Files
fil/docs/snippets/c/advanced/chunk_page_mapping.md
Henrik Jess Nielsen b4c07d3693
All checks were successful
Deploy fil (kreuzberg) / deploy (push) Successful in 49s
Nomad changes
2026-06-01 23:40:55 +02:00

51 lines
1.5 KiB
Markdown

```c title="C"
#include "kreuzberg.h"
#include <stdio.h>
#include <stdlib.h>
int main(void) {
const char *config_json =
"{"
"\"chunking\": {"
"\"chunker_type\": \"character\","
"\"max_characters\": 500,"
"\"overlap\": 50"
"},"
"\"pages\": {"
"\"extract_pages\": true"
"}"
"}";
KREUZBERGExtractionConfig *config = kreuzberg_extraction_config_from_json(config_json);
if (!config) {
fprintf(stderr, "config parse failed (code %d): %s\n",
kreuzberg_last_error_code(),
kreuzberg_last_error_context());
return 1;
}
KREUZBERGExtractionResult *result =
kreuzberg_extract_file_sync("document.pdf", NULL, config);
if (!result) {
fprintf(stderr, "extraction failed (code %d): %s\n",
kreuzberg_last_error_code(),
kreuzberg_last_error_context());
kreuzberg_extraction_config_free(config);
return 1;
}
char *chunks_json = kreuzberg_extraction_result_chunks(result);
printf("chunks (JSON, includes per-chunk first_page/last_page metadata):\n%s\n",
chunks_json ? chunks_json : "[]");
kreuzberg_free_string(chunks_json);
char *pages_json = kreuzberg_extraction_result_pages(result);
printf("pages (JSON): %s\n", pages_json ? pages_json : "[]");
kreuzberg_free_string(pages_json);
kreuzberg_extraction_result_free(result);
kreuzberg_extraction_config_free(config);
return 0;
}
```