Created the basic pdf retriever program

main.py

@@ -0,0 +1,66 @@
+import os
+import streamlit as st
+from PyPDF2 import PdfReader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain_community.vectorstores import FAISS
+from langchain_openai import OpenAIEmbeddings
+from langchain.text_splitter import CharacterTextSplitter
+from langchain_community.vectorstores import Chroma
+from dotenv import load_dotenv
+load_dotenv()
+
+os.environ['OPENAI_API_KEY'] = os.environ.get('OPENAI_API_KEY')
+
+
+
+
+def extractText(uploaded_file):
+    file = PdfReader(uploaded_file)
+    text_data = ''
+    for pg in file.pages:
+        text_data += pg.extract_text()
+    return text_data
+
+def chunkText(pdf_text):
+    text_chunker = CharacterTextSplitter(
+    separator="\n",
+    chunk_size=1000,
+    chunk_overlap=200,
+    length_function=len,
+    is_separator_regex=False,
+    )
+    text_sections = text_chunker.create_documents([pdf_text])
+    return text_sections
+
+
+
+def app():
+    st.set_page_config(page_title='AI reads your PDFs')
+    st.title("AI reads your PDFs")
+
+    file = st.file_uploader('Upload your PDF file', type='pdf')
+    if file is not None:
+        # Extract Text from the document, split it into chunks, embed each chunk and load it into the vector store.
+        text = extractText(file)
+        text_sections = chunkText(text)
+        query = st.text_input("Enter your query")
+        # # Query using vector embeddings
+        # db = Chroma.from_documents(text_sections, OpenAIEmbeddings())
+        # embedding_vector = OpenAIEmbeddings().embed_query(query)
+        # docs = db.similarity_search_by_vector(embedding_vector)
+        if st.button('retrieve from PDF'):
+            retriever = FAISS.from_documents(text_sections, OpenAIEmbeddings()).as_retriever()
+            docs = retriever.get_relevant_documents(
+                query
+                )
+            # Print for db embeddings
+            st.write(docs[0].page_content)
+
+
+
+
+def main():
+    app()
+
+if __name__ == '__main__':
+    main()

requirements.txt

@@ -0,0 +1,6 @@
+langchain==0.1.6
+langchain_community==0.0.19
+langchain_openai==0.0.5
+PyPDF2==3.0.1
+python-dotenv==1.0.1
+streamlit==1.31.0