35 lines
949 B
Markdown
35 lines
949 B
Markdown
|
```zig title="Zig"
|
||
|
|
const std = @import("std");
|
||
|
|
const kreuzberg = @import("kreuzberg");
|
||
|
|
|
||
|
|
pub fn main() !void {
|
||
|
|
var gpa = std.heap.GeneralPurposeAllocator(.{}){};
|
||
|
|
defer _ = gpa.deinit();
|
||
|
|
const allocator = gpa.allocator();
|
||
|
|
|
||
|
|
const config_json =
|
||
|
|
\\{
|
||
|
|
\\ "chunking": {
|
||
|
|
\\ "max_characters": 1000,
|
||
|
|
\\ "overlap": 200,
|
||
|
|
\\ "embedding": {
|
||
|
|
\\ "model": {"type": "preset", "name": "balanced"},
|
||
|
|
\\ "batch_size": 16,
|
||
|
|
\\ "normalize": true,
|
||
|
|
\\ "show_download_progress": true
|
||
|
|
\\ }
|
||
|
|
\\ }
|
||
|
|
\\}
|
||
|
|
;
|
||
|
|
|
||
|
|
const result_json = try kreuzberg.extract_file_sync("document.pdf", null, config_json);
|
||
|
|
defer std.heap.c_allocator.free(result_json);
|
||
|
|
|
||
|
|
const owned = try allocator.dupe(u8, result_json);
|
||
|
|
defer allocator.free(owned);
|
||
|
|
|
||
|
|
const stdout = std.io.getStdOut().writer();
|
||
|
|
try stdout.print("{s}\n", .{owned});
|
||
|
|
}
|
||
|
|
```
|