> For the complete documentation index, see [llms.txt](https://agenticai.kasinathanramesh.vip/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://agenticai.kasinathanramesh.vip/section-1-introduction-to-agentic-ai-and-llm-ecosystem/vector-database-explained.md).
# Vector Database Explained
**`Semantic search`** - **Based on the input it will understand and provide the result.**
**Semantic search is a search technique that aims to understand the meaning and intent behind a user's search query, rather than just matching keywords.**
**It leverages techniques like natural language processing (NLP) and machine learning to grasp the context and relationships between words, delivering more relevant results.**
**`Example: if i search this keyword in google "Speed of Jaguar" - will get the Jaguar animal related answers`**
**`Example: if i search this keyword in google "Top Speed of Jaguar" - will get the Jaguar car related answers`**
**`Word Embedding`** - **Coverting the word to numbers is called word embedding or word to vecotr or word to vec.**
**Word embeddings are a way to represent words as numerical vectors, allowing computers to understand and process the meaning and relationships between words.**
**This technique is crucial in natural language processing (NLP) as it transforms text into a format that machine learning models can utilize.**
**Vector - To identify the distance and direction between points (One to another)**
**Vector Search - Vector search is a method for finding items in a dataset that are similar to a given query, by representing those items as numerical vectors and comparing their similarity.**
**This approach is particularly useful for datasets where the meaning or context of the data is important, as opposed to traditional keyword-based searches.**
- **Used to visualize one word to another word distance.**
**Vector Database**** - A vector database is a specialized database designed to store and manage data as vectors, which are numerical representations of data points.**
**These vectors capture semantic meaning, making it easier for machine learning models to perform similarity searches, recommendations, and other tasks that rely on understanding relationships between data. Essentially, vector databases are built to handle unstructured data like text, images, and audio by converting them into a format that can be easily compared and analysed.**
### `Vector Search Architecture in RAG application development`
Chunking - To extract the PDF file and separate the small small parts of extracted text/words.
Encoder - Each chunks are converted from word to numbers using encoders. Encoders will be available any LLMs.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://agenticai.kasinathanramesh.vip/section-1-introduction-to-agentic-ai-and-llm-ecosystem/vector-database-explained.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.