add application file

.gitignore

@@ -0,0 +1,5 @@
+.vercel
+venv
+.venv
+.idea
+__pycache__

Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.9
+
+WORKDIR /code
+
+COPY requirements.txt ./
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+RUN useradd -m -u 1000 user
+
+USER user
+
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app/
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860" "--workers", "2"]

api/index.py

@@ -0,0 +1 @@
+from src.index import app

main.py

@@ -0,0 +1 @@
+from api.index import app

requirements.txt

@@ -0,0 +1,8 @@
+fastapi==0.88.0
+Pillow==9.5.0
+protobuf==4.25.0
+python-multipart==0.0.6
+sentencepiece==0.1.99
+# transformers==4.35.0
+transformers[torch]
+uvicorn==0.20.0

src/dtos/ISayHelloDto.py

@@ -0,0 +1,4 @@
+from pydantic import BaseModel
+
+class ISayHelloDto(BaseModel):
+    message: str

src/index.py

@@ -0,0 +1,77 @@
+from fastapi import FastAPI, File, UploadFile, Form
+from fastapi.responses import JSONResponse
+from fastapi.middleware.cors import CORSMiddleware
+from transformers import TrOCRProcessor, VisionEncoderDecoderModel
+import requests
+from PIL import Image
+import io
+import base64
+from src.dtos.ISayHelloDto import ISayHelloDto
+
+app = FastAPI()
+
+# Enable CORS for all origins
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+processor = TrOCRProcessor.from_pretrained("microsoft/trocr-small-printed")
+model = VisionEncoderDecoderModel.from_pretrained("src/model/captcha")
+
+def read_image(file) -> Image.Image:
+    image = Image.open(io.BytesIO(file))
+    return image
+
+def read_base64_image(base64_data) -> Image.Image:
+    base64_bytes = base64.b64decode(base64_data)
+    image = Image.open(io.BytesIO(base64_bytes))
+    return image
+
+def process_image(image):
+    # prepare image
+    pixel_values = processor(image, return_tensors="pt").pixel_values
+
+    # generate (no beam search)
+    generated_ids = model.generate(pixel_values)
+
+    # decode
+    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+
+    return generated_text
+
+@app.get("/")
+async def root():
+    return {"message": "Hello World"}
+
+
+@app.get("/hello/{name}")
+async def say_hello(name: str):
+    return {"message": f"Hello {name}"}
+
+
+@app.post("/hello")
+async def hello_message(dto: ISayHelloDto):
+    return {"message": f"Hello {dto.message}"}
+
+
+@app.post("/extract-text")
+async def extract_text(file: UploadFile = File(...)):
+    try:
+        image = read_image(await file.read())
+        text = process_image(image)
+        return JSONResponse(content={"text": text}, status_code=200)
+    except Exception as e:
+        return JSONResponse(content={"error": str(e)}, status_code=500)
+
+@app.post("/extract-text/bs64")
+async def extract_text_bs64(base64_data: str = Form(None)):
+    try:
+        image = read_base64_image(base64_data)
+        text = process_image(image)
+        return JSONResponse(content={"text": text}, status_code=200)
+    except Exception as e:
+        return JSONResponse(content={"error": str(e)}, status_code=500)

src/model/captcha/config.json

@@ -0,0 +1,177 @@
+{
+  "_name_or_path": "microsoft/trocr-small-printed",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "relu",
+    "add_cross_attention": true,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": 384,
+    "d_model": 256,
+    "decoder_attention_heads": 8,
+    "decoder_ffn_dim": 1024,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 6,
+    "decoder_start_token_id": 2,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "init_std": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layernorm_embedding": true,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "trocr",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": true,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": false,
+    "use_learned_position_embeddings": true,
+    "vocab_size": 64044
+  },
+  "decoder_start_token_id": 0,
+  "early_stopping": true,
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "encoder_stride": 16,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 384,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 384,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "deit",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 6,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "eos_token_id": 2,
+  "is_encoder_decoder": true,
+  "length_penalty": 2.0,
+  "max_length": 64,
+  "model_type": "vision-encoder-decoder",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "vocab_size": 64044
+}

src/model/captcha/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 0,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 64,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.35.0",
+  "use_cache": false
+}

src/model/captcha/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322e7adf1ff7d3b8d38fb7f0a1dc62834523e773a9828cd3b7b79342b91cc2d5
+size 246430696

test_index.http

@@ -0,0 +1,20 @@
+# Test your FastAPI endpoints
+
+GET http://127.0.0.1:8000/
+Accept: application/json
+
+###
+
+GET http://127.0.0.1:8000/hello/User
+Accept: application/json
+
+###
+
+POST /hello HTTP/1.1
+Host: 127.0.0.1:8000
+Content-Type: application/json
+Content-Length: 28
+
+{
+    "message": "Fulano!"
+}

test_index.py

@@ -0,0 +1,23 @@
+import pytest
+
+from src.dtos.ISayHelloDto import ISayHelloDto
+from src.index import root, say_hello, hello_message
+
+
+@pytest.mark.asyncio
+async def test_root():
+    result = await root()
+    assert result == {'message': 'Hello World'}
+
+
+@pytest.mark.asyncio
+async def test_say_hello():
+    result = await say_hello("John")
+    assert result == {'message': 'Hello John'}
+
+
+@pytest.mark.asyncio
+async def test_hello_message():
+    dto = ISayHelloDto(message="Alice")
+    result = await hello_message(dto)
+    assert result == {'message': 'Hello Alice'}