Committing changes to main.py that works locally.

.python-version

@@ -0,0 +1 @@
+3.11

.vscode/extensions.json

@@ -0,0 +1,5 @@
+{
+    "recommendations": [
+        "ms-azuretools.vscode-docker"
+    ]
+}

Dockerfile

@@ -1,16 +1,21 @@
-# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
 # you will also find guides on how best to write your Dockerfile
 
 FROM python:3.9
 
+# The two following lines are requirements for the Dev Mode to be functional
+# Learn more about the Dev Mode at https://huggingface.co/dev-mode-explorers
 RUN useradd -m -u 1000 user
-USER user
-ENV PATH="/home/user/.local/bin:$PATH"
-
 WORKDIR /app
 
 COPY --chown=user ./requirements.txt requirements.txt
 RUN pip install --no-cache-dir --upgrade -r requirements.txt
 
 COPY --chown=user . /app
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+
+USER user
+
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -1,8 +1,16 @@
 from fastapi import FastAPI
+from transformers import pipeline
 
 app = FastAPI()
+pipe_flan = pipeline("text2text-generation", model="google/flan-t5-small")
 
 @app.get("/")
 def greet_json():
     return {"Hello": "World!"}
 
+
+
+@app.get("/infer_t5")
+def t5(input):
+    output = pipe_flan(input)
+    return {"output": output[0]["generated_text"]}

main.py

@@ -0,0 +1,20 @@
+from fastapi import FastAPI
+from fastapi.responses import FileResponse
+from fastapi.staticfiles import StaticFiles
+from transformers import pipeline
+
+app = FastAPI()
+
+# Serve static files at /static
+app.mount("/static", StaticFiles(directory="static", html=True), name="static")
+
+pipe_flan = pipeline("text2text-generation", model="google/flan-t5-small")
+
+@app.get("/")
+def index():
+    return FileResponse("static/index.html", media_type="text/html")
+
+@app.get("/infer_t5")
+def t5(input: str):
+    output = pipe_flan(input)
+    return {"output": output[0]["generated_text"]}

pyproject.toml

@@ -0,0 +1,14 @@
+[project]
+name = "hf-mcp-server"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.11"
+dependencies = [
+    "fastapi==0.74.*",
+    "requests==2.27.*",
+    "sentencepiece==0.1.*",
+    "torch>1.12.0",
+    "transformers==4.*",
+    "uvicorn[standard]==0.17.*",
+]

requirements.txt

@@ -1,3 +1,7 @@
+fastapi==0.74.*
+requests==2.27.*
+sentencepiece==0.1.*
+torch>1.12.0
+transformers==4.*
+uvicorn[standard]==0.17.*
 fastapi
-uvicorn[standard]
-

static/index.html

@@ -0,0 +1,24 @@
+<main>
+  <section id="text-gen">
+    <h2>Text generation using Flan T5</h2>
+    <p>
+      Model:
+      <a
+        href="https://huggingface.co/google/flan-t5-small"
+        rel="noreferrer"
+        target="_blank"
+        >google/flan-t5-small
+      </a>
+    </p>
+    <form class="text-gen-form">
+      <label for="text-gen-input">Text prompt</label>
+      <input
+        id="text-gen-input"
+        type="text"
+        value="German: There are many ducks"
+      />
+      <button id="text-gen-submit">Submit</button>
+      <p class="text-gen-output"></p>
+    </form>
+  </section>
+</main>

static/script.js

@@ -0,0 +1,17 @@
+const textGenForm = document.querySelector(".text-gen-form");
+
+const translateText = async (text) => {
+  const inferResponse = await fetch(`infer_t5?input=${text}`);
+  const inferJson = await inferResponse.json();
+
+  return inferJson.output;
+};
+
+textGenForm.addEventListener("submit", async (event) => {
+  event.preventDefault();
+
+  const textGenInput = document.getElementById("text-gen-input");
+  const textGenParagraph = document.querySelector(".text-gen-output");
+
+  textGenParagraph.textContent = await translateText(textGenInput.value);
+});