diff --git a/ai_research/ML_Fundamentals/vector_databases.md b/ai_research/ML_Fundamentals/vector_databases.md
index 31dcc70..1e35729 100644
--- a/ai_research/ML_Fundamentals/vector_databases.md
+++ b/ai_research/ML_Fundamentals/vector_databases.md
@@ -4,26 +4,13 @@ Vector databases are specialized systems designed to store, retrieve, and search
 
 ### Examples of Vector Databases
 
-1. **[FAISS (Facebook AI Similarity Search)](https://github.com/facebookresearch/faiss)**
-   - FAISS is a high-performance library optimized for dense vector similarity search and clustering. It uses techniques like quantization and partitioning to enhance search efficiency[1].
-
-2. **[ChromaDB](https://www.trychroma.com/)**
-   - Chroma is an open-source embedding database that facilitates the creation of large language model (LLM) applications by allowing easy management of text documents and similarity searches[2].
-
-3. **[Pinecone](https://www.pinecone.io/)**
-   - Pinecone is a managed vector database platform designed for high-dimensional data. It offers features like real-time data ingestion and low-latency search, making it suitable for large-scale machine learning applications[2][4].
-
-4. **[MongoDB Atlas Vector Search](https://www.mongodb.com/products/platform/atlas-vector-search)**
-   - MongoDB Atlas integrates vector search capabilities with its core database, allowing for semantic search and generative AI applications. It provides a specialized vector index that can operate independently of the main database infrastructure[4][5].
-
-5. **[Weaviate](https://weaviate.io/)**
-   - Weaviate is an open-source vector database that supports various AI applications, offering features like faceted search and integration with existing infrastructures[3].
-
-6. **[Qdrant](https://qdrant.tech/)**
-   - Qdrant is a simple vector database known for its ease of use and a free-tier option. It is designed to handle vector data efficiently[3].
-
-7. **[Milvus](https://milvus.io/)**
-   - Milvus is an open-source vector database capable of handling large-scale vector data with low latency, making it suitable for production environments[3].
+- **[FAISS (Facebook AI Similarity Search)](https://github.com/facebookresearch/faiss)**
+- **[ChromaDB](https://www.trychroma.com/)**
+- **[Pinecone](https://www.pinecone.io/)**
+- **[MongoDB Atlas Vector Search](https://www.mongodb.com/products/platform/atlas-vector-search)**
+- **[Weaviate](https://weaviate.io/)**
+- **[Qdrant](https://qdrant.tech/)**
+- **[Milvus](https://milvus.io/)**
 
 These databases provide the infrastructure needed to support advanced AI and machine learning applications by enabling efficient vector storage and retrieval.