Interactive Preview
Hospitality
Chatbot with function calling
Here's how you can implement a chatbot that can perform actions for your employees or customers.
Input Variables
id
1224 2012 122
request
We ran out of fish, please remove it from the menu
Responses
Run
Run the prompt to see the model response...
Classify whether you need to collect more info from user to perform an action.
Continue to ask questions if needed, to capture all information needed before the agent takes an action.
Once all information is provided, the agent proceeds to do the action and outputs a JSON object that can trigger a specific action in the code.
1{
2
3"arguments": { "item_name": "fish" },
4"id": "call_oHBcnSzrf97vBO8WcCMv9jYY",
5"name": "remove_item",
6"state": "FULFILLED"
7
8}How it works
step
1
Classify user need
step
2
Gather more info
step
3
Perform action
Tools used
Tools
Chat
Data Extraction
Function calling
Parser
Customize this workflow
1/ Add your style and tone
2/ Integrate with your system
3/ Use out of box RAG
4/ Add custom evaluation metrics
5/ Use different models
See what else you can build
SaaS
Q&A across knowledge bases
Process documents with OCR, test different search strategies, and orchestrate multiple agents to work together to answer questions.
Recruitment
Convert Resume to JSON
Upload a resume, extract qualifications into JSON, and seamlessly map them to your app's UI fields.
Experiment, Evaluate, Deploy, Repeat.
AI development doesn’t end once you've defined your system. Learn how Vellum helps you manage the entire AI development lifecycle.
Talk with us
