removed gemini API and improved the UI

.gitignore

@@ -0,0 +1,164 @@
+# 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/
+
+#custom
+.streamlit
+/data

README.md

@@ -1,10 +1,10 @@
 ---
-title: Ask Your Pdf
-emoji: 💻
-colorFrom: indigo
-colorTo: gray
+title: Ask Pdf
+emoji: 😻
+colorFrom: blue
+colorTo: green
 sdk: streamlit
-sdk_version: 1.33.0
+sdk_version: 1.31.0
 app_file: app.py
 pinned: false
 ---

app.py

@@ -0,0 +1,159 @@
+from dotenv import load_dotenv
+load_dotenv()
+
+import pickle
+from dotenv import load_dotenv
+import streamlit as st
+from streamlit_chat import message
+import os
+from ocr import convert_pdf_to_images, extract_text_with_easyocr
+from langchain.prompts import PromptTemplate
+from langchain.chains import RetrievalQA
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_community.vectorstores import FAISS
+from langchain.docstore.document import Document
+from langchain.embeddings import HuggingFaceInstructEmbeddings
+from langchain import HuggingFaceHub
+
+load_dotenv()
+
+# @st.cache_resource
+def create_vector_store(file_path):
+    pdf_loader = PyPDFLoader(file_path)
+    docs = pdf_loader.load()
+    raw_text = ''
+    for doc in docs:
+        raw_text += doc.page_content
+
+    if len(raw_text) < 10:
+        raw_text = extract_text_with_easyocr(convert_pdf_to_images(file_path))
+
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=10000, chunk_overlap=200
+    )
+    texts = text_splitter.split_text(raw_text)
+    # # Create multiple documents
+    docs = [Document(page_content=t) for t in texts]
+    vectorstore_faiss = FAISS.from_documents(
+        documents=docs,
+        embedding=HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-base"),
+    )
+    return vectorstore_faiss
+
+def create_prompt_template():
+    prompt_template = """
+    Human: Answer the question as a full sentence from the context provided. If you don't know the answer, don't try to make up an answer.
+    <context>
+    {context}
+    </context>
+    Question: {question}
+    Assistant:"""
+    prompt = PromptTemplate(
+        input_variables=["context", "question"], template=prompt_template
+    )
+    return prompt
+
+
+# @st.cache_resource
+def create_retrieval_chain(vector_store, prompt_template):
+    qa = RetrievalQA.from_chain_type(
+        llm = HuggingFaceHub(repo_id="mistralai/Mistral-7B-Instruct-v0.2", model_kwargs={"max_new_tokens": 4000}),
+        chain_type="stuff",
+        retriever=vector_store.as_retriever(
+            search_type="similarity", search_kwargs={"k": 6}
+        ),
+        chain_type_kwargs={"prompt": prompt_template},
+    )
+
+    return qa
+
+
+def generate_response(chain, input_question):
+    answer = chain({"query": input_question})
+    return answer["result"]
+
+
+def get_file_size(file):
+    file.seek(0, os.SEEK_END)
+    file_size_bytes = file.tell()
+    file_size_mb = file_size_bytes / (1024 * 1024)  # Convert bytes to megabytes
+    file.seek(0)
+    return file_size_mb
+
+
+# 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")
+        if len(history["generated"][i]) == 0:
+            message("Please reframe your question properly", key=str(i))
+        else:
+            message(history["generated"][i],key=str(i))
+
+
+def create_folders_if_not_exist(*folders):
+    for folder in folders:
+        if not os.path.exists(folder):
+            os.makedirs(folder)
+
+
+def main():
+    st.set_page_config(
+        page_title="Ask PDF",
+        page_icon=":mag_right:",
+        layout="wide"
+    )
+
+    st.title("Ask PDF")
+    st.subheader("Unlocking Answers within Documents, Your Instant Query Companion!")
+
+    # Sidebar for file upload
+    st.sidebar.title("Upload PDF")
+    uploaded_file = st.sidebar.file_uploader("", label_visibility='collapsed', type=["pdf"])
+
+    create_folders_if_not_exist("data", "data/pdfs", "data/vectors")
+
+    if "uploaded_file" not in st.session_state or st.session_state.uploaded_file != uploaded_file:
+        st.session_state.uploaded_file = uploaded_file
+        st.session_state.generated = [f"Ask me a question about {uploaded_file.name}" if uploaded_file else ""]
+        st.session_state.past = ["Hey there!"]
+        st.session_state.last_uploaded_file = uploaded_file.name if uploaded_file else None
+
+    if uploaded_file is not None:
+        filepath = "data/pdfs/" + uploaded_file.name
+        with open(filepath, "wb") as temp_file:
+            temp_file.write(uploaded_file.read())
+        vector_file = os.path.join('data/vectors/', f'vector_store_{uploaded_file.name}.pkl')
+
+        # Display the uploaded file name in the sidebar
+        st.sidebar.markdown(f"**Uploaded file:** {uploaded_file.name}")
+
+        if not os.path.exists(vector_file) or "ingested_data" not in st.session_state:
+            with st.spinner('Embeddings are in process...'):
+                ingested_data = create_vector_store(filepath)
+                with open(vector_file, "wb") as f:
+                    pickle.dump(ingested_data, f)
+                st.session_state.ingested_data = ingested_data
+                st.success('Embeddings are created successfully! ✅✅✅')
+        else:
+            ingested_data = st.session_state.ingested_data
+
+        prompt = create_prompt_template()
+        chain = create_retrieval_chain(ingested_data, prompt)
+
+        user_input = st.chat_input(placeholder="Ask a question")
+
+        if user_input:
+            answer = generate_response(chain, 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()
+

ocr.py

@@ -0,0 +1,39 @@
+import easyocr
+from PIL import Image
+from io import BytesIO
+import pypdfium2 as pdfium
+
+
+def convert_pdf_to_images(file_path):
+    pdf_file = pdfium.PdfDocument(file_path)
+    page_indices = [i for i in range(len(pdf_file))]
+
+    renderer = pdf_file.render(
+        pdfium.PdfBitmap.to_pil,
+        page_indices=page_indices,
+        # scale=scale,
+    )
+
+    list_final_images = []
+
+    for i, image in zip(page_indices, renderer):
+        image_byte_array = BytesIO()
+        image.save(image_byte_array, format='jpeg', optimize=True)
+        image_byte_array = image_byte_array.getvalue()
+        list_final_images.append(dict({i: image_byte_array}))
+
+    return list_final_images
+
+def extract_text_with_easyocr(list_dict_final_images):
+    language_reader = easyocr.Reader(['en'])
+    image_list = [list(data.values())[0] for data in list_dict_final_images]
+    image_content = []
+
+    for index, image_bytes in enumerate(image_list):
+        image = Image.open(BytesIO(image_bytes))
+        raw_text = language_reader.readtext(image)
+        raw_text = "\n".join([res[1] for res in raw_text])
+
+        image_content.append(raw_text)
+
+    return "\n".join(image_content)