pip install python-dotenv pip install PyPDF2 pip install python-pptx pip install python-docx pip install langchain pip install sentence_transformers pip install InstructorEmbedding pip install streamlit pip install htmlTemplates pip install faiss-cpu
Make sure before run the project you have created the environment if not refer this: https://www.freecodecamp.org/news/how-to-setup-virtual-environments-in-python/
After installing run this command: streamlit run app.py
wait some time to download the model of project, it's around 4 GB
if any error occurs then try this: from langchain_community.embeddings import SentenceTransformerEmbeddings conda install pytorch torchvision cudatoolkit=10.0 -c pytorch pip install -U sentence-transformers
- Streamlit - Framework for building interactive web applications with Python.
- PyPDF2 - Library for reading and manipulating PDF files in Python.
- python-pptx - Library for working with PowerPoint (.pptx) files in Python.
- python-docx - Library for creating and modifying Word (.docx) files in Python.
- langchain - [Brief description or purpose of the langchain library.]
- Hugging Face Model Hub - Repository of pre-trained models and datasets for natural language processing tasks.
- HTML Templates - [Brief description of the HTML templates used in your project.]
Description: This project makes it easy for people to talk to their PDF documents using a simple website. With the help of Streamlit, users can ask questions or find information within their uploaded PDF files, and quickly get answers that make sense. It's like having a conversation with your documents!
Key Features: Free: It's free to use there are no charge or any limitations. Multiple docs: User can upload pdf,ppt,docx and text with our application Document Upload: Users can easily upload one or multiple PDF documents through the user-friendly interface. Natural Language Interaction: Engage in natural language conversations by typing queries or questions directly into the provided text input box. Dynamic Response Display: Responses from the system are displayed in real-time
How to Use: Upload Documents: Click on the file uploader to select one or multiple PDF documents containing the information you wish to explore. Initiate the Conversation: Once the documents are uploaded, type your questions or queries into the designated text input area and hit enter. Explore Responses: Instantly receive responses generated by the system, providing insights and information extracted from the uploaded PDF documents. Engage Continuously: Continue the conversation by posing follow-up questions or exploring different topics within the uploaded documents.
Who Can Benefit: Students and Researchers: Quickly extract information from research papers, academic articles, or textbooks. Professionals: Efficiently gather insights from reports, manuals, or documentation relevant to their field. General Users: Easily navigate and retrieve information from various documents in a conversational manner, without the need for extensive reading.
Why Choose This Project: Ease of Use: Our interface requires no prior technical expertise, making it accessible to a wide range of users. Efficiency: Extract information from multiple documents swiftly, saving time and effort in manual searching and reading. Interactivity: Engage in dynamic conversations with the system, promoting an interactive and engaging user experience.
Guidelines for contributing to the project.
- Fork the repository.
- Create a new branch('git checkout -b feature/fooBar').
- Make your changes.
- Commit your changes('git commit -am 'Add some fooBar'').
- Push to the branch('git push origin feature/fooBar'). Create a new Pull Request.