Semantic Search AI is an advanced search engine powered by artificial intelligence (AI) that enables users to find relevant information based on the meaning and context of their queries.
Semantic Search: The project enables users to perform semantic searches, allowing them to retrieve search results based on the meaning and context of their queries.
PDF Processing: It includes functionality for processing PDF documents, extracting text content, and preparing it for search indexing.
Pinecone Vector Database: Semantic Search AI integrates with Pinecone, a vector database, to store and retrieve vector embeddings efficiently.
OpenAI Embeddings: The project leverages OpenAI for generating vector embeddings, which encode the semantic information of documents.
semantic_search_ai.ipynb: This Jupyter Notebook file contains the Python code for the Semantic Search AI project. It includes the necessary dependencies, PDF processing, text splitting, vector embeddings, and search functionality.
index.html: This HTML file represents the user interface of the Semantic Search Engine. It provides a search form for users to enter their queries and displays the search results.
Here are a few examples of how to use Semantic Search AI:
-
Enter a natural language query like "What are the time complexities of sorting algorithms?" to retrieve relevant results from the vector database.
-
Use the query "Find information about graph traversal algorithms in DAA by CSLR.pdf" to retrieve specific information from the referenced PDF document.
Contributions to the Semantic Search AI project are welcome. If you find any issues or have suggestions for improvements, please feel free to submit a pull request or open an issue on the GitHub repository.
This project is licensed under the MIT License.