#include cactus.h

cactus_set_pro_key("optional, email founders@cactuscompute.com"); 

cactus_model_t model = cactus_init(
    "path/to/weight/folder",            
    "path to txt or dir of txts for auto-rag",  
);

const char* messages = R"([
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "My name is Henry Ndubuaku"}
])";

const char* options = R"({
    "max_tokens": 50,
    "stop_sequences": ["<|im_end|>"]
})";

char response[4096];
int result = cactus_complete(
    model,                            // model handle from cactus_init
    messages,                         // JSON array of chat messages
    response,                         // buffer to store response JSON
    sizeof(response),                 // size of response buffer
    options,                          // optional: generation options (nullptr for defaults)
    nullptr,                          // optional: tools JSON for function calling 
    nullptr,                          // optional: streaming callback fn(token, id, user_data)
    nullptr                           // optional: user data passed to callback
);

#include cactus.h

CactusGraph graph;
auto a = graph.input({2, 3}, Precision::FP16);
auto b = graph.input({3, 4}, Precision::INT8);

auto x1 = graph.matmul(a, b, false);
auto x2 = graph.transpose(x1);
auto result = graph.matmul(b, x2, true);

float a_data[6] = {1.1f, 2.3f, 3.4f, 4.2f, 5.7f, 6.8f};
float b_data[12] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12};

graph.set_input(a, a_data, Precision::FP16);
graph.set_input(b, b_data, Precision::INT8);

graph.execute();
void* output_data = graph.get_output(result);

graph.hard_reset();