the flake8 default of 79:
+max-line-length = 88

.github/workflows/update.yml

@@ -0,0 +1,17 @@
+name: Push Event Workflow
+
+on: push
+
+jobs:
+  unit-testing:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v2
+
+    - name: Install Package
+      run: pip install flake8
+
+    - name: Run tests
+      run: flake8 insight_engine/embeddings.py

.gitignore

@@ -0,0 +1,155 @@
+# Local data
+data/local_data/
+
+# Secrets
+.streamlit/secrets.toml
+
+# VSCode
+.vscode/
+
+# TODO
+TODO.md
+
+# 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
+
+# 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/
+
+

.streamlit/config.toml

@@ -0,0 +1,2 @@
+[server]
+maxUploadSize = 15

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Glory Olusola
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,40 @@
+<h1 align="center">
+📖Insight Engine
+</h1>
+
+Accurate answers and instant citations for your documents.
+
+## 🔧 Features
+
+- Upload documents 📁(PDF, DOCX, TXT) and answer questions about them.
+- Cite sources📚 for the answers, with excerpts from the text.
+
+## 💻 Running Locally
+
+1. Clone the repository📂
+
+```bash
+git clone https://github.com/mmz-001/insight_engine
+cd insight_engine
+```
+
+2. Install dependencies with [Poetry](https://python-poetry.org/) and activate virtual environment🔨
+
+```bash
+poetry install
+poetry shell
+```
+
+3. Run the Streamlit server🚀
+
+```bash
+cd engine
+streamlit run main.py
+```
+
+## 🚀 Upcoming Features
+
+- Add support for more formats (e.g. webpages 🕸️, PPTX 📊, etc.)
+- Highlight relevant phrases in citations 🔦
+- Support scanned documents with OCR 📝
+- More customization options (e.g. chain type 🔗, chunk size📏, etc.)

data/questions.md

@@ -0,0 +1,32 @@
+# Questions
+
+These are some questions you can ask from the example data to test KnowlegeGPT.
+
+## Paul Graham Essay
+
+1. Why did the author want to get rich?
+2. What are some important things the author learned at Interleaf?
+3. Why did the author drop out of art school?
+4. What was the author's first company?
+5. What made the author leave Y Combinator?
+6. Why did the author go to Italy?
+7. What advice does the author give to aspiring entrepreneurs?
+8. What kinds of projects have the author pursued in his career?
+9. Why did the author switch art schools?
+10. Who is Rtm?
+
+## Employment Contract
+
+1. What is the value of my stock options and when can I exercise them?
+2. What insurance options are available to me?
+3. Are there any mandatory arbitration clauses included in the contract?
+4. Are there any mandatory arbitration clauses included in this contract?
+5. What termination benefits am I entitled to?
+6. What is the vacation policy?
+7. What is the salary and bonus structure?
+
+## HyDE Paper
+
+> Link to paper [here](https://arxiv.org/abs/2212.10496)
+
+1. Explain what a Hypothetical Document Embedding is to a five-year-old

engine/components/faq.py

@@ -0,0 +1,41 @@
+# flake8: noqa
+import streamlit as st
+
+
+def faq():
+    st.markdown(
+        """
+# FAQ
+## How does DocGPT work?
+When you upload a document, it will be divided into smaller chunks 
+and stored in a special type of database called a vector index 
+that allows for semantic search and retrieval.
+
+When you ask a question, DocGPT will search through the
+document chunks and find the most relevant ones using the vector index.
+Then, it will use GPT3 to generate a final answer.
+
+## Is my data safe?
+Yes, your data is safe. DocGPT does not store your documents or
+questions. All uploaded data is deleted after you close the browser tab.
+
+## What do the numbers mean under each source?
+For a PDF document, you will see a citation number like this: 3-12. 
+The first number is the page number and the second number is 
+the chunk number on that page. For DOCS and TXT documents, 
+the first number is set to 1 and the second number is the chunk number.
+
+## Are the answers 100% accurate?
+No, the answers are not 100% accurate. DocGPT uses GPT-3 to generate
+answers. GPT-3 is a powerful language model, but it sometimes makes mistakes 
+and is prone to hallucinations. Also, DocGPT uses semantic search
+to find the most relevant chunks and does not see the entire document,
+which means that it may not be able to find all the relevant information and
+may not be able to answer all questions (especially summary-type questions
+or questions that require a lot of context from the document).
+
+But for most use cases, DocGPT is very accurate and can answer
+most questions. Always check with the sources to make sure that the answers
+are correct.
+"""
+    )

engine/components/sidebar.py

@@ -0,0 +1,42 @@
+import streamlit as st
+
+from engine.components.faq import faq
+
+
+def set_openai_api_key(api_key: str):
+    st.session_state["OPENAI_API_KEY"] = api_key
+
+
+def sidebar():
+    with st.sidebar:
+        st.markdown(
+            "## How to use\n"
+#            "1. Enter your [OpenAI API key](https://platform.openai.com/account/api-keys) below🔑\n"  # noqa: E501
+            "1. Upload a pdf, docx, or txt file📄 (Currently we don't support scanned PDF)\n"
+            "2. Ask a question about the document💬\n"
+            "   Or you can ask DocGPT to give you some questions about the document💬\n"
+        )
+#        api_key_input = st.text_input(
+#            "OpenAI API Key",
+#            type="password",
+#            placeholder="Paste your OpenAI API key here (sk-...)",
+#            help="You can get your API key from https://platform.openai.com/account/api-keys.",  # noqa: E501
+#            value=st.session_state.get("OPENAI_API_KEY", ""),
+#        )
+
+#        if api_key_input:
+#            set_openai_api_key(api_key_input)
+        # set_openai_api_key(st.secrets["OPENAI_API_KEY"])
+
+        st.markdown("---")
+        st.markdown("# About")
+        st.markdown(
+            "📖DocGPT allows you to ask questions about your "
+            "documents and get accurate answers with instant citations. "
+            "You can use it to research a paper or practice your exam. "
+        )
+        st.markdown(
+            "This tool is a work in progress. "
+        )
+
+        faq()