update docs

samples/python/text_generation/chat_sample.py

@@ -9,7 +9,6 @@
 def streamer(subword):
     print(subword, end='', flush=True)
     # Return flag corresponds whether generation should be stopped.
-    # False means continue generation.
     return openvino_genai.StreamerRunningStatus.RUNNING
 
 def main():

samples/python/text_generation/multinomial_causal_lm.py

@@ -59,9 +59,9 @@ def get_stop_flag(self):
         Checks whether the generation process should be stopped.
         
         Returns:
-            bool: Always returns False in this implementation.
+            openvino_genai.StreamerRunningStatus: Always returns RUNNING in this implementation.
         """
-        return False
+        return openvino_genai.StreamerRunningStatus.RUNNING
 
     def put_word(self, word: str):
         """

samples/python/text_generation/prompt_lookup_decoding_lm.py

@@ -8,8 +8,7 @@
 def streamer(subword):
     print(subword, end='', flush=True) 
     # Return flag corresponds whether generation should be stopped. 
-    # False means continue generation. 
-    return False
+    return openvino_genai.StreamerRunningStatus.RUNNING
 
 def main():
     parser = argparse.ArgumentParser()

samples/python/text_generation/speculative_decoding_lm.py

@@ -9,8 +9,7 @@
 def streamer(subword):
     print(subword, end='', flush=True)
     # Return flag corresponds whether generation should be stopped. 
-    # False means continue generation.
-    return False
+    return openvino_genai.StreamerRunningStatus.RUNNING
 
 def main():
     parser = argparse.ArgumentParser()

src/cpp/include/openvino/genai/generation_handle.hpp

@@ -93,6 +93,7 @@ GenerationHandleImpl {
 
     bool is_canceled();
 
+    OPENVINO_DEPRECATED("Please, use `stop()` instead of `drop()`.")
     void drop();
 
     void stop();

src/cpp/include/openvino/genai/llm_pipeline.hpp

@@ -18,7 +18,9 @@
 namespace ov {
 namespace genai {
 
-// Return flag corresponds whether generation should be stopped: false means continue generation, true means stop.
+// Return flag corresponds whether generation should be stopped. It could be:
+// ov::genai::StreamerRunningStatus flag, RUNNING means continue generation, STOP means stop generation, CANCEL means stop generation and remove last propmt and answer from history
+// *DEPRECATED* bool flag, false means continue generation, true means stop. Please, use `ov::genai::StreamerRunningStatus` instead.
 using StreamerVariant = std::variant<std::function<bool(std::string)>, std::function<StreamerRunningStatus(std::string)>, std::shared_ptr<StreamerBase>, std::monostate>;
 using OptionalGenerationConfig = std::optional<GenerationConfig>;
 using EncodedInputs = std::variant<ov::Tensor, TokenizedInputs>;

src/cpp/include/openvino/genai/streamer_base.hpp

@@ -24,16 +24,20 @@ using CallbackTypeVariant = std::variant<bool, StreamerRunningStatus, std::monos
  * @param m_tokenizer tokenizer
  */
 class OPENVINO_GENAI_EXPORTS StreamerBase {
-public:
+protected:
     StreamerRunningStatus m_streaming_finish_status = StreamerRunningStatus::RUNNING;
+
+public:
     /// @brief put is called every time new token is decoded,
     /// @return bool flag to indicate whether generation should be stopped, if return true generation stops
     virtual bool put(int64_t token) = 0;
 
     /// @brief end is called at the end of generation. It can be used to flush cache if your own streamer has one
     virtual void end() = 0;
 
-    StreamerRunningStatus get_streaming_status() {
+    /// @brief get_streaming_status() is called by the pipline to take more detailed about streaming status. m_streaming_finish_status, which contains streaming status info, could be set in put().
+    /// @return ov::genai::StreamerRunningStatus to determine the streaming status of generation, whether generation is running, stopped or cancelled
+    virtual StreamerRunningStatus get_streaming_status() {
         return m_streaming_finish_status;
     }
 

src/cpp/src/utils.hpp

@@ -93,6 +93,7 @@ Config from_config_json_if_exists(const std::filesystem::path& models_path, cons
     return std::filesystem::exists(config_file_path) ? Config{config_file_path} : Config{};
 }
 
+OPENVINO_DEPRECATED("Callback streamer with `bool` return value is depricated. Please, use `ov::genai::StreamerRunningStatus` instead.")
 ov::genai::StreamerVariant get_streamer_from_map(const ov::AnyMap& config_map);
 
 ov::genai::OptionalGenerationConfig get_config_from_map(const ov::AnyMap& config_map);