PipelineRun class - checkpoint()

TypeScript

Python

The PipelineRun class captures the generative output for a unique invocation of a generative pipeline. checkpoint() is a method under this class.

checkpoint()

checkpoint() tracks the inputs, outputs, and duration it takes to run a step in a generative pipeline relative to the last time checkpoint() was called.

Arguments

inputs

Rather than passing inputs to a measured function, with checkpoint() you must directly specify the inputs to the step.

outputs

The outputs that you want to track for that checkpoint.

typescript

stepInfo

python

step_info

An object containing additional information about the step. The most important key/value pair in the stepInfo is the context key, which attaches more metadata to the step.

Read about the typing for the context key here.

Examples

typescript

typescript
import { init, Pipeline } from "@gentrace/core";
import { initPlugin as initOpenAIPlugin } from "@gentrace/openai";
import { User } from "../models";
 
// This function globally initializes Gentrace with the appropriate 
// credentials. Constructors like Pipeline() will transparently use
// these credentials to authenticate with Gentrace.
init({
  apiKey: process.env.GENTRACE_API_KEY
});
 
const openaiPlugin = await initOpenAIPlugin({
  apiKey: process.env.OPENAI_KEY,
});
 
const pipeline = new Pipeline({
  slug: "create-embedding",
  plugins: {
    openai: openaiPlugin,
    pinecone: pineconePlugin
  },
});
 
const runner = pipeline.start()
 
const openai = runner.openai;
 
const userId = "550e8400-e29b-41d4-a716-446655440000";
const gentraceOrgId = "c9a646d3-9c61-4cb7-bfcd-ee2522c8f633";
 
// Custom application logic
const user = await User.findOne({
  where: {
    id: userId,
    orgId: gentraceOrgId,
  }
});
 
const name = user.name;
 
runner.checkpoint({
  inputs: { userId, orgId: gentraceOrgId },
  outputs: { name },
});
 
const embeddingResponse = await openai.embeddings.create({
  model: 'text-embedding-ada-002',
  input: `Human, software engineer, Gentrace: ${name}!`,
});
 
await runner.submit();

python

python
import gentrace
import os
# TODO: replace with your own function that you want to benchmark with checkpoint()
from db_utils import get_organization_usernames
pipeline = gentrace.Pipeline(
    slug="example-pipeline",
    openai_config={
        "api_key": os.environ["OPENAI_API_KEY"],
    }
)
runner = pipeline.start()
usernames = get_organization_usernames(organization_id),
runner.checkpoint({
    "inputs": {
        "organization_id": organization_id,
    },
    "outputs": {
        "usernames": usernames,
    },
})
openai = runner.get_openai()
initial_draft_response = openai.ChatCompletion.create(
    messages=[
        {
            "role": "system",
            "content": f"Write an email on behalf of {sender} to the members of organization {organization_name}. These are the names of the members: {usernames.join(", ")}"
        },
    ],
    model="gpt-3.5-turbo"
)
initial_draft = initial_draft_response.choices[0].message.content
runner.submit()
return [initial_draft, runner]