Skip to main content

Using the REST API

The LlamaExtract API directly can be used with any language that can make HTTP requests. Here are some sample calls:

Upload the files​

curl -X 'POST' \
  'https://api.cloud.llamaindex.ai/api/v1/files' \
  -H 'accept: application/json' \
  -H 'Content-Type: multipart/form-data' \
  -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \
  -F 'upload_file=@/path/to/your/file.pdf;type=application/pdf'

Infer and create a schema​

curl -X 'POST' \
  'https://api.cloud.llamaindex.ai/api/v1/extraction/schemas/infer' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \
  -d '{"name":"Schema Name","file_ids":["<file_id_1>", "<file_id_2>"]}'

Start an extraction job​

curl -X 'POST' \
  'https://api.cloud.llamaindex.ai/api/v1/extraction/jobs' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \
  -d '{"schema_id":"<schema_id>","file_id":"<file_id_1>"}'

Or in batch:

curl -X 'POST' \
  'https://api.cloud.llamaindex.ai/api/v1/extraction/jobs/batch' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \
  -d '{"schema_id":"<schema_id>","file_ids":["<file_id_1>", "<file_id_2>"]}'

Check the status of the extraction job:​

curl -X 'GET' \
  'https://api.cloud.llamaindex.ai/api/v1/extraction/jobs/<job_id>' \
  -H 'accept: application/json' \
  -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY"

Get the results​

curl -X 'GET' \
  'https://api.cloud.llamaindex.ai/api/v1/extraction/jobs/<job_id>/result' \
  -H 'accept: application/json' \
  -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY"

You can see all the available endpoints in our full API documentation.