You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 2 Next »


DRAFT SPEC | Services are in active development and are subject to change


The Charity Engine Smart Proxy Post Processing (SP3) interface allows web data that is collected via Smart Proxy scripts to be processed by any application or execution environment available on the Charity Engine network. This processing takes place on the same node that collects the data.



General Usage

To submit data for local processing on the proxy node, include the charityengine module in a smart proxy script and call the desired processing function. See the Charity Engine Application Library for details on the specific functionality of applications or execution environments.

Processing functions return a Promise object, which resolves with the response from the model or application.

For example, to generate embeddings for text collected  using the Llama3.2 model:

charityengine.embeddings('llama3.2:3b', 'What is the weather')
  .then(response => console.log('Embedding response:', response))
  .catch(error => console.error('Error:', error));

To generate a chi-squared distribution with v degrees of freedom using Wolfram Engine:

charityengine.wolframengine('ChiSquareDistribution[v]')
  .then(response => console.log('Response:', response))
  .catch(error => console.error('Error:', error));

Processing Functions

A variety of post-processing functions are available based on applications that are compatible with the Charity Engine network. 

docker

Any image that can be pulled from Docker Hub can be used for post-processing by calling the docker() function:

charityengine.docker(image, commandline, inputfile)
PARAMETERS
  image // Name of the Docker image to run [string] [required]
  commandline // Command to execute within the container [string] [required]
  inputfile // Names of local files to use as input [array of string]

vina

charityengine.vina(commandline, inputfile)
PARAMETERS
  commandline // Command line for the application [string] [required]
  inputfile // Names of local files to use as input [array of string]

blastp

charityengine.blastp(commandline, inputfile)
PARAMETERS
  commandline // Command line for the application [string] [required]
  inputfile // Names of local files to use as input [array of string]

wolframengine

charityengine.wolframengine(commandline, inputfile)
PARAMETERS
  commandline // Command to execute within the application [string] [required]
  inputfile // Names of local files to use as input [array of string]

inference

charityengine.inference(model, prompt, assets, context, system, template, options)
PARAMETERS
  model // Name of the model to use [string] [required]
  prompt // Text to pass to the model as input [string] [required]
  assets // Images or files [array of string]
  context // Additional context for the model [string]
  system // System parameters for the model [string]
  template // Template to guide response format [string]
  options // Additional options for the request [object]

embeddings

charityengine.embeddings(model, prompt)
PARAMETERS
  model // Name of the model to use [string] [required]
  prompt // Text to pass to the model as input [string] [required]


  • No labels