Params

Body

Response

REST API

Examples

Metal

Contact

Add Memory

Metal is your production ready, fully-managed, LLM retrieval engine.

Welcome

Metal is an ETL and Retrieval Engine for LLM driven experiences

What is Metal?

Metal Retrieval allows you to utilize AI on your data. 

AI Retrieval

Metal Memory enables you to give your users LLM session history.

AI Memory

Metal Attribute Extraction allows you to easily pull and organize information from unstructured data.

AI Extraction

Quickstart

Extracting attributes from documents and other unstructured data.

Attribute Extraction

Build a custom chatbot on your data in just a few steps

Chatbot

Build semantic search on your data in just a few steps

Semantic Search

Node SDK

Python SDK

Familiarize with resources, response codes, and authentication.

Introduction

This endpoint retrieves the current API key information for the authenticated user.

Current API Key

This endpoint retrieves the current organization's information.

Current Organization

This endpoint retrieves a list of queries related to a specific index, sorted by time and limited to the last 100 queries.

List Queries

Add an App

This endpoint retrieves the details of an app by its ID.

Get an App

This endpoint retrieves a list of all apps for the specified organization

Get All Apps

This endpoint updates an existing app based on the provided App ID.

Update an App

Add a Data Entity

This endpoint retrieves a Data Entity by its ID

Get Data Entity

This endpoint retrieves a list of all data entities.

List Data Entities

This endpoint deletes a specific data entity by its ID.

Delete Data Entity

This endpoint creates and stores a Datasource with the provided details.

Add a Datasource

This endpoint retrieves the details of a specific Datasource by its ID.

Get Datasource

This endpoint retrieves a list with all Datasources available for the authenticated org.

List Datasources

This endpoint updates the details of an existing Datasource by its ID.

Update Datasource

This endpoint deletes a Datasource by its ID.

Delete Datasource

This endpoint generates and stores a Document(embedding) with the inputted data.

Add Document

This endpoint generates and stores a Document(embedding) with the inputted data in bulk.

Add Documents (bulk)

This endpoint updates and replaces an existing Document(embedding).

Update Document

Semantically search your embedded documents.

Search Documents

This endpoint gets an embedding document.

Get Document

This endpoint gets a list of documents for a given index.

List Documents

This endpoint deletes an embedding document.

Delete Document

This endpoint deletes multiple embedding documents.

Delete Documents (bulk)

This endpoint creates an index for an app.

Add Index

Get Index

This endpoint gets a list of indexes for an app.

List Indexes

Update Index

This endpoint deletes an index and all documents within that index.

Delete Index

Observability and analytics for your application

Analytics

Integrate Metal into your existing stack.

Integrations

Limits & Plans

Logs

Get started in minutes with our chatbot starter kit built with Next.js.

Chatbot Starter Kit

Indexes in Metal represent a particular ML based experience (eg Video Ranking).

Add an Index

Analyze User Queries

Build a custom chatbot on your data in just a few steps.

Build a Chatbot

Build a semantic search engine with Metal.

Build Semantic Search

Build a LLM retrieval pipeline with Metal (RAG)

Create a Retrieval Pipeline

How to configure chunking for your indexes

Chunking Configuration

API Keys are used to authenticate requests to the Metal API and SDKs.

Generate an API Key

How to archive and unarchive indexes in Metal

Index Archiving

Identify and retrieve specific pieces of information from unstructured data and transform them into a structured format.

Overview

🔑 Account

📈 Analytics

🚀 Apps

📄 Data Entities

🗄️ Datasources

🧬 Embedding Documents

🔗 Indexes

Add Memory

Params

Body

Response

Overview

🔑 Account

📈 Analytics

🚀 Apps

📄 Data Entities

🗄️ Datasources

🧬 Embedding Documents

🔗 Indexes

​Params

​Body

​Response

Params

Body

Response