Add API endpoints for file conversion

Dockerfile

@@ -12,7 +12,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     ffmpeg \
     && rm -rf /var/lib/apt/lists/*
 
-RUN pip install markitdown
+RUN pip install markitdown fastapi uvicorn
 
 # Default USERID and GROUPID
 ARG USERID=10000
@@ -20,4 +20,4 @@ ARG GROUPID=10000
 
 USER $USERID:$GROUPID
 
-ENTRYPOINT [ "markitdown" ]
+ENTRYPOINT ["uvicorn", "markitdown.api:app", "--host", "0.0.0.0", "--port", "8000"]

README.md

@@ -66,6 +66,29 @@ result = md.convert("example.jpg")
 print(result.text_content)
 ```
 
+### RESTful API
+
+MarkItDown also provides a RESTful API using FastAPI. You can deploy the application on Vercel or another hosting service.
+
+#### Endpoints
+
+- `GET /`: Returns a welcome message.
+- `POST /convert`: Converts an uploaded file to Markdown.
+
+#### Example Usage
+
+Using `curl`:
+
+```sh
+curl -X POST "http://<your-deployment-url>/convert" -F "file=@path-to-file.pdf"
+```
+
+Using `httpie`:
+
+```sh
+http --form POST "http://<your-deployment-url>/convert" file@path-to-file.pdf
+```
+
 ### Docker
 
 ```sh

src/markitdown/api.py

@@ -0,0 +1,21 @@
+from fastapi import FastAPI, HTTPException, UploadFile, File
+from markitdown import MarkItDown, UnsupportedFormatException, FileConversionException
+
+app = FastAPI()
+
+@app.get("/")
+async def root():
+    return {"message": "Welcome to the MarkItDown API"}
+
+@app.post("/convert")
+async def convert(file: UploadFile = File(...)):
+    try:
+        markitdown = MarkItDown()
+        result = markitdown.convert_stream(file.file, file_extension=file.filename.split('.')[-1])
+        return {"title": result.title, "text_content": result.text_content}
+    except UnsupportedFormatException:
+        raise HTTPException(status_code=400, detail="Unsupported file format")
+    except FileConversionException:
+        raise HTTPException(status_code=500, detail="File conversion error")
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))

tests/test_api.py

@@ -0,0 +1,28 @@
+import pytest
+from fastapi.testclient import TestClient
+from markitdown.api import app
+
+client = TestClient(app)
+
+def test_root():
+    response = client.get("/")
+    assert response.status_code == 200
+    assert response.json() == {"message": "Welcome to the MarkItDown API"}
+
+def test_convert_success():
+    with open("tests/test_files/test.docx", "rb") as file:
+        response = client.post("/convert", files={"file": file})
+    assert response.status_code == 200
+    assert "AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation" in response.json()["text_content"]
+
+def test_convert_unsupported_format():
+    with open("tests/test_files/test.unsupported", "rb") as file:
+        response = client.post("/convert", files={"file": file})
+    assert response.status_code == 400
+    assert response.json() == {"detail": "Unsupported file format"}
+
+def test_convert_conversion_error():
+    with open("tests/test_files/test_corrupted.docx", "rb") as file:
+        response = client.post("/convert", files={"file": file})
+    assert response.status_code == 500
+    assert response.json() == {"detail": "File conversion error"}