Streaming the Output

For more interactive UIs during generation, you can stream output tokens.

info

Streaming is supported for LLMPipeline, VLMPipeline and WhisperPipeline.

Streaming Function

In this example, a function outputs words to the console immediately upon generation:

Python

import openvino_genai as ov_genai

pipe = ov_genai.LLMPipeline(model_path, "CPU")

# Create a streamer function
def streamer(subword):
    print(subword, end='', flush=True)
    # Return flag corresponds whether generation should be stopped.
    return ov_genai.StreamingStatus.RUNNING

pipe.start_chat()
while True:
    try:
        prompt = input('question:\n')
    except EOFError:
        break
    pipe.generate(prompt, streamer=streamer, max_new_tokens=100)
    print('\n----------\n')
pipe.finish_chat()

C++

#include "openvino/genai/llm_pipeline.hpp"
#include <iostream>

int main(int argc, char* argv[]) {
    std::string prompt;

    std::string model_path = argv[1];
    ov::genai::LLMPipeline pipe(model_path, "CPU");

    // Create a streamer function
    auto streamer = [](std::string word) {
        std::cout << word << std::flush;
        // Return flag corresponds whether generation should be stopped.
        return ov::genai::StreamingStatus::RUNNING;
    };

    pipe.start_chat();
    std::cout << "question:\n";
    while (std::getline(std::cin, prompt)) {
        pipe.generate(prompt, ov::genai::streamer(streamer), ov::genai::max_new_tokens(100));
        std::cout << "\n----------\n"
            "question:\n";
    }
    pipe.finish_chat();
}

Custom Streamer Class

You can also create your custom streamer for more sophisticated processing:

Python

import openvino_genai as ov_genai

pipe = ov_genai.LLMPipeline(model_path, "CPU")

# Create custom streamer class
class CustomStreamer(ov_genai.StreamerBase):
    def __init__(self):
        super().__init__()
        # Initialization logic.

    def write(self, token: int | list[int]) -> ov_genai.StreamingStatus:
        # Custom processing logic for new decoded token(s).

        # Return flag corresponds whether generation should be stopped.
        return ov_genai.StreamingStatus.RUNNING

    def end(self):
        # Custom finalization logic.
        pass

pipe.start_chat()
while True:
    try:
        prompt = input('question:\n')
    except EOFError:
        break
    pipe.generate(prompt, streamer=CustomStreamer(), max_new_tokens=100)
    print('\n----------\n')
pipe.finish_chat()

C++

#include "openvino/genai/streamer_base.hpp"
#include "openvino/genai/llm_pipeline.hpp"
#include <iostream>

// Create custom streamer class
class CustomStreamer: public ov::genai::StreamerBase {
public:
    ov::genai::StreamingStatus write(int64_t token) {
        // Custom processing logic for new decoded token.

        // Return flag corresponds whether generation should be stopped.
        return ov::genai::StreamingStatus::RUNNING;
    };

    ov::genai::StreamingStatus write(const std::vector<int64_t>& tokens) {
        // Custom processing logic for new vector of decoded tokens.

        // Return flag corresponds whether generation should be stopped.
        return ov::genai::StreamingStatus::RUNNING;
    };

    void end() {
        // Custom finalization logic.
    };
};

int main(int argc, char* argv[]) {
    std::string prompt;
    std::shared_ptr<CustomStreamer> custom_streamer;

    std::string model_path = argv[1];
    ov::genai::LLMPipeline pipe(model_path, "CPU");

    pipe.start_chat();
    std::cout << "question:\n";
    while (std::getline(std::cin, prompt)) {
        pipe.generate(prompt, ov::genai::streamer(custom_streamer), ov::genai::max_new_tokens(100));
        std::cout << "\n----------\n"
            "question:\n";
    }
    pipe.finish_chat();
}

info

For fully implemented iterable CustomStreamer refer to multinomial_causal_lm sample.