Add application file

.gitignore

@@ -0,0 +1,195 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python,visualstudiocode
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,visualstudiocode
+
+### Python ###
+# 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/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+# End of https://www.toptal.com/developers/gitignore/api/python,visualstudiocode

app.py

@@ -0,0 +1,127 @@
+import os
+from langchain.chains.question_answering import load_qa_chain
+from langchain.document_loaders import UnstructuredFileLoader
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.llms import OpenAI
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores import FAISS
+from pypdf import PdfReader
+import mimetypes
+import validators
+import requests
+import tempfile
+import gradio as gr
+
+
+def get_empty_state():
+ return {"knowledge_base": None}
+
+
+def on_token_change(user_token):
+ os.environ["OPENAI_API_KEY"] = user_token
+
+
+def create_knowledge_base(docs):
+ # split into chunks
+ text_splitter = CharacterTextSplitter(
+ separator="\n", chunk_size=1000, chunk_overlap=200, length_function=len
+ )
+ chunks = text_splitter.split_documents(docs)
+
+ # Create embeddings
+ embeddings = OpenAIEmbeddings()
+ knowledge_base = FAISS.from_documents(chunks, embeddings)
+ return knowledge_base
+
+
+def upload_file(file_obj):
+ # pdf_reader = PdfReader(file_obj.name)
+ # text = ""
+ # for page in pdf_reader.pages:
+ # text += page.extract_text()
+ loader = UnstructuredFileLoader(file_obj.name, strategy="fast")
+ docs = loader.load()
+
+ knowledge_base = create_knowledge_base(docs)
+ return file_obj.name, {"knowledge_base": knowledge_base}
+
+
+def upload_via_url(url):
+ if validators.url(url):
+ r = requests.get(url)
+
+ if r.status_code != 200:
+ raise ValueError(
+ "Check the url of your file; returned status code %s" % r.status_code
+ )
+
+ content_type = r.headers.get("content-type")
+ file_extension = mimetypes.guess_extension(content_type)
+ temp_file = tempfile.NamedTemporaryFile(suffix=file_extension, delete=False)
+ temp_file.write(r.content)
+ file_path = temp_file.name
+ loader = UnstructuredFileLoader(file_path, strategy="fast")
+ docs = loader.load()
+ with open(file_path, mode="rb") as f:
+ pass
+ knowledge_base = create_knowledge_base(docs)
+ return file_path, {"knowledge_base": knowledge_base}
+ else:
+ raise ValueError("Please enter a valid URL")
+
+
+def answer_question(question, state):
+ knowledge_base = state["knowledge_base"]
+ if knowledge_base:
+ docs = knowledge_base.similarity_search(question)
+
+ llm = OpenAI(temperature=0.4)
+ chain = load_qa_chain(llm, chain_type="stuff")
+ response = chain.run(input_documents=docs, question=question)
+ return response
+ else:
+ return "Please upload a file first"
+
+
+with gr.Blocks(css="style.css") as demo:
+ state = gr.State(get_empty_state())
+ with gr.Column(elem_id="col-container"):
+ gr.Markdown(
+ """
+ # Ask your PDF 💬
+ """
+ )
+ user_token = gr.Textbox(
+ value="",
+ label="OpenAI API Key",
+ placeholder="OpenAI API Key",
+ type="password",
+ show_label=True,
+ )
+ gr.Markdown("**Upload your file**")
+ with gr.Row(elem_id="row-flex"):
+ with gr.Column(scale=3):
+ file_url = gr.Textbox(
+ value="",
+ label="Upload your file",
+ placeholder="Enter a url",
+ show_label=False,
+ )
+ with gr.Column(scale=1, min_width=160):
+ upload_button = gr.UploadButton(
+ "Browse File", file_types=[".txt", ".pdf", ".doc", ".docx"]
+ )
+ file_output = gr.File()
+ user_question = gr.Textbox(value="", label="Ask a question about your file:")
+ answer = gr.Textbox(value="", label="Answer:")
+ gr.Examples(
+ ["What is the main topic of the file?", "Who is the author of the file?"],
+ user_question,
+ )
+
+ file_url.submit(upload_via_url, file_url, [file_output, state])
+ upload_button.upload(upload_file, upload_button, [file_output, state])
+ user_token.change(on_token_change, inputs=[user_token], outputs=[])
+ user_question.submit(answer_question, [user_question, state], [answer])
+
+demo.queue().launch()

requirements.txt

@@ -0,0 +1,13 @@
+openai
+tiktoken
+langchain
+gradio
+pypdf
+requests
+unstructured
+validators
+pytesseract
+pdf2image
+tabulate
+nltk
+python-dotenv

style.css

@@ -0,0 +1,25 @@
+#col-container {
+ max-width: 600px;
+ margin-left: auto;
+ margin-right: auto;
+}
+
+#row-flex {
+ display: flex;
+ align-items: center;
+ justify-content: center;
+}
+
+a,
+a:hover,
+a:visited {
+ text-decoration-line: underline;
+ font-weight: 600;
+ color: #1f2937 !important;
+}
+
+.dark a,
+.dark a:hover,
+.dark a:visited {
+ color: #f3f4f6 !important;
+}