Testing streaming outputs

Various version of this PR are for testing streaming implementations of the HuggingFace model parsers

cookbooks/Gradio/hf_model_parsers.py

@@ -0,0 +1,31 @@
+from aiconfig_extension_hugging_face import (
+    HuggingFaceAutomaticSpeechRecognitionTransformer,
+    HuggingFaceImage2TextTransformer,
+    HuggingFaceTextSummarizationTransformer,
+    HuggingFaceText2ImageDiffusor,
+    HuggingFaceText2SpeechTransformer,
+    HuggingFaceTextGenerationTransformer,
+    HuggingFaceTextTranslationTransformer,
+)
+from aiconfig import (AIConfigRuntime, ModelParserRegistry)
+
+def register_model_parsers() -> None:
+    """Register model parsers for HuggingFace models.
+    """
+    # Audio --> Text
+    # AIConfigRuntime.register_model_parser(HuggingFaceAutomaticSpeechRecognitionTransformer(), "AutomaticSpeechRecognition")
+
+    # # Image --> Text
+    # AIConfigRuntime.register_model_parser(HuggingFaceImage2TextTransformer(), "Image2Text")
+
+    # # Text --> Image
+    # AIConfigRuntime.register_model_parser(HuggingFaceText2ImageDiffusor(), "Text2Image")
+
+    # # Text --> Audio
+    # AIConfigRuntime.register_model_parser(HuggingFaceText2SpeechTransformer(), "Text2Speech")
+
+    # # Text --> Text
+    # AIConfigRuntime.register_model_parser(HuggingFaceTextGenerationTransformer(), "TextGeneration")
+    # AIConfigRuntime.register_model_parser(HuggingFaceTextSummarizationTransformer(), "TextSummarization")
+    ModelParserRegistry.register_model_parser(HuggingFaceTextSummarizationTransformer())
+    # AIConfigRuntime.register_model_parser(HuggingFaceTextTranslationTransformer(), "TextTranslation")

cookbooks/Gradio/huggingface.aiconfig.json

@@ -0,0 +1,38 @@
+{
+  "name": "The Tale of the Quick Brown Fox",
+  "schema_version": "latest",
+  "metadata": {
+    "parameters": {},
+    "models": {
+      "facebook/bart-large-cnn": {
+        "model": "facebook/bart-large-cnn"
+      }
+    },
+    "default_model": "TextGeneration",
+    "model_parsers": {
+      "facebook/bart-large-cnn": "HuggingFaceTextSummarizationTransformer"
+    }
+  },
+  "description": "The Tale of the Quick Brown Fox",
+  "prompts": [
+    {
+      "name": "Summarize a story",
+      "input": "Once upon a time, in a lush and vibrant forest, there lived a magnificent creature known as the Quick Brown Fox. This fox was unlike any other, possessing incredible speed and agility that awed all the animals in the forest. With its fur as golden as the sun and its eyes as sharp as emeralds, the Quick Brown Fox was admired by everyone, from the tiniest hummingbird to the mightiest bear. The fox had a kind heart and would often lend a helping paw to those in need. The Quick Brown Fox had a particular fondness for games and challenges. It loved to test its skills against others, always seeking new adventures to satisfy its boundless curiosity. Its favorite game was called \"The Great Word Hunt,\" where it would embark on a quest to find hidden words scattered across the forest. \n\nOne day it got very old and died",
+      "metadata": {
+        "model": {
+          "name": "facebook/bart-large-cnn",
+          "settings": {
+            "max_length": 100,
+            "min_length": 50,
+            "num_beams": 1
+          }
+        },
+        "parameters": {
+          "city": "New York"
+        }
+      },
+      "outputs": []
+    }
+  ],
+  "$schema": "https://json.schemastore.org/aiconfig-1.0"
+}

extensions/HuggingFace/python/src/aiconfig_extension_hugging_face/local_inference/text_summarization.py

@@ -128,7 +128,7 @@ def construct_stream_output(
             "metadata": {},
         }
     )
-
+    
     accumulated_message = ""
     for new_text in streamer:
         if isinstance(new_text, str):

python/src/aiconfig/editor/server/server.py

@@ -293,9 +293,9 @@ def kill_thread(thread_id: int | None):
 
             # Yea I know time.sleep() isn't super accurate, but it's fine,
             # we can fix later
-            time.sleep(0.1)
+            # time.sleep(0.1)
             wait_time_in_seconds += SLEEP_DELAY_SECONDS
-            print(f"Output queue is currently empty. Waiting for {wait_time_in_seconds:.1f}s...")
+            # print(f"Output queue is currently empty. Waiting for {wait_time_in_seconds:.1f}s...")
 
         # Yield in flask is weird and you either need to send responses as a
         # string, or artificially wrap them around "[" and "]"