370
edits
Vector database: Difference between revisions
no edit summary
(Created page with "==Introduction== A vector database is a type of database specifically designed for storing and querying high-dimensional vector data, which is often used in artificial intelligence applications (AI apps). These databases are gaining popularity due to their ability to extend large language models (LLMs) with long-term memory and provide efficient [[querying\\ for AI-driven applications. ==Vector Embeddings== Vectors are arrays of n...") |
No edit summary |
||
| Line 1: | Line 1: | ||
==Introduction== | ==Introduction== | ||
A [[vector database]] is a type of [[database]] specifically designed for storing and querying [[high-dimensional vector data]], which is often used in [[artificial intelligence applications]] ([[AI]] [[apps]]). These databases are gaining popularity due to their ability to extend [[large language models]] ([[LLMs]]) with [[long-term memory]] and provide efficient [[querying | A [[vector database]] is a type of [[database]] specifically designed for storing and querying [[high-dimensional vector data]], which is often used in [[artificial intelligence applications]] ([[AI]] [[apps]]). These databases are gaining popularity due to their ability to extend [[large language models]] ([[LLMs]]) with [[long-term memory]] and provide efficient [[querying]] for AI-driven applications. | ||
==Vector Embeddings== | ==Vector Embeddings== | ||
[[Vector]]s are arrays of numbers that can represent complex objects such as words, sentences, images, or audio files in a | [[Vector]]s are arrays of numbers that can represent complex objects such as [[words]], [[sentences]], [[images]], or [[audio]] files in a [[continuous high-dimensional space]], called an [[embedding]]. [[Embeddings]] work by mapping [[semantically similar]] words or features from various data types together. These embeddings can be used in [[recommendation systems]], [[search engines]], and [[text generation applications]] like [[ChatGPT]]. | ||
==Database | ==Database Structure== | ||
In a relational database, data is organized in rows and columns, while in a document database, it is organized in documents and collections. In contrast, a vector database stores arrays of numbers that are clustered based on similarity. These databases can be queried with ultra-low latency, making them ideal for AI-driven applications. | In a [[relational database]], data is organized in rows and columns, while in a [[document database]], it is organized in documents and collections. In contrast, a vector database stores arrays of numbers that are clustered based on [[similarity]]. These databases can be queried with [[ultra-low latency]], making them ideal for AI-driven applications. | ||
==Vector Database Solutions== | |||
Several vector databases have emerged to cater to the growing demand for AI applications. Some of the popular native vector databases include open-source options like [[Weaviate]] and [[Milvus]], both written in Go. [[Pinecone]] is another popular vector database, although it is not open source. [[Chroma]], based on Clickhouse, is an open-source project with a growing following. Relational databases like Postgres have tools like pgVector, and Redis has first-class vector support to accommodate this type of functionality. | Several vector databases have emerged to cater to the growing demand for AI applications. Some of the popular native vector databases include open-source options like [[Weaviate]] and [[Milvus]], both written in Go. [[Pinecone]] is another popular vector database, although it is not open source. [[Chroma]], based on Clickhouse, is an open-source project with a growing following. Relational databases like Postgres have tools like pgVector, and Redis has first-class vector support to accommodate this type of functionality. | ||
== Using Vector Databases with Large Language Models == | ==Using Vector Databases with Large Language Models== | ||
One of the primary reasons for the increasing popularity of vector databases is their ability to extend large language models (LLMs) with long-term memory. By providing a general-purpose model, such as OpenAI's GPT-4, Meta's LLMA, or Google's Lambda, users can store their own data in a vector database. When prompted, the database can query relevant documents to update the context, customizing the final response and providing the AI with long-term memory. | One of the primary reasons for the increasing popularity of vector databases is their ability to extend large language models (LLMs) with long-term memory. By providing a general-purpose model, such as OpenAI's GPT-4, Meta's LLMA, or Google's Lambda, users can store their own data in a vector database. When prompted, the database can query relevant documents to update the context, customizing the final response and providing the AI with long-term memory. | ||
In addition, vector databases can integrate with tools like LangChain, which combine multiple LLMs together for more advanced applications. | In addition, vector databases can integrate with tools like LangChain, which combine multiple LLMs together for more advanced applications. | ||
== Example Code == | ==Example Code== | ||
To demonstrate the usage of a vector database, the following example shows how to use Chroma with JavaScript. First, create the client and define an embedding function. In this case, the OpenAI API is used to update the embeddings whenever a new data point is added. Each data point is a document with an ID and some text. The database can be queried by passing a string of text, and the result includes the data along with an array of distances, where smaller numbers indicate higher degrees of similarity. | To demonstrate the usage of a vector database, the following example shows how to use Chroma with JavaScript. First, create the client and define an embedding function. In this case, the OpenAI API is used to update the embeddings whenever a new data point is added. Each data point is a document with an ID and some text. The database can be queried by passing a string of text, and the result includes the data along with an array of distances, where smaller numbers indicate higher degrees of similarity. | ||
== Related Developments == | ==Related Developments== | ||
The growing interest in vector databases can be seen in the top trending repositories on GitHub, with many of them focusing on creating artificial general intelligence. Examples include Microsoft's Jarvis, AutoGPT, and BabyAGI, which are tools that use vector databases and LLMs to prompt themselves and expand their capabilities. | The growing interest in vector databases can be seen in the top trending repositories on GitHub, with many of them focusing on creating artificial general intelligence. Examples include Microsoft's Jarvis, AutoGPT, and BabyAGI, which are tools that use vector databases and LLMs to prompt themselves and expand their capabilities. | ||