Overview
Pinecone makes it easy to build high-performance vector search applications. With a managed, cloud-native vector database, a simple API, and no complex infrastructure management, development of custom search functionality is easier than ever. Unlike traditional search methods that revolve around keywords, vector databases index and search through ML-generated representations of data, called vector embeddings, to find items most similar to the query.
Pinecone indexes and stores vector embeddings for efficient management and fast retrieval. Unlike a standalone vector index, a vector database like Pinecone provides additional capabilities such as index management, data management, metadata storage and filtering, and horizontal scaling.
By utilizing the Pinecone connected system, you can take advantage of Appian’s powerful process automation capabilities and access the knowledge you need quickly and effectively. It will help make your already powerful Appian applications more efficient in executing on your vision.
Use this plugin in conjunction with your choice of large language model to build your own custom chatbot! By vectorizing your data and storing it in Pinecone, you can easily receive contextually relevant data based on a user’s query, then feed this data and the user’s query into a large language model to get a response sourced directly from your data. With this plugin, custom chatbots are now easier than ever to build.
Key Features & Functionality
Pinecone no longer requires the environment to be part of the connection. Our latest SDKs all connect to a global control plane instead. This means a single project can now host indexes in different environments/cloud regions, and you only need to set the API key to use your indexes.
Which platform are you using to connect to Pinecone? We can reach out to those folks and make sure they’re using the latest Pinecone SDKs to remove this requirement of knowing the environment.