1. Create an App

Go to your organization Dashboard and start by creating a new App. Give it a name and select type: Chatbot.

chatbot-1

2. Connect to Datasource

A Datasource is a collection of data that will feed your app. You can add multiple files or Data Entities to a Datasource. Connect your app to an existing Datasource or create a new one.

chatbot-2

3. Add Data Entities

A Data Entity is a single file or entry in a Datasource. Accepted file formats are PDF, DOC, DOCX, XLSX, and CSV.

After youโ€™ve added a Data Entity, Metal will create an Index, process the data into chunks, and generate the embeddings that will be used to match the userโ€™s input to the right response.

chatbot-3

4. Deploy your Chatbot

Try out your chatbot with Metalโ€™s open source Chatbot UI. Start by cloning the repo and following the instructions in the README. Youโ€™ll need to add Open AI API Key, and Metalโ€™s API key, Client Id and Index Id to the .env.local file.

chatbot-4

1. Create an App

Go to your organization Dashboard and start by creating a new App. Give it a name and select type: Chatbot.

chatbot-1

2. Connect to Datasource

A Datasource is a collection of data that will feed your app. You can add multiple files or Data Entities to a Datasource. Connect your app to an existing Datasource or create a new one.

chatbot-2

3. Add Data Entities

A Data Entity is a single file or entry in a Datasource. Accepted file formats are PDF, DOC, DOCX, XLSX, and CSV.

After youโ€™ve added a Data Entity, Metal will create an Index, process the data into chunks, and generate the embeddings that will be used to match the userโ€™s input to the right response.

chatbot-3

4. Deploy your Chatbot

Try out your chatbot with Metalโ€™s open source Chatbot UI. Start by cloning the repo and following the instructions in the README. Youโ€™ll need to add Open AI API Key, and Metalโ€™s API key, Client Id and Index Id to the .env.local file.

chatbot-4