Webscrapping

Overview

Use a flow that summarizes a website and finds the best page for you query

Web Scraping

Web scraping is a technique used to extract large amounts of data from websites, allowing for automated collection of information using various tools and programming languages. It's widely utilized for data analysis, research, and

Prompt Engineering

Well Known LLMs indexed webiste (bot protection may affect the result)

Get the latest news in the new york times

Specific url

Get the resume of the latest news in descubre.vc

Unknown or google search specification

Search for the best electric service in mexico city and get the contact info

Usage

Leverage Base to easily design your API and prototype apps, UX, or screens. To experiment with different outcomes, set "cached" to false

Using /base with "cached" is equivalent to direclty calling the function after is creation, all none neccesary params will be ignored.

POST /base

Creates a new flow with one or more actions, installs dependencies, builds tests and executes the resulting code.

Actions can be agents, backend functions, or cloud functions.

Headers

Name	Value
Content-Type	application/json
Authorization	Bearer <token>

Body

Name	Type	Required	Description
name	string		Name of the flow to summarize the actions
prompt	string		The instructions for AgentBase to transform in to code
data	object		The data example or parameters for your function to work
schedule	string		The cron calendar for the function to run automatically
return	object		The data example of your expected return
model	string		The model to run for your prompt
errors	array		List or possible errors your function needs to catch
cached	boolean		It will use the last version of the function whenever is available to save time and tokens

Response

200

{
  "run_id": 1,
  "return": {
    "news_count" : 44
  },
  "error": null
}

400

Body Example

{
    "function": "get_news",
    "prompt": "obtain the lastest news in descubre.vc and save them in the database",
    "data" : {
    },
    "return" : {
     "news_count" : "count"
    }
}