Generate a Private Deep Research on a pipeline

Beta Feature

The API and Deep Research are currently in beta. Features and configuration may change.

Prerequisites

Before you begin, you'll need:

1. A Vectorize account
2. An API access token (create one here)
3. Your organization ID (see below)
4. A pipeline ID (see below)

Finding your Organization ID

Your organization ID is in the Vectorize platform URL:

https://platform.vectorize.io/organization/[YOUR-ORG-ID]

For example, if your URL is:

https://platform.vectorize.io/organization/ecf3fa1d-30d0-4df1-8af6-f4852bc851cb

Your organization ID is: ecf3fa1d-30d0-4df1-8af6-f4852bc851cb

Finding your Pipeline ID

Navigate to your pipeline in the Vectorize platform. The pipeline ID is shown in:

• The URL: https://platform.vectorize.io/organization/[org-id]/pipeline/[PIPELINE-ID]
• The pipeline details page
• The "Connect" tab of your pipeline

Generate the Deep Research

With your pipeline ID ready, you can now start a deep research task. This will analyze your pipeline's data to generate comprehensive insights based on your query.

Python

# Using the pipelines_api from Getting Started
response = pipelines_api.start_deep_research(
    org_id, 
    pipeline_id, 
    v.StartDeepResearchRequest(
        # make sure to include a relevant prompt here
        query="What is the meaning of life?",
        # optionally enable additional search on the web
        web_search=False,
    )
)
research_id = response.research_id

Node.js

const pipelineId = "your-pipeline-id";
const response = await pipelinesApi.startDeepResearch({
    organizationId: orgId,
    pipelineId: pipelineId,
    startDeepResearchRequest: {
        // make sure to include a relevant prompt here
        query: "Generate a report on financial status of company XX",
        // optionally enable additional search on the web
        webSearch: false
    }
});
const researchId = response.researchId;

Get the Deep Research result

Deep Research tasks run asynchronously. Use the research ID returned from the previous step to check the status and retrieve your results.

Python

while True:
    response = pipelines_api.get_deep_research_result(org_id, pipeline_id, research_id)
    if response.ready:
        if response.data.success:
            print(response.data.markdown)
        else:
            print("Deep Research failed:", response.data.error)
        break
    print("Deep Research in progress...")
    time.sleep(5)  # Wait 5 seconds before checking again

Node.js

// Helper function to sleep
const sleep = (ms) => new Promise(resolve => setTimeout(resolve, ms));

while (true) {
    const result = await pipelinesApi.getDeepResearchResult({
        organizationId: orgId,
        pipelineId: pipelineId,
        researchId: researchId
    });
    
    if (result.ready) {
        if (result.data.success) {
            console.log(result.data.markdown);
        } else {
            console.log("Deep Research failed:", result.data.error);
        }
        break;
    }
    
    console.log("Deep Research in progress...");
    await sleep(5000);  // Wait 5 seconds before checking again
}