SearchImage is a Streamlit-based application that allows users to search text from Image/PDF file using LLM. The App extracts information from uploaded Image/Pdf file and get the data focused by user.
- Image/PDF Upload: Users can upload Images or PDF files.
- Text Extraction: Extracts text from uploaded PDF files.Show the data focused by user.
Note: This project requires Python 3.10 or higher.
-
Clone the Repository:
git clone https://github.com/your-username/searchimage.git
-
Install Dependencies:
pip install -r requirements.txt
-
Set up API Key:
- Obtain a Google API key and set it in the
.env
file.
GOOGLE_API_KEY=your_api_key_here - Obtain a OpenAI API key and set it in the `.env` file. ```bash OPENAI_API_KEY = "sk-
- Obtain a Google API key and set it in the
-
install mongodb in docker: install_stores.bat
-
Run the Application:
streamlit run app.py
Home.py
: Main application script..env
: file which will contain your environment variable.requirements.txt
: Python packages required for working of the app.README.md
: Project documentation.
- PyMuPDF
- Streamlit
- google.generativeai
- dotenv
- unstructured
- unstructured.paddleocr
- Google Gemini: For providing the underlying language model.
- Streamlit: For the user interface framework.