feat!: remove api (#111)

Removed code related to the unstructured-inference api, as we are doing inference purely through the general unstructured API, and if we were to again serve an inference-only API, we wouldn't do it through this code, or store the code in this repo.

Author: qued

.gitignore

@@ -76,6 +76,7 @@ target/
 
 # Jupyter Notebook
 .ipynb_checkpoints
+nbs/
 
 # IPython
 profile_default/

CHANGELOG.md

@@ -1,7 +1,8 @@
-## 0.4.5
+## 0.5.0
 
 * Preserve image format in PIL.Image.Image when loading
 * Added ONNX version of Detectron2 and make default model
+* Remove API code, we don't serve this as a standalone API any more
 
 ## 0.4.4
 

Dockerfile

@@ -54,43 +54,6 @@ pip-compile:
 	pip-compile --upgrade requirements/test.in
 	pip-compile --upgrade requirements/dev.in
 
-##########
-# Docker #
-##########
-
-# Docker targets are provided for convenience only and are not required in a standard development environment
-
-# Note that the current working directory is mounted under
-# /home/notebook-user/local/ when the image is started with
-# docker-start-api
-
-.PHONY: docker-build
-docker-build:
-	PIP_VERSION=${PIP_VERSION} ./scripts/docker-build.sh
-
-.PHONY: docker-start-api
-docker-start-api:
-	docker run -p 8000:8000 --mount type=bind,source=$(realpath .),target=/home/notebook-user/local -t --rm --entrypoint uvicorn unstructured-inference-dev:latest ${PACKAGE_NAME}.api:app --log-config logger_config.yaml --host 0.0.0.0 --port 8000
-
-
-#########
-# Local #
-########
-
-## run-app-dev:             runs the FastAPI api with hot reloading
-.PHONY: run-app-dev
-run-app-dev:
-	PYTHONPATH=. uvicorn unstructured_inference.api:app --log-config logger_config.yaml --reload
-
-## start-app-local:         runs FastAPI in the container with hot reloading
-.PHONY: start-app-local
-start-app-local:
-	docker run --name=ml-inference-container -p 127.0.0.1:5000:5000 ml-inference-dev
-
-## stop-app-local:          stops the container
-.PHONY: stop-app-local
-stop-app-local:
-	docker stop ml-inference-container | xargs docker rm
 
 #################
 # Test and Lint #

Makefile

@@ -91,65 +91,6 @@ The `UnstructuredDetectronModel` class in `unstructured_inference.modelts.detect
 
 Any detection model can be used for in the `unstructured_inference` pipeline by wrapping the model in the `UnstructuredObjectDetectionModel` class. To integrate with the `DocumentLayout` class, a subclass of `UnstructuredObjectDetectionModel` must have a `predict` method that accepts a `PIL.Image.Image` and returns a list of `LayoutElement`s, and an `initialize` method, which loads the model and prepares it for inference.
 
-## API
-
-To build the Docker container, run `make docker-build`. Note that Apple hardware with an M1 chip 
-has trouble building `Detectron2` on Docker and for best results you should build it on Linux. To 
-run the API locally, use `make start-app-local`. You can stop the API with `make stop-app-local`. 
-The API will run at `http:/localhost:5000`. 
-You can then `POST` a PDF file to the API endpoint to see its layout with the command:
-```
-curl -X 'POST' 'http://localhost:5000/layout/default/pdf' -F 'file=@<your_pdf_file>' | jq -C . | less -R
-```
-
-You can also choose the types of elements you want to return from the output of PDF parsing by 
-passing a list of types to the `include_elems` parameter. For example, if you only want to return 
-`Text` elements and `Title` elements, you can curl:
-```
-curl -X 'POST' 'http://localhost:5000/layout/default/pdf' \
--F 'file=@<your_pdf_file>' \
--F include_elems=Text \
--F include_elems=Title \
- | jq -C | less -R
-```
-If you are using an Apple M1 chip, use `make run-app-dev` instead of `make start-app-local` to 
-start the API with hot reloading. The API will run at `http:/localhost:8000`.
-
-View the swagger documentation at `http://localhost:5000/docs`.
-
-### YoloX model
-
-For using the YoloX model the endpoints are: 
-```
-http://localhost:8000/layout/yolox/pdf
-http://localhost:8000/layout/yolox/image
-```
-For example:
-```
-curl -X 'POST' 'http://localhost:8000/layout/yolox/image' \
--F 'file=@sample-docs/test-image.jpg' \
- | jq -C | less -R
-
-curl -X 'POST' 'http://localhost:8000/layout/yolox/pdf' \
--F 'file=@sample-docs/loremipsum.pdf' \
- | jq -C | less -R
-```
-
-If your PDF file doesn't have text embedded you can force the use of OCR with
-the parameter force_ocr=True:
-```
-curl -X 'POST' 'http://localhost:8000/layout/yolox/pdf' \
--F 'file=@sample-docs/loremipsum-flat.pdf' \
--F force_ocr=true 
- | jq -C | less -R
-```
-
-or in local:
-
-```
-layout = yolox_local_inference(filename, type="pdf")
-```
-
 ## Security Policy
 
 See our [security policy](https://github.com/Unstructured-IO/unstructured-inference/security/policy) for

README.md

@@ -1,7 +1,5 @@
-fastapi
 layoutparser[layoutmodels,tesseract]
 python-multipart
-uvicorn
 huggingface-hub
 opencv-python!=4.7.0.68
 onnxruntime

requirements/base.in

@@ -6,52 +6,44 @@
 #
 antlr4-python3-runtime==4.9.3
     # via omegaconf
-anyio==3.6.2
-    # via starlette
-certifi==2022.12.7
+certifi==2023.5.7
     # via requests
 cffi==1.15.1
     # via cryptography
 charset-normalizer==3.1.0
     # via
     #   pdfminer-six
     #   requests
-click==8.1.3
-    # via uvicorn
 coloredlogs==15.0.1
     # via onnxruntime
 contourpy==1.0.7
     # via matplotlib
-cryptography==40.0.1
+cryptography==40.0.2
     # via pdfminer-six
 cycler==0.11.0
     # via matplotlib
 effdet==0.3.0
     # via layoutparser
-fastapi==0.95.0
-    # via -r requirements/base.in
-filelock==3.10.7
+filelock==3.12.0
     # via
     #   huggingface-hub
     #   torch
     #   transformers
-flatbuffers==23.3.3
+flatbuffers==23.5.9
     # via onnxruntime
-fonttools==4.39.3
+fonttools==4.39.4
     # via matplotlib
-h11==0.14.0
-    # via uvicorn
-huggingface-hub==0.13.3
+fsspec==2023.5.0
+    # via huggingface-hub
+huggingface-hub==0.14.1
     # via
     #   -r requirements/base.in
     #   timm
     #   transformers
 humanfriendly==10.0
     # via coloredlogs
 idna==3.4
-    # via
-    #   anyio
-    #   requests
+    # via requests
 importlib-resources==5.12.0
     # via matplotlib
 iopath==0.1.10
@@ -70,7 +62,7 @@ mpmath==1.3.0
     # via sympy
 networkx==3.1
     # via torch
-numpy==1.24.2
+numpy==1.24.3
     # via
     #   contourpy
     #   layoutparser
@@ -90,20 +82,20 @@ opencv-python==4.7.0.72
     # via
     #   -r requirements/base.in
     #   layoutparser
-packaging==23.0
+packaging==23.1
     # via
     #   huggingface-hub
     #   matplotlib
     #   onnxruntime
     #   pytesseract
     #   transformers
-pandas==2.0.0
+pandas==2.0.1
     # via layoutparser
 pdf2image==1.16.3
     # via layoutparser
 pdfminer-six==20221105
     # via pdfplumber
-pdfplumber==0.8.0
+pdfplumber==0.9.0
     # via layoutparser
 pillow==9.5.0
     # via
@@ -115,14 +107,12 @@ pillow==9.5.0
     #   torchvision
 portalocker==2.7.0
     # via iopath
-protobuf==4.22.1
+protobuf==4.23.1
     # via onnxruntime
 pycocotools==2.0.6
     # via effdet
 pycparser==2.21
     # via cffi
-pydantic==1.10.7
-    # via fastapi
 pyparsing==3.0.9
     # via matplotlib
 pytesseract==0.3.10
@@ -142,36 +132,34 @@ pyyaml==6.0
     #   omegaconf
     #   timm
     #   transformers
-regex==2023.3.23
+regex==2023.5.5
     # via transformers
-requests==2.28.2
+requests==2.30.0
     # via
     #   huggingface-hub
     #   torchvision
     #   transformers
+safetensors==0.3.1
+    # via timm
 scipy==1.10.1
     # via layoutparser
 six==1.16.0
     # via python-dateutil
-sniffio==1.3.0
-    # via anyio
-starlette==0.26.1
-    # via fastapi
-sympy==1.11.1
+sympy==1.12
     # via
     #   onnxruntime
     #   torch
-timm==0.6.13
+timm==0.9.2
     # via effdet
-tokenizers==0.13.2
+tokenizers==0.13.3
     # via transformers
-torch==2.0.0
+torch==2.0.1
     # via
     #   effdet
     #   layoutparser
     #   timm
     #   torchvision
-torchvision==0.15.1
+torchvision==0.15.2
     # via
     #   effdet
     #   layoutparser
@@ -181,21 +169,17 @@ tqdm==4.65.0
     #   huggingface-hub
     #   iopath
     #   transformers
-transformers==4.27.4
+transformers==4.29.2
     # via -r requirements/base.in
 typing-extensions==4.5.0
     # via
     #   huggingface-hub
     #   iopath
-    #   pydantic
-    #   starlette
     #   torch
 tzdata==2023.3
     # via pandas
-urllib3==1.26.15
+urllib3==2.0.2
     # via requests
-uvicorn==0.21.1
-    # via -r requirements/base.in
 wand==0.6.11
     # via pdfplumber
 zipp==3.15.0

requirements/base.txt

@@ -3,3 +3,8 @@
 jupyter
 ipython
 pip-tools
+# NOTE(alan): Pinned to prevent errors that occur with newer versions, see
+# https://discourse.jupyter.org/t/jupyter-notebook-zmq-message-arrived-on-closed-channel-error/17869
+jupyter_client==7.3.4
+jupyter_server==1.23.6
+tornado==6.1