Skip to main content

Documentation Index

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

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

These endpoints add data to your Cognee Cloud tenant. All require authentication via API key. For the underlying concepts, see Remember and Add.

​
Remember

POST /api/v1/remember — Ingest data and build the knowledge graph in a single call. Combines the add and cognify steps. Equivalent to calling cognee.remember() in the Python SDK. Accepts multipart form data. 
curl -X POST https://your-tenant.aws.cognee.ai/api/v1/remember \
  -H "X-Api-Key: your-key" \
  -F "data=@document.pdf" \
  -F "datasetName=my_dataset"
ParameterTypeRequiredDescription
datafile(s)yesOne or more files to upload
datasetNamestringnoTarget dataset name
datasetIdUUIDnoExisting dataset UUID
session_idstringnoSession identifier for grouping operations
node_setstring[]noNode identifiers
run_in_backgroundbooleannoRun asynchronously (default: false)
custom_promptstringnoCustom extraction prompt
chunks_per_batchintegernoChunks per batch (default: 10)
For most workflows, remember is the simplest entry point — it handles ingestion and graph building in one call. Use the lower-level add + cognify separately when you need to upload multiple files before triggering processing.

​
Lower-level operations

The following endpoints provide more granular control over data ingestion. Most users should prefer remember above.

​
Add

POST /api/v1/add — Upload files to a dataset without processing. Accepts multipart form data. Files are stored in the dataset but not yet processed into the knowledge graph — call cognify separately. 
curl -X POST https://your-tenant.aws.cognee.ai/api/v1/add \
  -H "X-Api-Key: your-key" \
  -F "data=@document.pdf" \
  -F "datasetName=my_dataset"
Supported file types: PDF, CSV, TXT, Markdown, JSON, DOCX.

​
Update

PATCH /api/v1/update — Replace an existing document in a dataset. Accepts multipart form data. Requires both the data item ID and dataset ID as query parameters. 
curl -X PATCH "https://your-tenant.aws.cognee.ai/api/v1/update?data_id=<uuid>&dataset_id=<uuid>" \
  -H "X-Api-Key: your-key" \
  -F "data=@updated_document.pdf"
ParameterLocationTypeRequiredDescription
data_idqueryUUIDyesID of the document to replace
dataset_idqueryUUIDyesID of the dataset containing the document
dataformfile(s)yesReplacement file(s)
node_setformstring[]noNode identifiers