env_debug

Remove quotation marks from .env

.gitignore

@@ -0,0 +1,160 @@
+# 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/

README.md

@@ -1,8 +1,8 @@
 ---
 title: Langchain PDF-QA
-emoji: 📉
-colorFrom: gray
-colorTo: pink
+emoji: ❓
+colorFrom: purple
+colorTo: blue
 sdk: gradio
 sdk_version: 4.8.0
 app_file: app.py

app.py

@@ -0,0 +1,93 @@
+# %% auto 0
+__all__ = ['text_splitter', 'embeddings', 'hub_llm', 'pdf_example_1', 'pdf_example_2', 'question_example_1', 'question_example_2',
+           'title', 'description', 'file_upload', 'question', 'output', 'split_pdf', 'ask_pdf']
+
+import dotenv
+from dotenv import load_dotenv
+load_dotenv()
+
+# Import qa chain
+from langchain.chains.question_answering import load_qa_chain
+
+# Import gradio for UI/app interface
+import gradio as gr
+
+# Import PDF Loaders
+from langchain.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+# Create an instance of RecursiveCharacterTextSplitter with your desired chunk_size and chunk_overlap
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=250)
+
+def split_pdf(pdf):
+  if pdf is not None:
+      # load pdf
+    loader = PyPDFLoader(pdf)
+      # Split pages from pdf (SEE: https://api.python.langchain.com/en/latest/document_loaders/langchain.document_loaders.pdf.PyPDFLoader.html)
+    chunks = loader.load_and_split(text_splitter=text_splitter)
+    return chunks
+
+# Import HuggingFace as main LLM service
+from langchain.embeddings import HuggingFaceEmbeddings
+
+embeddings = HuggingFaceEmbeddings(
+    model_name = "bert-base-nli-mean-tokens",
+    model_kwargs = {'device': 'cpu'},
+    encode_kwargs = {'normalize_embeddings': True}
+)
+
+# Import FAISS as the vector store
+from langchain.vectorstores import FAISS
+
+# import transformers
+# from transformers import AutoTokenizer, AutoModelForCausalLM
+from langchain import HuggingFaceHub
+import torch
+
+hub_llm = HuggingFaceHub(
+    repo_id = 'tiiuae/falcon-7b-instruct',
+    # repo_id = 'tiiuae/falcon-7b-instruct',
+    model_kwargs = {'temperature' : 0.01,  # 'randomness' of outputs, 0.0 is the min and 1.0 the max
+                    # 'top_p': 0.15,  # select from top tokens whose probability add up to x%
+                    'top_k': 25,  # select from top x tokens
+                    'max_new_tokens': 300,  # mex number of tokens to generate in the output
+                    'repetition_penalty': 999  # without this output begins repeating
+                    }
+)
+
+chain = load_qa_chain(hub_llm, chain_type="stuff")
+
+# App Function
+def ask_pdf(pdf, user_question):
+  if pdf is not None and user_question != '':
+      chunks = split_pdf(pdf) # split pdf into smaller chunks
+      store = FAISS.from_documents(chunks, embeddings) # Load documents into vector database
+      docs = store.similarity_search(user_question) # take user input and look for chunks that might contain the answer
+    # run chain
+      response = chain.run(input_documents=docs, question=user_question)
+
+  return response
+
+pdf_example_1 = '/attention.pdf' 
+pdf_example_2 = '/bert.pdf'
+question_example_1 = "What does 'attention' mean in this context?"
+question_example_2 = "What does BERT stand for?"
+
+title="LangChain project: Conversational Retrieval Chain"
+description="Upload a PDF file and ask a question related to its content."
+
+# Create Gradio interface
+file_upload = gr.File(file_types = ['.pdf'],
+                              file_count='single',
+                              label="Upload a PDF file")
+question = gr.Textbox(label="Write your question here:", show_copy_button= True)
+output = gr.Textbox(label="Your answer:")
+
+gr.Interface(
+    fn=ask_pdf,
+    inputs=[file_upload, question],
+    outputs=output,
+    title=title,
+    description=description,
+    examples=[[pdf_example_1, question_example_1], [pdf_example_2, question_example_2]]
+).launch() #share=True

requirements.txt

@@ -0,0 +1,12 @@
+python-dotenv==1.0.0
+langchain==0.0.344
+langchain-core==0.0.8
+accelerate==0.25.0
+sentence-transformers==2.2.2
+sentence-transformers==2.2.2
+transformers==4.35.2
+faiss-gpu==1.7.2
+pypdf==3.17.1
+gradio==4.7.1
+gradio_client==0.7.0
+fastapi==0.104.1