llama-cpp-bindings-sys 0.8.0

Low level bindings to llama.cpp
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131

#pragma once

#include "llama.cpp/include/llama.h"
#include "wrapper_utils.h"

#include <stddef.h>

#ifdef __cplusplus
extern "C" {
#endif

struct llama_rs_parsed_chat;
typedef struct llama_rs_parsed_chat * llama_rs_parsed_chat_handle;

typedef enum llama_rs_parse_chat_message_status {
    LLAMA_RS_PARSE_CHAT_MESSAGE_OK = 0,
    LLAMA_RS_PARSE_CHAT_MESSAGE_NULL_MODEL_ARG,
    LLAMA_RS_PARSE_CHAT_MESSAGE_NULL_INPUT_ARG,
    LLAMA_RS_PARSE_CHAT_MESSAGE_NULL_OUT_HANDLE_ARG,
    LLAMA_RS_PARSE_CHAT_MESSAGE_NULL_OUT_ERROR_ARG,
    LLAMA_RS_PARSE_CHAT_MESSAGE_MODEL_HAS_NO_CHAT_TEMPLATE,
    LLAMA_RS_PARSE_CHAT_MESSAGE_MODEL_HAS_NO_VOCAB,
    LLAMA_RS_PARSE_CHAT_MESSAGE_ERROR_STRING_ALLOCATION_FAILED,
    LLAMA_RS_PARSE_CHAT_MESSAGE_VENDORED_THREW_CXX_EXCEPTION,
} llama_rs_parse_chat_message_status;

llama_rs_parse_chat_message_status llama_rs_parse_chat_message(
    const struct llama_model * model,
    const char * tools_json,
    const char * input,
    int is_partial,
    llama_rs_parsed_chat_handle * out_handle,
    char ** out_error);

typedef enum llama_rs_parsed_chat_free_status {
    LLAMA_RS_PARSED_CHAT_FREE_OK = 0,
    LLAMA_RS_PARSED_CHAT_FREE_ERROR_STRING_ALLOCATION_FAILED,
    LLAMA_RS_PARSED_CHAT_FREE_DESTRUCTOR_THREW_CXX_EXCEPTION,
} llama_rs_parsed_chat_free_status;

llama_rs_parsed_chat_free_status llama_rs_parsed_chat_free(
    llama_rs_parsed_chat_handle handle,
    char ** out_error);

typedef enum llama_rs_parsed_chat_tool_call_count_status {
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_COUNT_OK = 0,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_COUNT_NULL_HANDLE_ARG,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_COUNT_NULL_OUT_COUNT_ARG,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_COUNT_ERROR_STRING_ALLOCATION_FAILED,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_COUNT_VENDORED_THREW_CXX_EXCEPTION,
} llama_rs_parsed_chat_tool_call_count_status;

llama_rs_parsed_chat_tool_call_count_status llama_rs_parsed_chat_tool_call_count(
    llama_rs_parsed_chat_handle handle,
    size_t * out_count,
    char ** out_error);

typedef enum llama_rs_parsed_chat_tool_call_id_status {
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_ID_OK = 0,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_ID_NULL_HANDLE_ARG,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_ID_NULL_OUT_STRING_ARG,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_ID_INDEX_OUT_OF_BOUNDS,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_ID_ERROR_STRING_ALLOCATION_FAILED,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_ID_VENDORED_THREW_CXX_EXCEPTION,
} llama_rs_parsed_chat_tool_call_id_status;

llama_rs_parsed_chat_tool_call_id_status llama_rs_parsed_chat_tool_call_id(
    llama_rs_parsed_chat_handle handle,
    size_t index,
    char ** out_string,
    char ** out_error);

typedef enum llama_rs_parsed_chat_tool_call_name_status {
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_NAME_OK = 0,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_NAME_NULL_HANDLE_ARG,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_NAME_NULL_OUT_STRING_ARG,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_NAME_INDEX_OUT_OF_BOUNDS,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_NAME_ERROR_STRING_ALLOCATION_FAILED,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_NAME_VENDORED_THREW_CXX_EXCEPTION,
} llama_rs_parsed_chat_tool_call_name_status;

llama_rs_parsed_chat_tool_call_name_status llama_rs_parsed_chat_tool_call_name(
    llama_rs_parsed_chat_handle handle,
    size_t index,
    char ** out_string,
    char ** out_error);

typedef enum llama_rs_parsed_chat_tool_call_arguments_status {
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_ARGUMENTS_OK = 0,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_ARGUMENTS_NULL_HANDLE_ARG,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_ARGUMENTS_NULL_OUT_STRING_ARG,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_ARGUMENTS_INDEX_OUT_OF_BOUNDS,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_ARGUMENTS_ERROR_STRING_ALLOCATION_FAILED,
    LLAMA_RS_PARSED_CHAT_TOOL_CALL_ARGUMENTS_VENDORED_THREW_CXX_EXCEPTION,
} llama_rs_parsed_chat_tool_call_arguments_status;

llama_rs_parsed_chat_tool_call_arguments_status llama_rs_parsed_chat_tool_call_arguments(
    llama_rs_parsed_chat_handle handle,
    size_t index,
    char ** out_string,
    char ** out_error);

typedef enum llama_rs_parsed_chat_content_status {
    LLAMA_RS_PARSED_CHAT_CONTENT_OK = 0,
    LLAMA_RS_PARSED_CHAT_CONTENT_NULL_HANDLE_ARG,
    LLAMA_RS_PARSED_CHAT_CONTENT_NULL_OUT_STRING_ARG,
    LLAMA_RS_PARSED_CHAT_CONTENT_ERROR_STRING_ALLOCATION_FAILED,
    LLAMA_RS_PARSED_CHAT_CONTENT_VENDORED_THREW_CXX_EXCEPTION,
} llama_rs_parsed_chat_content_status;

llama_rs_parsed_chat_content_status llama_rs_parsed_chat_content(
    llama_rs_parsed_chat_handle handle,
    char ** out_string,
    char ** out_error);

typedef enum llama_rs_parsed_chat_reasoning_content_status {
    LLAMA_RS_PARSED_CHAT_REASONING_CONTENT_OK = 0,
    LLAMA_RS_PARSED_CHAT_REASONING_CONTENT_NULL_HANDLE_ARG,
    LLAMA_RS_PARSED_CHAT_REASONING_CONTENT_NULL_OUT_STRING_ARG,
    LLAMA_RS_PARSED_CHAT_REASONING_CONTENT_ERROR_STRING_ALLOCATION_FAILED,
    LLAMA_RS_PARSED_CHAT_REASONING_CONTENT_VENDORED_THREW_CXX_EXCEPTION,
} llama_rs_parsed_chat_reasoning_content_status;

llama_rs_parsed_chat_reasoning_content_status llama_rs_parsed_chat_reasoning_content(
    llama_rs_parsed_chat_handle handle,
    char ** out_string,
    char ** out_error);

#ifdef __cplusplus
}
#endif