initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,3 @@
+.envrc
+.venv
+__pycache__/

Dockerfile

@@ -0,0 +1,32 @@
+FROM debian:11-slim AS build
+RUN apt-get update && apt-get upgrade -yy && \
+    apt-get install --no-install-suggests --no-install-recommends --yes python3-venv gcc  libpython3-dev && \
+    python3 -m venv /venv && \
+    /venv/bin/pip install --no-cache-dir --upgrade pip setuptools wheel
+
+FROM build AS build-venv
+COPY requirements.txt /requirements.txt
+RUN /venv/bin/pip install --no-cache-dir --upgrade --disable-pip-version-check -r /requirements.txt
+
+# Copy the virtualenv into a distroless image
+FROM gcr.io/distroless/python3-debian11
+COPY --from=build-venv /venv /venv
+
+#RUN useradd -m -u 1000 user
+USER nonroot:nonroot
+ENV HOME=/tmp \
+    PATH=/venv/bin:$PATH
+WORKDIR $HOME/app
+
+COPY --chown=nonroot captioner.py $HOME/app/captioner.py
+
+ARG MODEL="Salesforce/blip-image-captioning-base"
+ENV MODEL=${MODEL}
+ENTRYPOINT ["/venv/bin/python3", "/venv/bin/uvicorn", "--host", "0.0.0.0", "captioner:app"]
+EXPOSE 8000
+USER nonroot:nonroot
+
+
+
+
+

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 Baptiste Canton
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

Makefile

@@ -0,0 +1,14 @@
+
+.PHONY: run dockerbuild dockerrun
+
+run:
+	@uvicorn captioner:app
+
+dockerbuild:
+	@docker build -t captioner .
+
+dockerrun:
+	@docker run --rm -p 8000:8000 captioner
+
+test: 
+	@time curl -X POST -H "Content-Type: application/json" -d '{"url": "https://cataas.com/cat" }'  http://127.0.0.1:8000/caption/

README.md

@@ -0,0 +1,11 @@
+---
+title: Truc
+emoji: 🌍
+colorFrom: yellow
+colorTo: purple
+sdk: docker
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

captioner.py

@@ -0,0 +1,118 @@
+import asyncio
+import logging
+import os
+import time
+from typing import List, Union
+
+from pillow_heif import register_heif_opener
+
+register_heif_opener()
+
+import gradio as gr
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel, HttpUrl
+from transformers import pipeline
+
+LOG_LEVEL = os.getenv("LOG_LEVEL", "DEBUG")
+MAX_URLS = int(os.getenv("MAX_URLS", 5))
+MAX_NEW_TOKENS = int(os.getenv("MAX_NEW_TOKENS", 200))
+# https://huggingface.co/models?pipeline_tag=image-to-text&sort=likes
+MODEL = os.getenv("MODEL", "../models/Salesforce/blip-image-captioning-large")
+
+
+logging.basicConfig(level=LOG_LEVEL)
+logger = logging.getLogger(__name__)
+
+
+app = FastAPI()
+
+
+captioner = None  # Placeholder for the captioner pipeline
+is_initialized = asyncio.Event()  # Event to track initialization status
+lock = asyncio.Lock()
+
+
+def load_model():
+    global captioner
+    logger.info("Loading model...")
+    # simpler model: "ydshieh/vit-gpt2-coco-en"
+    captioner = pipeline(
+        "image-to-text",
+        model=MODEL,
+        max_new_tokens=MAX_NEW_TOKENS,
+    )
+    logger.info("Done loading model.")
+    is_initialized.set()
+
+
+class Image(BaseModel):
+    url: Union[HttpUrl, List[HttpUrl]]  # url can be a string or a list of strings
+
+
+@app.on_event("startup")
+async def startup_event():
+    global app
+    asyncio.create_task(asyncio.to_thread(load_model))
+    # add gradio interface
+    iface = gr.Interface(fn=captioner_gradapter, inputs="text", outputs=["text"], allow_flagging="never")
+    app = gr.mount_gradio_app(app, iface, path="/gradio")
+
+
+async def captioner_gradapter(image_url):
+    await is_initialized.wait()
+    async with lock:
+        result = await asyncio.to_thread(captioner, image_url)
+        caption = result[0]["generated_text"]
+    return caption
+
+
+@app.get("/")
+async def root():
+    return {"message": "Hello World"}
+
+
+# the image url is passed in as a "url" tag in the json body
+@app.post("/caption/")
+async def create_caption(image: Image):
+    if isinstance(image.url, list) and len(image.url) > MAX_URLS:
+        logger.debug(
+            f"Request with more than {MAX_URLS} URLs received. Refusing the request."
+        )
+
+        raise HTTPException(
+            status_code=400,
+            detail=f"Maximum of {MAX_URLS} URLs can be processed at once",
+        )
+    async with lock:
+        await is_initialized.wait()  # Wait until initialization is completed
+
+        start_time = time.time()
+        # get the image url from the json body
+        image_url = image.url
+        try:
+            caption = await asyncio.to_thread(captioner, image_url)
+        except Exception as e:
+            logger.error("Error during caption generation: %s", str(e))
+            raise HTTPException(
+                status_code=500,
+                detail="An error occurred during caption generation. Please try again later.",
+            )
+        end_time = time.time()
+        duration = end_time - start_time
+        logger.debug("Captioning completed. Time taken: %s seconds.", duration)
+
+        return {"caption": caption, "duration": duration}
+
+
+# add liveness probe
+@app.get("/healthz")
+async def healthz():
+    return {"status": "ok"}
+
+
+# add readiness probe
+@app.get("/readyz")
+async def readyz():
+    if not is_initialized.is_set():
+        raise HTTPException(status_code=503, detail="Initialization in progress")
+    return {"status": "ok"}

data.json

@@ -0,0 +1,3 @@
+{
+  "url": "https://huggingface.co/datasets/Narsil/image_dummy/raw/main/parrots.png"
+}

gg.py

@@ -0,0 +1,18 @@
+from gradio_client import Client
+import logging
+import os
+
+LOG_LEVEL = os.getenv("LOG_LEVEL", "DEBUG")
+
+logging.basicConfig(level=LOG_LEVEL)
+logger = logging.getLogger(__name__)
+
+
+
+client = Client("https://batmac-captioner.hf.space/")
+print(client.view_api())
+result = client.predict(
+				"https://images.pexels.com/photos/58997/pexels-photo-58997.jpeg",	# str  in 'image_url' Textbox component
+				api_name="/predict"
+)
+print(result)

grapi.py

@@ -0,0 +1,15 @@
+import logging
+import os
+import sys
+
+from gradio_client import Client
+
+LOG_LEVEL = os.getenv("LOG_LEVEL", "DEBUG")
+
+logging.basicConfig(level=LOG_LEVEL)
+logger = logging.getLogger(__name__)
+
+url = sys.argv[1]
+
+client = Client(url)
+print(client.view_api())

requirements.txt

@@ -0,0 +1,10 @@
+fastapi
+pillow
+transformers
+torch
+accelerate
+pillow-heif
+gradio
+
+uvicorn
+