Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.meibel.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Data Elements

Data elements are the individual pieces of knowledge extracted from your datasource files during ingestion. Each element represents a discrete chunk of content (a paragraph, table, figure, or section) that agents can retrieve and cite. This guide covers listing, searching, inspecting, and updating data elements.

​
List data elements

Retrieve all data elements for a datasource. Results are paginated automatically by the SDK iterator. 
import os
from meibel import MeibelClient

client = MeibelClient(api_key=os.environ["MEIBEL_API_KEY"])

for element in client.data_elements.list_data_elements(datasource_id="ds_123"):
    print(f"{element.id}: {element.content[:80]}...")
The iterator handles cursor-based pagination transparently. Each element includes id, content, metadata, and source file information.

​
Get a data element

Retrieve the full details of a specific data element, including its content, metadata, and source location. 
element = client.data_elements.get_data_element(
    datasource_id="ds_123",
    data_element_id="de_456",
)

print(element.id)
print(element.content)
print(element.source_file)
print(element.metadata)

​
Search data elements

Search across data elements within a datasource using semantic or keyword queries. This is useful for previewing what an agent would retrieve for a given question. 
from meibel.models import DataElementSearchRequest

results = client.data_elements.search_data_elements(
    datasource_id="ds_123",
    body=DataElementSearchRequest(
        regex_filter="quarterly revenue",
    ),
)

for result in results:
    print(f"[{result.score:.2f}] {result.content[:100]}...")
Each result includes a relevance score, the element content, and its id for further inspection. Higher scores indicate stronger matches.

​
Update a data element

Modify a data element’s content or metadata. This is useful for correcting extraction errors or enriching elements with additional context. 
from meibel.models import UpdateDataElementRequest

updated = client.data_elements.update_data_element(
    datasource_id="ds_123",
    data_element_id="de_456",
    body=UpdateDataElementRequest(
        content="Corrected content with accurate figures for Q4 2025.",
        metadata={"reviewed": True, "reviewer": "finance-team"},
    ),
)

print(updated.id)
print(updated.content)
Updating a data element’s content triggers re-embedding so that search results reflect the new content. This happens automatically in the background.