Upload 8 files

.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/

Dockerfile

@@ -0,0 +1,20 @@
+# Use the official Python image
+FROM python:3.10
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy the requirements.txt file first to leverage Docker cache
+COPY requirements.txt .
+
+# Install required Python packages
+RUN pip install -r requirements.txt --default-timeout=100 future
+
+# Copy the rest of the application files to the container's working directory
+COPY . .
+
+# Expose the port that Streamlit will run on
+EXPOSE 8501
+
+# Command to run your Streamlit application
+CMD ["streamlit", "run", "chatbot_app.py"]

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 AI Anytime
+
+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

@@ -1,12 +1,30 @@
----
-title: Local GPT 2
-emoji: 🦀
-colorFrom: blue
-colorTo: gray
-sdk: streamlit
-sdk_version: 1.31.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Chat-with-PDF-Chatbot
+This Chatbot is an interactive app developed to assist users to interact with their PDF. It is built using Open Source Stack. No OpenAI is required.
+
+## Getting Started
+
+Follow these steps to set up and run the project on your local machine.
+
+
+### Installation
+
+```sh
+## Clone the repository
+git clone <repository_url>
+
+## Create the necessary folders
+mkdir db
+mkdir models
+## Add your model files to the 'models' folder
+mkdir docs
+
+----
+### Usage 
+
+## Run the ingestion script to prepare the data
+
+`python ingest.py`
+
+## Start the chatbot application using Streamlit
+
+`streamlit run chatbot_app.py`

chatbot_app.py

@@ -0,0 +1,171 @@
+import streamlit as st 
+import os
+import base64
+import time
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM 
+from transformers import pipeline
+import torch 
+import textwrap 
+from langchain.document_loaders import PyPDFLoader, DirectoryLoader, PDFMinerLoader 
+from langchain.text_splitter import RecursiveCharacterTextSplitter 
+from langchain.embeddings import SentenceTransformerEmbeddings 
+from langchain.vectorstores import Chroma 
+from langchain.llms import HuggingFacePipeline
+from langchain.chains import RetrievalQA 
+from constants import CHROMA_SETTINGS
+from streamlit_chat import message
+
+st.set_page_config(layout="wide")
+
+device = torch.device('cpu')
+
+checkpoint = "MBZUAI/LaMini-T5-738M"
+print(f"Checkpoint path: {checkpoint}")  # Add this line for debugging
+tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+base_model = AutoModelForSeq2SeqLM.from_pretrained(
+    checkpoint,
+    device_map=device,
+    torch_dtype=torch.float32
+)
+
+persist_directory = "db"
+
+@st.cache_resource
+def data_ingestion():
+    for root, dirs, files in os.walk("docs"):
+        for file in files:
+            if file.endswith(".pdf"):
+                print(file)
+                loader = PDFMinerLoader(os.path.join(root, file))
+    documents = loader.load()
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=500)
+    texts = text_splitter.split_documents(documents)
+    #create embeddings here
+    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+    #create vector store here
+    db = Chroma.from_documents(texts, embeddings, persist_directory=persist_directory, client_settings=CHROMA_SETTINGS)
+    db.persist()
+    db=None 
+
+@st.cache_resource
+def llm_pipeline():
+    pipe = pipeline(
+        'text2text-generation',
+        model = base_model,
+        tokenizer = tokenizer,
+        max_length = 256,
+        do_sample = True,
+        temperature = 0.3,
+        top_p= 0.95,
+        device=device
+    )
+    local_llm = HuggingFacePipeline(pipeline=pipe)
+    return local_llm
+
+@st.cache_resource
+def qa_llm():
+    llm = llm_pipeline()
+    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+    db = Chroma(persist_directory="db", embedding_function = embeddings, client_settings=CHROMA_SETTINGS)
+    retriever = db.as_retriever()
+    qa = RetrievalQA.from_chain_type(
+        llm = llm,
+        chain_type = "stuff",
+        retriever = retriever,
+        return_source_documents=True
+    )
+    return qa
+
+def process_answer(instruction):
+    response = ''
+    instruction = instruction
+    qa = qa_llm()
+    generated_text = qa(instruction)
+    answer = generated_text['result']
+    return answer
+
+def get_file_size(file):
+    file.seek(0, os.SEEK_END)
+    file_size = file.tell()
+    file.seek(0)
+    return file_size
+
+@st.cache_data
+#function to display the PDF of a given file 
+def displayPDF(file):
+    # Opening file from file path
+    with open(file, "rb") as f:
+        base64_pdf = base64.b64encode(f.read()).decode('utf-8')
+
+    # Embedding PDF in HTML
+    pdf_display = F'<iframe src="data:application/pdf;base64,{base64_pdf}" width="100%" height="600" type="application/pdf"></iframe>'
+
+    # Displaying File
+    st.markdown(pdf_display, unsafe_allow_html=True)
+
+# Display conversation history using Streamlit messages
+def display_conversation(history):
+    for i in range(len(history["generated"])):
+        message(history["past"][i], is_user=True, key=str(i) + "_user")
+        message(history["generated"][i],key=str(i))
+
+def main():
+    st.markdown("<h1 style='text-align: center; color: blue;'>Chat with your PDF 🦜📄 </h1>", unsafe_allow_html=True)
+    st.markdown("<h3 style='text-align: center; color: grey;'>Built by <a href='https://github.com/AIAnytime'>AI Anytime with ❤️ </a></h3>", unsafe_allow_html=True)
+
+    st.markdown("<h2 style='text-align: center; color:red;'>Upload your PDF 👇</h2>", unsafe_allow_html=True)
+
+    uploaded_file = st.file_uploader("", type=["pdf"])
+
+    if uploaded_file is not None:
+        file_details = {
+            "Filename": uploaded_file.name,
+            "File size": get_file_size(uploaded_file)
+        }
+        filepath = "docs/"+uploaded_file.name
+        with open(filepath, "wb") as temp_file:
+                temp_file.write(uploaded_file.read())
+
+        col1, col2= st.columns([1,2])
+        with col1:
+            st.markdown("<h4 style color:black;'>File details</h4>", unsafe_allow_html=True)
+            st.json(file_details)
+            st.markdown("<h4 style color:black;'>File preview</h4>", unsafe_allow_html=True)
+            pdf_view = displayPDF(filepath)
+
+        with col2:
+            with st.spinner('Embeddings are in process...'):
+                ingested_data = data_ingestion()
+            st.success('Embeddings are created successfully!')
+            st.markdown("<h4 style color:black;'>Chat Here</h4>", unsafe_allow_html=True)
+
+
+            user_input = st.text_input("", key="input")
+
+            # Initialize session state for generated responses and past messages
+            if "generated" not in st.session_state:
+                st.session_state["generated"] = ["I am ready to help you"]
+            if "past" not in st.session_state:
+                st.session_state["past"] = ["Hey there!"]
+                
+            # Search the database for a response based on user input and update session state
+            if user_input:
+                answer = process_answer({'query': user_input})
+                st.session_state["past"].append(user_input)
+                response = answer
+                st.session_state["generated"].append(response)
+
+            # Display conversation history using Streamlit messages
+            if st.session_state["generated"]:
+                display_conversation(st.session_state)
+        
+
+        
+
+
+
+
+if __name__ == "__main__":
+    main()
+
+

constants.py

@@ -0,0 +1,8 @@
+import os 
+import chromadb
+from chromadb.config import Settings 
+CHROMA_SETTINGS = Settings(
+        chroma_db_impl='duckdb+parquet',
+        persist_directory='db',
+        anonymized_telemetry=False
+)

ingest.py

@@ -0,0 +1,32 @@
+from langchain.document_loaders import PyPDFLoader, DirectoryLoader, PDFMinerLoader 
+from langchain.text_splitter import RecursiveCharacterTextSplitter 
+from langchain.embeddings import SentenceTransformerEmbeddings 
+from langchain.vectorstores import Chroma 
+import os 
+from constants import CHROMA_SETTINGS
+
+persist_directory = "db"
+
+def main():
+    for root, dirs, files in os.walk("docs"):
+        for file in files:
+            if file.endswith(".pdf"):
+                print(file)
+                loader = PyPDFLoader(os.path.join(root, file))
+    documents = loader.load()
+    print("splitting into chunks")
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)
+    texts = text_splitter.split_documents(documents)
+    #create embeddings here
+    print("Loading sentence transformers model")
+    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+    #create vector store here
+    print(f"Creating embeddings. May take some minutes...")
+    db = Chroma.from_documents(texts, embeddings, persist_directory=persist_directory, client_settings=CHROMA_SETTINGS)
+    db.persist()
+    db=None 
+
+    print(f"Ingestion complete! You can now run privateGPT.py to query your documents")
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,21 @@
+langchain==0.0.267
+streamlit==1.25.0
+transformers==4.31.0
+torch==2.0.1
+einops==0.6.1
+bitsandbytes==0.41.1
+accelerate==0.21.0
+pdfminer.six==20221105
+bs4==0.0.1
+sentence_transformers
+duckdb==0.7.1
+chromadb==0.3.26
+beautifulsoup4==4.12.2
+sentence-transformers==2.2.2
+sentencepiece==0.1.99
+six==1.16.0
+requests==2.31.0
+uvicorn==0.18.3
+torch==2.0.1
+torchvision==0.15.2
+streamlit-chat