test

README.md

@@ -1,8 +1,8 @@
 ---
-title: OmniTest
-emoji: 💬
-colorFrom: yellow
-colorTo: purple
+title: OmniFusion
+emoji: 👁
+colorFrom: green
+colorTo: pink
 sdk: gradio
 sdk_version: 4.36.1
 app_file: app.py
@@ -10,4 +10,4 @@ pinned: false
 license: apache-2.0
 ---
 
-An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,63 +1,55 @@
+import os
+from io import BytesIO
+
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import grpc
+from PIL import Image
+
+from inference_pb2 import OmniRequest, OmniResponse
+from inference_pb2_grpc import OmniServiceStub
+#from utils.shape_predictor import align_face
+
+
+def get_bytes(img):
+    if img is None:
+        return img
+
+    buffered = BytesIO()
+    img.save(buffered, format="JPEG")
+    return buffered.getvalue()
+
+
+def bytes_to_image(image: bytes) -> Image.Image:
+    image = Image.open(BytesIO(image))
+    return image
+
+
+
+def generate_answer(question, image):
+    image_bytes = get_bytes(image)
+
+    if image_bytes is None:
+        image_bytes = b'image'
+
+    with grpc.insecure_channel(os.environ['SERVER']) as channel:
+        stub = OmniServiceStub(channel)
+
+        output: OmniResponse = stub.get_answer(OmniRequest(image=image_bytes, question=question))
+        output = output.answer
+    #output = bytes_to_image(output.image)
+    return output
+
+
+def get_demo():
+    demo = gr.Interface(
+        fn=generate_answer,
+        inputs=["text", gr.Image(type="pil")],
+        outputs=["text"],
+    )
+    return demo
+
+
+if __name__ == '__main__':
+    #align_cache = LRUCache(maxsize=10)
+    demo = get_demo()
+    demo.launch(server_name="0.0.0.0", server_port=7860, share=True)

inference_pb2.py

@@ -0,0 +1,30 @@
+# -*- coding: utf-8 -*-
+# Generated by the protocol buffer compiler.  DO NOT EDIT!
+# source: inference.proto
+# Protobuf Python Version: 5.26.1
+"""Generated protocol buffer code."""
+from google.protobuf import descriptor as _descriptor
+from google.protobuf import descriptor_pool as _descriptor_pool
+from google.protobuf import symbol_database as _symbol_database
+from google.protobuf.internal import builder as _builder
+# @@protoc_insertion_point(imports)
+
+_sym_db = _symbol_database.Default()
+
+
+
+
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\x0finference.proto\x12\tinference\".\n\x0bOmniRequest\x12\r\n\x05image\x18\x01 \x01(\x0c\x12\x10\n\x08question\x18\x02 \x01(\t\"\x1e\n\x0cOmniResponse\x12\x0e\n\x06\x61nswer\x18\x01 \x01(\t2L\n\x0bOmniService\x12=\n\nget_answer\x12\x16.inference.OmniRequest\x1a\x17.inference.OmniResponseb\x06proto3')
+
+_globals = globals()
+_builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
+_builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'inference_pb2', _globals)
+if not _descriptor._USE_C_DESCRIPTORS:
+  DESCRIPTOR._loaded_options = None
+  _globals['_OMNIREQUEST']._serialized_start=30
+  _globals['_OMNIREQUEST']._serialized_end=76
+  _globals['_OMNIRESPONSE']._serialized_start=78
+  _globals['_OMNIRESPONSE']._serialized_end=108
+  _globals['_OMNISERVICE']._serialized_start=110
+  _globals['_OMNISERVICE']._serialized_end=186
+# @@protoc_insertion_point(module_scope)

inference_pb2.pyi

@@ -0,0 +1,19 @@
+from google.protobuf import descriptor as _descriptor
+from google.protobuf import message as _message
+from typing import ClassVar as _ClassVar, Optional as _Optional
+
+DESCRIPTOR: _descriptor.FileDescriptor
+
+class OmniRequest(_message.Message):
+    __slots__ = ("image", "question")
+    IMAGE_FIELD_NUMBER: _ClassVar[int]
+    QUESTION_FIELD_NUMBER: _ClassVar[int]
+    image: bytes
+    question: str
+    def __init__(self, image: _Optional[bytes] = ..., question: _Optional[str] = ...) -> None: ...
+
+class OmniResponse(_message.Message):
+    __slots__ = ("answer",)
+    ANSWER_FIELD_NUMBER: _ClassVar[int]
+    answer: str
+    def __init__(self, answer: _Optional[str] = ...) -> None: ...

inference_pb2_grpc.py

@@ -0,0 +1,102 @@
+# Generated by the gRPC Python protocol compiler plugin. DO NOT EDIT!
+"""Client and server classes corresponding to protobuf-defined services."""
+import grpc
+import warnings
+
+import inference_pb2 as inference__pb2
+
+GRPC_GENERATED_VERSION = '1.64.1'
+GRPC_VERSION = grpc.__version__
+EXPECTED_ERROR_RELEASE = '1.65.0'
+SCHEDULED_RELEASE_DATE = 'June 25, 2024'
+_version_not_supported = False
+
+try:
+    from grpc._utilities import first_version_is_lower
+    _version_not_supported = first_version_is_lower(GRPC_VERSION, GRPC_GENERATED_VERSION)
+except ImportError:
+    _version_not_supported = True
+
+if _version_not_supported:
+    warnings.warn(
+        f'The grpc package installed is at version {GRPC_VERSION},'
+        + f' but the generated code in inference_pb2_grpc.py depends on'
+        + f' grpcio>={GRPC_GENERATED_VERSION}.'
+        + f' Please upgrade your grpc module to grpcio>={GRPC_GENERATED_VERSION}'
+        + f' or downgrade your generated code using grpcio-tools<={GRPC_VERSION}.'
+        + f' This warning will become an error in {EXPECTED_ERROR_RELEASE},'
+        + f' scheduled for release on {SCHEDULED_RELEASE_DATE}.',
+        RuntimeWarning
+    )
+
+
+class OmniServiceStub(object):
+    """Missing associated documentation comment in .proto file."""
+
+    def __init__(self, channel):
+        """Constructor.
+
+        Args:
+            channel: A grpc.Channel.
+        """
+        self.get_answer = channel.unary_unary(
+                '/inference.OmniService/get_answer',
+                request_serializer=inference__pb2.OmniRequest.SerializeToString,
+                response_deserializer=inference__pb2.OmniResponse.FromString,
+                _registered_method=True)
+
+
+class OmniServiceServicer(object):
+    """Missing associated documentation comment in .proto file."""
+
+    def get_answer(self, request, context):
+        """Missing associated documentation comment in .proto file."""
+        context.set_code(grpc.StatusCode.UNIMPLEMENTED)
+        context.set_details('Method not implemented!')
+        raise NotImplementedError('Method not implemented!')
+
+
+def add_OmniServiceServicer_to_server(servicer, server):
+    rpc_method_handlers = {
+            'get_answer': grpc.unary_unary_rpc_method_handler(
+                    servicer.get_answer,
+                    request_deserializer=inference__pb2.OmniRequest.FromString,
+                    response_serializer=inference__pb2.OmniResponse.SerializeToString,
+            ),
+    }
+    generic_handler = grpc.method_handlers_generic_handler(
+            'inference.OmniService', rpc_method_handlers)
+    server.add_generic_rpc_handlers((generic_handler,))
+    server.add_registered_method_handlers('inference.OmniService', rpc_method_handlers)
+
+
+ # This class is part of an EXPERIMENTAL API.
+class OmniService(object):
+    """Missing associated documentation comment in .proto file."""
+
+    @staticmethod
+    def get_answer(request,
+            target,
+            options=(),
+            channel_credentials=None,
+            call_credentials=None,
+            insecure=False,
+            compression=None,
+            wait_for_ready=None,
+            timeout=None,
+            metadata=None):
+        return grpc.experimental.unary_unary(
+            request,
+            target,
+            '/inference.OmniService/get_answer',
+            inference__pb2.OmniRequest.SerializeToString,
+            inference__pb2.OmniResponse.FromString,
+            options,
+            channel_credentials,
+            insecure,
+            call_credentials,
+            compression,
+            wait_for_ready,
+            timeout,
+            metadata,
+            _registered_method=True)

protos/.ipynb_checkpoints/inference-checkpoint.proto

@@ -0,0 +1,15 @@
+syntax = "proto3";
+package inference;
+
+service OmniService {
+  rpc get_answer(OmniRequest) returns (OmniResponse);
+}
+
+message OmniRequest {
+  bytes image = 1;
+  string question = 2;
+}
+
+message OmniResponse {
+  string answer = 1;
+}

protos/inference.proto

@@ -0,0 +1,15 @@
+syntax = "proto3";
+package inference;
+
+service OmniService {
+  rpc get_answer(OmniRequest) returns (OmniResponse);
+}
+
+message OmniRequest {
+  bytes image = 1;
+  string question = 2;
+}
+
+message OmniResponse {
+  string answer = 1;
+}

requirements.txt

@@ -1 +1,3 @@
-huggingface_hub==0.22.2
+huggingface_hub==0.22.2
+grpcio
+grpcio-tools

run_codegen.py

@@ -0,0 +1,10 @@
+from grpc_tools import protoc
+
+protoc.main((
+    '',
+    '-Iprotos',
+    '--python_out=.',
+    '--grpc_python_out=.',
+    '--pyi_out=.',
+    'protos/inference.proto',
+))