Mobius is the perfect way for companies to easily organize, access and leverage their data. With Mobius, companies can quickly and intuitively search their data to answer any question, while still staying organized and on track. Mobius' powerful semantic search capabilities cut through all the noise and access only the data that's necessary to get the answers companies need. With Mobius, companies can be smarter and more efficient in the way they work with data.
""", unsafe_allow_html=True) # st.subheader( # "With Mobius, companies can be smarter and more efficient in the way they work with data.") top_match_sentences = [] @ st.cache_data def process_pdf_data(uploaded_files): """ The function accepts an uploaded PDF file as input and then proceeds to extract, preprocess, and vectorize the text. It ultimately returns a list of filtered sentences and their respective embeddings. Parameters: uploaded_files (list): List of uploaded files Returns: filt1_list (list): List of filtered sentences embeddings (list): List of embeddings of the sentences """ filt1_list = [] embeddings = [] text_ext = [] for i in uploaded_files: if i.type == "application/pdf": # Reading the pdf file and extracting the text text_ext += op.read_pdf(i) # Applying sent_tokenize to the text and storing the result in a list sent_toks = [] for i in text_ext: sent_toks.append(sent_tokenize(i)) concat_list = [j for i in sent_toks for j in i] # Removing the new line characters from the list for i in concat_list: a = (i.replace('\n', ' ')) filt1_list.append(a) # Creating embeddings for the sentences embeddings = op.create_content_embeddings(filt1_list) return filt1_list, embeddings # Streamlit code to upload files uploaded_files = st.file_uploader( "Upload files - ", accept_multiple_files=True, type=['pdf']) if st.button("Process!"): if len(uploaded_files) != 0: # Calling the function process_pdf_data to process the uploaded files filt1_list, embeddings = process_pdf_data(uploaded_files) st.write("Process Completed") else: st.warning("Please upload a PDF file.") # Streamlit code to take user input after vectorization of the documents query = st.text_input('Ask me anything!', placeholder='Type.....') try: if st.button("Confirm!"): cached_data = process_pdf_data(uploaded_files) filt1_list = cached_data[0] embeddings = cached_data[1] # Creating embeddings for the query query_embedding = op.create_query_embeddings(query) # Calculating cosine similarity between the query and the sentences cosine_lis = op.calculate_cosine( query_embedding, embeddings, filt1_list) # Fetching the top 15 sentences with the highest cosine similarity indexes_final = op.fetch_top_rank_ans(cosine_lis, 15) # Fetching the most relevant sentence from the top 15 sentences, and providing it as the context to the GPT-3 model most_relevant = op.fetch_most_relevant( indexes_final, filt1_list, cosine_lis, query) # Calling the GPT-3 model to generate the answer # COMPLETIONS_API_PARAMS = { # "temperature": 0.0, # "max_tokens": 300, # "model": "text-davinci-003", # } response = openai.ChatCompletion.create( model="gpt-3.5-turbo", messages=[ {"role": "system", "content": "You are an educational assistant. Answer the questions with detail and in 200-300 characters only"}, {"role": "user", "content": most_relevant}, ] ) # print("\n\n", textwrap.fill( # response["choices"][0]["text"].strip(" \n"))) # Displaying the answer to the user # print(response['choices'][0].message.content) st.write(textwrap.fill(response['choices'][0].message.content)) # import streamlit_scrollable_textbox as stx # long_text = response['choices'][0].message.content # stx.scrollableTextbox(long_text, height=300) except Exception as e: print(e) st.warning("Something went wrong. Please try again.")