Get Started
API Reference
- Chunk
- Extract
- Embeddings
Chunk document
Chunk a document.
curl --request POST \
--url https://api.aurelio.ai/v1/chunk \
--header 'Content-Type: application/json' \
--header 'authorization: <api-key>' \
--data '{
"content": "<string>",
"processing_options": {
"max_chunk_length": 400,
"chunker_type": "regex",
"window_size": 1,
"delimiters": []
}
}'
{
"status": "pending",
"usage": {
"tokens": 123,
"pages": 123,
"seconds": 123
},
"message": "<string>",
"processing_options": {
"max_chunk_length": 400,
"chunker_type": "regex",
"window_size": 1,
"delimiters": []
},
"document": {
"id": "<string>",
"content": "<string>",
"source": "<string>",
"source_type": "application/pdf",
"num_chunks": 123,
"metadata": {},
"chunks": []
},
"uploaded_urls": {
"original_file": "<string>",
"result_html": "<string>",
"result_json": "<string>",
"result_markdown": "<string>"
}
}
Authorizations
Body
Input text to chunk.
The processing options for the chunker
The maximum chunk length for the chunker
The chunker type, either semantic or regex
semantic
, regex
The window size for the semantic chunker
Optional. The regex delimiters for the regex chunker
Response
Extended response payload for chunking
The status of the chunking process
pending
, completed
, failed
The processing options for the chunker
The maximum chunk length for the chunker
The chunker type, either semantic or regex
semantic
, regex
The window size for the semantic chunker
Optional. The regex delimiters for the regex chunker
ID of the document
Content of the document
Source of the document
Type of the document e.g. video/mp4, application/pdf
application/pdf
, text/plain
, video/mp4
Total number of chunks in the document
Metadata for users
Chunks of the document
ID of the chunk
Content of the chunk
Index of the chunk in the document
Number of tokens in the chunk
Metadata of the chunk
Message
Uploaded URLs
URL of the uploaded file
GCP URL of the result HTML
GCP URL of the result JSON
GCP URL of the result Markdown
curl --request POST \
--url https://api.aurelio.ai/v1/chunk \
--header 'Content-Type: application/json' \
--header 'authorization: <api-key>' \
--data '{
"content": "<string>",
"processing_options": {
"max_chunk_length": 400,
"chunker_type": "regex",
"window_size": 1,
"delimiters": []
}
}'
{
"status": "pending",
"usage": {
"tokens": 123,
"pages": 123,
"seconds": 123
},
"message": "<string>",
"processing_options": {
"max_chunk_length": 400,
"chunker_type": "regex",
"window_size": 1,
"delimiters": []
},
"document": {
"id": "<string>",
"content": "<string>",
"source": "<string>",
"source_type": "application/pdf",
"num_chunks": 123,
"metadata": {},
"chunks": []
},
"uploaded_urls": {
"original_file": "<string>",
"result_html": "<string>",
"result_json": "<string>",
"result_markdown": "<string>"
}
}