55 lines
1.4 KiB
Markdown
55 lines
1.4 KiB
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,
|
||
|
|
\\ "chunker_type": "markdown",
|
||
|
|
\\ "prepend_heading_context": true
|
||
|
|
\\ }
|
||
|
|
\\}
|
||
|
|
;
|
||
|
|
|
||
|
|
const result_json = try kreuzberg.extract_file_sync("document.pdf", null, config_json);
|
||
|
|
defer std.heap.c_allocator.free(result_json);
|
||
|
|
|
||
|
|
var parsed = try std.json.parseFromSlice(std.json.Value, allocator, result_json, .{});
|
||
|
|
defer parsed.deinit();
|
||
|
|
}
|
||
|
|
```
|
||
|
|
|
||
|
|
```zig title="Zig - Semantic"
|
||
|
|
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,
|
||
|
|
\\ "chunker_type": "semantic"
|
||
|
|
\\ }
|
||
|
|
\\}
|
||
|
|
;
|
||
|
|
|
||
|
|
const result_json = try kreuzberg.extract_file_sync("document.pdf", null, config_json);
|
||
|
|
defer std.heap.c_allocator.free(result_json);
|
||
|
|
|
||
|
|
var parsed = try std.json.parseFromSlice(std.json.Value, allocator, result_json, .{});
|
||
|
|
defer parsed.deinit();
|
||
|
|
}
|
||
|
|
```
|