Commited Chat with Pdf

chat-with-pdf/.gitignore

@@ -0,0 +1,163 @@
+# 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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/
+venv-app/
+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/

chat-with-pdf/main.py

@@ -0,0 +1,107 @@
+import streamlit as st
+from streamlit_extras.add_vertical_space import add_vertical_space
+from PyPDF2 import PdfReader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_openai.embeddings import OpenAIEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_openai import OpenAI
+from langchain.chains.question_answering import load_qa_chain
+from langchain.callbacks import get_openai_callback
+
+import pickle
+from dotenv import load_dotenv
+import os
+
+load_dotenv()
+st.set_page_config(page_title="Chat with Pdf", page_icon=":robots:", layout="wide")
+
+##side bar components
+with st.sidebar:
+    st.title("About")
+    st.write("Chat with Pdf 🚀")
+
+    add_vertical_space(5)
+    st.write("Created by Manimaran [Blog](https://rmanimaran.wordpress.com)")
+
+import threading
+
+class PicklableFAISS(FAISS):
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.lock = threading.RLock()
+
+    def __getstate__(self):
+        state = self.__dict__.copy()
+        del state['lock']
+        return state
+
+    def __setstate__(self, state):
+        self.__dict__.update(state)
+        self.lock = threading.RLock()
+
+
+
+def main():
+    st.title("Chat with Pdf")
+    pdf = st.file_uploader("Upload a PDF", type="pdf")
+    if pdf is not None:
+        st.write("PDF uploaded successfully")
+        # You can now use the 'pdf' object to process the PDF file
+        pdf_reader = PdfReader(pdf)
+        st.write("Number of pages:", len(pdf_reader.pages))
+        # extract the text from each page
+        text = ""
+        for page in pdf_reader.pages:
+            text += page.extract_text()
+
+        text_splitter = RecursiveCharacterTextSplitter(
+            chunk_size=1000,
+            chunk_overlap=200,
+            length_function=len,
+            separators=["\n\n", "\n", ".", " ", ""],
+        )
+        chunks = text_splitter.split_text(text)
+        st.write("Number of chunks:", len(chunks))
+        store_name = pdf.name[:-4]
+        # check if the vector store already exists
+        if os.path.exists(f"{store_name}.faiss"):
+            st.write("Vector store already exists")
+            vectorstore = FAISS.load_local(f"{store_name}.faiss", OpenAIEmbeddings(), allow_dangerous_deserialization=True)
+        else:
+            st.write("Creating vector store...")
+            #embeddings
+            embeddings = OpenAIEmbeddings()
+            #vectorstore = PicklableFAISS.from_texts(chunks, embeddings)
+            vectorstore = FAISS.from_texts(chunks, embeddings)
+            # store the vector for the pdf and save using picke
+
+            vectorstore.save_local(f"{store_name}.faiss")
+            st.write("Vector store saved successfully")
+
+            #load the vector store
+            vectorstore = FAISS.load_local(f"{store_name}.faiss", embeddings, allow_dangerous_deserialization=True)
+            st.write("Vector store loaded successfully")
+
+        #Accept user question
+        query = st.text_input("Ask a question about your PDF:")
+        if query:
+            docs = vectorstore.similarity_search(query,k=3)
+            #st.write(docs)
+            #st.write("Answer:", docs)
+            # Now create the chain and pass to LLM
+            llm = OpenAI(temperature=0)
+            chain = load_qa_chain(llm, chain_type="stuff")
+            # Run the chain and get the response
+            with st.spinner("Generating response..."):
+                with get_openai_callback() as cb:
+                    response = chain.run(input_documents=docs, question=query)
+                    st.sidebar.success(f"Total Tokens: {cb.total_tokens}")
+                    st.sidebar.success(f"Prompt Tokens: {cb.prompt_tokens}")
+                    st.sidebar.success(f"Completion Tokens: {cb.completion_tokens}")
+                    st.sidebar.success(f"Total Cost (USD): ${cb.total_cost}")   
+                st.write(response)
+    else:
+        st.write("Please upload a PDF file")
+
+if __name__ == "__main__":
+    main()

chat-with-pdf/readme.md

@@ -0,0 +1,2 @@
+Final Output
+![alt text](image.png)

chat-with-pdf/requirements.txt

@@ -0,0 +1,8 @@
+langchain
+PyPDF2
+python-dotenv
+streamlit
+faiss-cpu
+streamlit-extras
+langchain_community
+langchain_openai