44 lines
1.2 KiB
Markdown
44 lines
1.2 KiB
Markdown
```c title="C"
|
|
#include "kreuzberg.h"
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
|
|
int main(void) {
|
|
const char *config_json =
|
|
"{"
|
|
"\"chunking\": {"
|
|
"\"chunker_type\": \"markdown\","
|
|
"\"max_characters\": 500,"
|
|
"\"overlap\": 50,"
|
|
"\"prepend_heading_context\": 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): %s\n", chunks_json ? chunks_json : "[]");
|
|
kreuzberg_free_string(chunks_json);
|
|
|
|
kreuzberg_extraction_result_free(result);
|
|
kreuzberg_extraction_config_free(config);
|
|
return 0;
|
|
}
|
|
```
|